disbib.bib

% Generated by Paperpile. Check out https://paperpile.com for more information.
% BibTeX export options can be customized via Settings -> BibTeX.


@ARTICLE{Labrie2010-jh,
  title    = "Bacteriophage resistance mechanisms",
  author   = "Labrie, Simon J and Samson, Julie E and Moineau, Sylvain",
  abstract = "Phages are now acknowledged as the most abundant microorganisms
              on the planet and are also possibly the most diversified. This
              diversity is mostly driven by their dynamic adaptation when
              facing selective pressure such as phage resistance mechanisms,
              which are widespread in bacterial hosts. When infecting bacterial
              cells, phages face a range of antiviral mechanisms, and they have
              evolved multiple tactics to avoid, circumvent or subvert these
              mechanisms in order to thrive in most environments. In this
              Review, we highlight the most important antiviral mechanisms of
              bacteria as well as the counter-attacks used by phages to evade
              these systems.",
  journal  = "Nat. Rev. Microbiol.",
  volume   =  8,
  number   =  5,
  pages    = "317--327",
  month    =  may,
  year     =  2010,
  language = "en"
}

@MISC{Mayneris-Perxachs2022-wi,
  title   = "Caudovirales bacteriophages are associated with improved executive
             function and memory in flies, mice, and humans",
  author  = "Mayneris-Perxachs, Jordi and Castells-Nobau, Anna and
             Arnoriaga-Rodr{\'\i}guez, Mar{\'\i}a and Garre-Olmo, Josep and
             Puig, Josep and Ramos, Rafael and Mart{\'\i}nez-Hern{\'a}ndez,
             Francisco and Burokas, Aurelijus and Coll, Cl{\`a}udia and
             Moreno-Navarrete, Jos{\'e} Maria and Zapata-Tona, Cristina and
             Pedraza, Salvador and P{\'e}rez-Brocal, Vicente and
             Rami{\'o}-Torrent{\`a}, Llu{\'\i}s and Ricart, Wifredo and Moya,
             Andr{\'e}s and Mart{\'\i}nez-Garc{\'\i}a, Manuel and Maldonado,
             Rafael and Fern{\'a}ndez-Real, Jos{\'e}-Manuel",
  journal = "Cell Host \& Microbe",
  volume  =  30,
  number  =  3,
  pages   = "340--356.e8",
  year    =  2022
}

@ARTICLE{Roux2019-dc,
  title    = "Minimum Information about an Uncultivated Virus Genome ({MIUViG})",
  author   = "Roux, Simon and Adriaenssens, Evelien M and Dutilh, Bas E and
              Koonin, Eugene V and Kropinski, Andrew M and Krupovic, Mart and
              Kuhn, Jens H and Lavigne, Rob and Brister, J Rodney and Varsani,
              Arvind and Amid, Clara and Aziz, Ramy K and Bordenstein, Seth R
              and Bork, Peer and Breitbart, Mya and Cochrane, Guy R and Daly,
              Rebecca A and Desnues, Christelle and Duhaime, Melissa B and
              Emerson, Joanne B and Enault, Fran{\c c}ois and Fuhrman, Jed A
              and Hingamp, Pascal and Hugenholtz, Philip and Hurwitz, Bonnie L
              and Ivanova, Natalia N and Labont{\'e}, Jessica M and Lee,
              Kyung-Bum and Malmstrom, Rex R and Martinez-Garcia, Manuel and
              Mizrachi, Ilene Karsch and Ogata, Hiroyuki and P{\'a}ez-Espino,
              David and Petit, Marie-Agn{\`e}s and Putonti, Catherine and
              Rattei, Thomas and Reyes, Alejandro and Rodriguez-Valera,
              Francisco and Rosario, Karyna and Schriml, Lynn and Schulz,
              Frederik and Steward, Grieg F and Sullivan, Matthew B and
              Sunagawa, Shinichi and Suttle, Curtis A and Temperton, Ben and
              Tringe, Susannah G and Thurber, Rebecca Vega and Webster, Nicole
              S and Whiteson, Katrine L and Wilhelm, Steven W and Wommack, K
              Eric and Woyke, Tanja and Wrighton, Kelly C and Yilmaz, Pelin and
              Yoshida, Takashi and Young, Mark J and Yutin, Natalya and Allen,
              Lisa Zeigler and Kyrpides, Nikos C and Eloe-Fadrosh, Emiley A",
  abstract = "We present an extension of the Minimum Information about any (x)
              Sequence (MIxS) standard for reporting sequences of uncultivated
              virus genomes. Minimum Information about an Uncultivated Virus
              Genome (MIUViG) standards were developed within the Genomic
              Standards Consortium framework and include virus origin, genome
              quality, genome annotation, taxonomic classification,
              biogeographic distribution and in silico host prediction.
              Community-wide adoption of MIUViG standards, which complement the
              Minimum Information about a Single Amplified Genome (MISAG) and
              Metagenome-Assembled Genome (MIMAG) standards for uncultivated
              bacteria and archaea, will improve the reporting of uncultivated
              virus genomes in public databases. In turn, this should enable
              more robust comparative studies and a systematic exploration of
              the global virosphere.",
  journal  = "Nat. Biotechnol.",
  volume   =  37,
  number   =  1,
  pages    = "29--37",
  month    =  jan,
  year     =  2019,
  keywords = "phamb;phamb;1st\_regular\_assessment",
  language = "en"
}

@ARTICLE{Zaragoza-Solas2022-ky,
  title    = "{Long-Read} Metagenomics Improves the Recovery of Viral Diversity
              from Complex Natural Marine Samples",
  author   = "Zaragoza-Solas, Asier and Haro-Moreno, Jose M and
              Rodriguez-Valera, Francisco and L{\'o}pez-P{\'e}rez, Mario",
  abstract = "The recovery of DNA from viromes is a major obstacle in the use
              of long-read sequencing to study their genomes. For this reason,
              the use of cellular metagenomes (>0.2-$\mu$m size range) emerges
              as an interesting complementary tool, since they contain large
              amounts of naturally amplified viral genomes from prelytic
              replication. We have applied second-generation (Illumina NextSeq;
              short reads) and third-generation (PacBio Sequel II; long reads)
              sequencing to compare the diversity and features of the viral
              community in a marine sample obtained from offshore waters of the
              western Mediterranean. We found that a major wedge of the
              expected marine viral diversity was directly recovered by the raw
              PacBio circular consensus sequencing (CCS) reads. More than
              30,000 sequences were detected only in this data set, with no
              homologues in the long- and short-read assembly, and ca. 26,000
              had no homologues in the large data set of the Global Ocean
              Virome 2 (GOV2), highlighting the information gap created by the
              assembly bias. At the level of complete viral genomes, the
              performance was similar in both approaches. However, the hybrid
              long- and short-read assembly provided the longest average length
              of the sequences and improved the host assignment. Although no
              novel major clades of viruses were found, there was an increase
              in the intraclade genomic diversity recovered by long reads that
              produced an enriched assessment of the real diversity and allowed
              the discovery of novel genes with biotechnological potential
              (e.g., endolysin genes). IMPORTANCE We explored the vast genetic
              diversity of environmental viruses by using a combination of
              cellular metagenome (as opposed to virome) sequencing using
              high-fidelity long-read sequences (in this case, PacBio CCS).
              This approach resulted in the recovery of a representative sample
              of the viral population, and it performed better (more phage
              contigs, larger average contig size) than Illumina sequencing
              applied to the same sample. By this approach, the many biases of
              assembly are avoided, as the CCS reads recovers (typically around
              5 kb) complete genes and even operons, resulting in a better
              discovery of the viral gene diversity based on viral marker
              proteins. Thus, biotechnologically promising genes, such as
              endolysin genes, can be very efficiently searched with this
              approach. In addition, hybrid assembly produces more complete and
              longer contigs, which is particularly important for studying
              little-known viral groups such as the nucleocytoplasmic large DNA
              viruses (NCLDV).",
  journal  = "mSystems",
  volume   =  7,
  number   =  3,
  pages    = "e0019222",
  month    =  jun,
  year     =  2022,
  keywords = "PacBio CCS long reads; bacteriophage; long-read sequencing;
              metagenome; viral diversity; virome",
  language = "en"
}

@ARTICLE{Zuo2020-dz,
  title    = "{Human-Gut-DNA} Virome Variations across Geography, Ethnicity,
              and Urbanization",
  author   = "Zuo, Tao and Sun, Yang and Wan, Yating and Yeoh, Yun Kit and
              Zhang, Fen and Cheung, Chun Pan and Chen, Nan and Luo, Juan and
              Wang, Wen and Sung, Joseph J Y and Chan, Paul K S and Wang,
              Kunhua and Chan, Francis K L and Miao, Yinglei and Ng, Siew C",
  abstract = "The human-gut-DNA virome is highly diverse and individual
              specific, but little is known of its variation at a population
              level. Here, we report the fecal DNA virome of 930 healthy adult
              subjects from two regions in China (Hong Kong and Yunnan)
              spanning six ethnicities (Han, Zang, Miao, Bai, Dai, and Hani),
              and including urban and rural residents for each ethnicity.
              Twenty host factors were found to significantly correlate with
              the human-gut virome variation, with geography carrying the
              strongest impact and ethnicity-distinct diets associating with
              certain viral species. Urbanization enhances interindividual
              dissimilarities between gut viromes, with the duration of urban
              residence associating with multiple bacteriophages, including
              Lactobacillus phage and Lactococcus phage. Overall, the gut
              virome presents more heterogeneity relative to the bacterial
              microbiome across the examined Chinese populations. This study
              highlights population-based variations and the importance of host
              and environmental factors in shaping the DNA virome in the human
              gut.",
  journal  = "Cell Host Microbe",
  volume   =  28,
  number   =  5,
  pages    = "741--751.e4",
  month    =  nov,
  year     =  2020,
  keywords = "cholesterol; diet; ethnicity; geography; metacommunity; metadata;
              region; urbanization; virome",
  language = "en"
}

@ARTICLE{Statnikov2013-gz,
  title    = "A comprehensive evaluation of multicategory classification
              methods for microbiomic data",
  author   = "Statnikov, Alexander and Henaff, Mikael and Narendra, Varun and
              Konganti, Kranti and Li, Zhiguo and Yang, Liying and Pei, Zhiheng
              and Blaser, Martin J and Aliferis, Constantin F and Alekseyenko,
              Alexander V",
  abstract = "BACKGROUND: Recent advances in next-generation DNA sequencing
              enable rapid high-throughput quantitation of microbial community
              composition in human samples, opening up a new field of
              microbiomics. One of the promises of this field is linking
              abundances of microbial taxa to phenotypic and physiological
              states, which can inform development of new diagnostic,
              personalized medicine, and forensic modalities. Prior research
              has demonstrated the feasibility of applying machine learning
              methods to perform body site and subject classification with
              microbiomic data. However, it is currently unknown which
              classifiers perform best among the many available alternatives
              for classification with microbiomic data. RESULTS: In this work,
              we performed a systematic comparison of 18 major classification
              methods, 5 feature selection methods, and 2 accuracy metrics
              using 8 datasets spanning 1,802 human samples and various
              classification tasks: body site and subject classification and
              diagnosis. CONCLUSIONS: We found that random forests, support
              vector machines, kernel ridge regression, and Bayesian logistic
              regression with Laplace priors are the most effective machine
              learning techniques for performing accurate classification from
              these microbiomic data.",
  journal  = "Microbiome",
  volume   =  1,
  number   =  1,
  pages    = "11",
  month    =  apr,
  year     =  2013,
  language = "en"
}

@ARTICLE{McInnes2017-up,
  title     = "hdbscan: Hierarchical density based clustering",
  author    = "McInnes, Leland and Healy, John and Astels, Steve",
  abstract  = "HDBSCAN: Hierarchical Density-Based Spatial Clustering of
               Applications with Noise (Campello, Moulavi, and Sander 2013),
               (Campello et al. 2015). Performs DBSCAN over varying epsilon
               values and integrates the result to find a clustering that gives
               the best stability over epsilon. This allows HDBSCAN to find
               clusters of varying densities (unlike DBSCAN), and be more
               robust to parameter selection. The library also includes support
               for Robust Single Linkage clustering (Chaudhuri et al. 2014),
               (Chaudhuri and Dasgupta 2010), GLOSH outlier detection (Campello
               et al. 2015), and tools for visualizing and exploring cluster
               structures. Finally support for prediction and soft clustering
               is also available.",
  journal   = "J. Open Source Softw.",
  publisher = "The Open Journal",
  volume    =  2,
  number    =  11,
  pages     = "205",
  month     =  mar,
  year      =  2017,
  copyright = "http://creativecommons.org/licenses/by/4.0/"
}

@ARTICLE{Wooley2010-mr,
  title    = "Metagenomics: Facts and Artifacts, and Computational Challenges",
  author   = "Wooley, John C and Ye, Yuzhen",
  abstract = "Metagenomics is the study of microbial communities sampled
              directly from their natural environment, without prior culturing.
              By enabling an analysis of populations including many (so-far)
              unculturable and often unknown microbes, metagenomics is
              revolutionizing the field of microbiology, and has excited
              researchers in many disciplines that could benefit from the study
              of environmental microbes, including those in ecology,
              environmental sciences, and biomedicine. Specific computational
              and statistical tools have been developed for metagenomic data
              analysis and comparison. New studies, however, have revealed
              various kinds of artifacts present in metagenomics data caused by
              limitations in the experimental protocols and/or inadequate data
              analysis procedures, which often lead to incorrect conclusions
              about a microbial community. Here, we review some of the
              artifacts, such as overestimation of species diversity and
              incorrect estimation of gene family frequencies, and discuss
              emerging computational approaches to address them. We also review
              potential challenges that metagenomics may encounter with the
              extensive application of next-generation sequencing (NGS)
              techniques.",
  journal  = "J. Comput. Sci. Technol.",
  volume   =  25,
  number   =  1,
  pages    = "71--81",
  month    =  jan,
  year     =  2010
}

@ARTICLE{Pride2003-qx,
  title    = "Evolutionary implications of microbial genome tetranucleotide
              frequency biases",
  author   = "Pride, David T and Meinersmann, Richard J and Wassenaar, Trudy M
              and Blaser, Martin J",
  abstract = "We compared nucleotide usage pattern conservation for related
              prokaryotes by examining the representation of DNA
              tetranucleotide combinations in 27 representative microbial
              genomes. For each of the organisms studied, tetranucleotide usage
              departures from expectations (TUD) were shared between related
              organisms using both Markov chain analysis and a zero-order
              Markov method. Individual strains, multiple chromosomes,
              plasmids, and bacteriophages share TUDs within a species. TUDs
              varied between coding and noncoding DNA. Grouping prokaryotes
              based on TUD profiles resulted in relationships with important
              differences from those based on 16S rRNA phylogenies, which may
              reflect unequal rates of evolution of nucleotide usage patterns
              following divergence of particular organisms from a common
              ancestor. By both symmetrical tree distance and likelihood
              analysis, phylogenetic trees based on TUD profiles demonstrate a
              level of congruence with 16S rRNA trees similar to that of both
              RpoA and RecA trees. Congruence of these trees indicates that
              there exists phylogenetic signal in TUD patterns, most prominent
              in coding region DNA. Because relationships demonstrated in
              TUD-based analyses utilize whole genomes, they should be
              considered complementary to phylogenies based on single genetic
              elements, such as 16S rRNA.",
  journal  = "Genome Res.",
  volume   =  13,
  number   =  2,
  pages    = "145--158",
  month    =  feb,
  year     =  2003,
  language = "en"
}

@ARTICLE{Round2009-lt,
  title    = "The gut microbiota shapes intestinal immune responses during
              health and disease",
  author   = "Round, June L and Mazmanian, Sarkis K",
  abstract = "Immunological dysregulation is the cause of many non-infectious
              human diseases such as autoimmunity, allergy and cancer. The
              gastrointestinal tract is the primary site of interaction between
              the host immune system and microorganisms, both symbiotic and
              pathogenic. In this Review we discuss findings indicating that
              developmental aspects of the adaptive immune system are
              influenced by bacterial colonization of the gut. We also
              highlight the molecular pathways that mediate host-symbiont
              interactions that regulate proper immune function. Finally, we
              present recent evidence to support that disturbances in the
              bacterial microbiota result in dysregulation of adaptive immune
              cells, and this may underlie disorders such as inflammatory bowel
              disease. This raises the possibility that the mammalian immune
              system, which seems to be designed to control microorganisms, is
              in fact controlled by microorganisms.",
  journal  = "Nat. Rev. Immunol.",
  volume   =  9,
  number   =  5,
  pages    = "313--323",
  month    =  may,
  year     =  2009,
  language = "en"
}

@ARTICLE{Barr_undated-cn,
  title   = "Bacteriophage adhering to mucus provide a non--host-derived
             immunity",
  author  = "{Barr} and {Auro} and {Furlan} and {others}",
  journal = "Proc. Estonian Acad. Sci. Biol. Ecol."
}

@ARTICLE{Wu2021-bd,
  title    = "{DeePhage}: distinguishing virulent and temperate phage-derived
              sequences in metavirome data with a deep learning approach",
  author   = "Wu, Shufang and Fang, Zhencheng and Tan, Jie and Li, Mo and Wang,
              Chunhui and Guo, Qian and Xu, Congmin and Jiang, Xiaoqing and
              Zhu, Huaiqiu",
  abstract = "BACKGROUND: Prokaryotic viruses referred to as phages can be
              divided into virulent and temperate phages. Distinguishing
              virulent and temperate phage-derived sequences in metavirome data
              is important for elucidating their different roles in
              interactions with bacterial hosts and regulation of microbial
              communities. However, there is no experimental or computational
              approach to effectively classify their sequences in
              culture-independent metavirome. We present a new computational
              method, DeePhage, which can directly and rapidly judge each read
              or contig as a virulent or temperate phage-derived fragment.
              FINDINGS: DeePhage uses a ``one-hot'' encoding form to represent
              DNA sequences in detail. Sequence signatures are detected via a
              convolutional neural network to obtain valuable local features.
              The accuracy of DeePhage on 5-fold cross-validation reaches as
              high as 89\%, nearly 10\% and 30\% higher than that of 2 similar
              tools, PhagePred and PHACTS. On real metavirome, DeePhage
              correctly predicts the highest proportion of contigs when using
              BLAST as annotation, without apparent preferences. Besides,
              DeePhage reduces running time vs PhagePred and PHACTS by 245 and
              810 times, respectively, under the same computational
              configuration. By direct detection of the temperate viral
              fragments from metagenome and metavirome, we furthermore propose
              a new strategy to explore phage transformations in the microbial
              community. The ability to detect such transformations provides us
              a new insight into the potential treatment for human disease.
              CONCLUSIONS: DeePhage is a novel tool developed to rapidly and
              efficiently identify 2 kinds of phage fragments especially for
              metagenomics analysis. DeePhage is freely available via
              http://cqb.pku.edu.cn/ZhuLab/DeePhage or
              https://github.com/shufangwu/DeePhage.",
  journal  = "Gigascience",
  volume   =  10,
  number   =  9,
  month    =  sep,
  year     =  2021,
  language = "en"
}

@ARTICLE{Van_der_Post2019-ez,
  title    = "Structural weakening of the colonic mucus barrier is an early
              event in ulcerative colitis pathogenesis",
  author   = "van der Post, Sjoerd and Jabbar, Karolina S and Birchenough,
              George and Arike, Liisa and Akhtar, Noreen and Sjovall, Henrik
              and Johansson, Malin E V and Hansson, Gunnar C",
  abstract = "OBJECTIVE: The colonic inner mucus layer protects us from
              pathogens and commensal-induced inflammation, and has been shown
              to be defective in active UC. The aim of this study was to
              determine the underlying compositional alterations, their
              molecular background and potential contribution to UC
              pathogenesis. DESIGN: In this single-centre case-control study,
              sigmoid colon biopsies were obtained from patients with UC with
              ongoing inflammation (n=36) or in remission (n=28), and from 47
              patients without colonic disease. Mucus samples were collected
              from biopsies ex vivo, and their protein composition analysed by
              nanoliquid chromatography-tandem mass spectrometry. Mucus
              penetrability and goblet cell responses to microbial stimulus
              were assessed in a subset of patients. RESULTS: The core mucus
              proteome was found to consist of a small set of 29
              secreted/transmembrane proteins. In active UC, major structural
              mucus components including the mucin MUC2 (p<0.0001) were
              reduced, also in non-inflamed segments. Active UC was associated
              with decreased numbers of sentinel goblet cells and attenuation
              of the goblet cell secretory response to microbial challenge.
              Abnormal penetrability of the inner mucus layer was observed in a
              subset of patients with UC (12/40; 30\%). Proteomic alterations
              in penetrable mucus samples included a reduction of the SLC26A3
              apical membrane anion exchanger, which supplies bicarbonate
              required for colonic mucin barrier formation. CONCLUSION: Core
              mucus structural components were reduced in active UC. These
              alterations were associated with attenuation of the goblet cell
              secretory response to microbial challenge, but occurred
              independent of local inflammation. Thus, mucus abnormalities are
              likely to contribute to UC pathogenesis.",
  journal  = "Gut",
  volume   =  68,
  number   =  12,
  pages    = "2142--2151",
  month    =  dec,
  year     =  2019,
  keywords = "mucins; mucosal barrier; mucosal protection; mucus; ulcerative
              colitis",
  language = "en"
}

@ARTICLE{Norman2015-eb,
  title    = "Disease-specific alterations in the enteric virome in
              inflammatory bowel disease",
  author   = "Norman, Jason M and Handley, Scott A and Baldridge, Megan T and
              Droit, Lindsay and Liu, Catherine Y and Keller, Brian C and
              Kambal, Amal and Monaco, Cynthia L and Zhao, Guoyan and Fleshner,
              Phillip and Stappenbeck, Thaddeus S and McGovern, Dermot P B and
              Keshavarzian, Ali and Mutlu, Ece A and Sauk, Jenny and Gevers,
              Dirk and Xavier, Ramnik J and Wang, David and Parkes, Miles and
              Virgin, Herbert W",
  abstract = "Decreases in the diversity of enteric bacterial populations are
              observed in patients with Crohn's disease (CD) and ulcerative
              colitis (UC). Less is known about the virome in these diseases.
              We show that the enteric virome is abnormal in CD and UC
              patients. In-depth analysis of preparations enriched for free
              virions in the intestine revealed that CD and UC were associated
              with a significant expansion of Caudovirales bacteriophages. The
              viromes of CD and UC patients were disease and cohort specific.
              Importantly, it did not appear that expansion and diversification
              of the enteric virome was secondary to changes in bacterial
              populations. These data support a model in which changes in the
              virome may contribute to intestinal inflammation and bacterial
              dysbiosis. We conclude that the virome is a candidate for
              contributing to, or being a biomarker for, human inflammatory
              bowel disease and speculate that the enteric virome may play a
              role in other diseases.",
  journal  = "Cell",
  volume   =  160,
  number   =  3,
  pages    = "447--460",
  month    =  jan,
  year     =  2015,
  keywords = "phamb;1st\_regular\_assessment",
  language = "en"
}

@ARTICLE{Pasolli2016-pi,
  title    = "Machine Learning Meta-analysis of Large Metagenomic Datasets:
              Tools and Biological Insights",
  author   = "Pasolli, Edoardo and Truong, Duy Tin and Malik, Faizan and
              Waldron, Levi and Segata, Nicola",
  abstract = "Shotgun metagenomic analysis of the human associated microbiome
              provides a rich set of microbial features for prediction and
              biomarker discovery in the context of human diseases and health
              conditions. However, the use of such high-resolution microbial
              features presents new challenges, and validated computational
              tools for learning tasks are lacking. Moreover, classification
              rules have scarcely been validated in independent studies, posing
              questions about the generality and generalization of
              disease-predictive models across cohorts. In this paper, we
              comprehensively assess approaches to metagenomics-based
              prediction tasks and for quantitative assessment of the strength
              of potential microbiome-phenotype associations. We develop a
              computational framework for prediction tasks using quantitative
              microbiome profiles, including species-level relative abundances
              and presence of strain-specific markers. A comprehensive
              meta-analysis, with particular emphasis on generalization across
              cohorts, was performed in a collection of 2424 publicly available
              metagenomic samples from eight large-scale studies.
              Cross-validation revealed good disease-prediction capabilities,
              which were in general improved by feature selection and use of
              strain-specific markers instead of species-level taxonomic
              abundance. In cross-study analysis, models transferred between
              studies were in some cases less accurate than models tested by
              within-study cross-validation. Interestingly, the addition of
              healthy (control) samples from other studies to training sets
              improved disease prediction capabilities. Some microbial species
              (most notably Streptococcus anginosus) seem to characterize
              general dysbiotic states of the microbiome rather than
              connections with a specific disease. Our results in modelling
              features of the ``healthy'' microbiome can be considered a first
              step toward defining general microbial dysbiosis. The software
              framework, microbiome profiles, and metadata for thousands of
              samples are publicly available at
              http://segatalab.cibio.unitn.it/tools/metaml.",
  journal  = "PLoS Comput. Biol.",
  volume   =  12,
  number   =  7,
  pages    = "e1004977",
  month    =  jul,
  year     =  2016,
  language = "en"
}

@ARTICLE{Gao2022-ux,
  title    = "Prokaryotic innate immunity through pattern recognition of
              conserved viral proteins",
  author   = "Gao, Linyi Alex and Wilkinson, Max E and Strecker, Jonathan and
              Makarova, Kira S and Macrae, Rhiannon K and Koonin, Eugene V and
              Zhang, Feng",
  abstract = "Many organisms have evolved specialized immune
              pattern-recognition receptors, including nucleotide-binding
              oligomerization domain-like receptors (NLRs) of the STAND
              superfamily that are ubiquitous in plants, animals, and fungi.
              Although the roles of NLRs in eukaryotic immunity are well
              established, it is unknown whether prokaryotes use similar
              defense mechanisms. Here, we show that antiviral STAND (Avs)
              homologs in bacteria and archaea detect hallmark viral proteins,
              triggering Avs tetramerization and the activation of diverse
              N-terminal effector domains, including DNA endonucleases, to
              abrogate infection. Cryo-electron microscopy reveals that Avs
              sensor domains recognize conserved folds, active-site residues,
              and enzyme ligands, allowing a single Avs receptor to detect a
              wide variety of viruses. These findings extend the paradigm of
              pattern recognition of pathogen-specific proteins across all
              three domains of life.",
  journal  = "Science",
  volume   =  377,
  number   =  6607,
  pages    = "eabm4096",
  month    =  aug,
  year     =  2022,
  language = "en"
}

@MISC{Parks2017-jk,
  title   = "Recovery of nearly 8,000 metagenome-assembled genomes
             substantially expands the tree of life",
  author  = "Parks, Donovan H and Rinke, Christian and Chuvochina, Maria and
             Chaumeil, Pierre-Alain and Woodcroft, Ben J and Evans, Paul N and
             Hugenholtz, Philip and Tyson, Gene W",
  journal = "Nature Microbiology",
  volume  =  2,
  number  =  11,
  pages   = "1533--1542",
  year    =  2017
}

@ARTICLE{Metzger2018-jz,
  title    = "Enteric Virome {Sensing-Its} Role in Intestinal Homeostasis and
              Immunity",
  author   = "Metzger, Rebecca N and Krug, Anne B and Eisen{\"a}cher, Katharina",
  abstract = "Pattern recognition receptors (PRRs) sensing commensal
              microorganisms in the intestine induce tightly controlled tonic
              signaling in the intestinal mucosa, which is required to maintain
              intestinal barrier integrity and immune homeostasis. At the same
              time, PRR signaling pathways rapidly trigger the innate immune
              defense against invasive pathogens in the intestine. Intestinal
              epithelial cells and mononuclear phagocytes in the intestine and
              the gut-associated lymphoid tissues are critically involved in
              sensing components of the microbiome and regulating immune
              responses in the intestine to sustain immune tolerance against
              harmless antigens and to prevent inflammation. These processes
              have been mostly investigated in the context of the bacterial
              components of the microbiome so far. The impact of viruses
              residing in the intestine and the virus sensors, which are
              activated by these enteric viruses, on intestinal homeostasis and
              inflammation is just beginning to be unraveled. In this review,
              we will summarize recent findings indicating an important role of
              the enteric virome for intestinal homeostasis as well as
              pathology when the immune system fails to control the enteric
              virome. We will provide an overview of the virus sensors and
              signaling pathways, operative in the intestine and the
              mononuclear phagocyte subsets, which can sense viruses and shape
              the intestinal immune response. We will discuss how these might
              interact with resident enteric viruses directly or in context
              with the bacterial microbiome to affect intestinal homeostasis.",
  journal  = "Viruses",
  volume   =  10,
  number   =  4,
  month    =  mar,
  year     =  2018,
  keywords = "RIG-I-like receptors; Toll-like receptors; dendritic cells;
              enteric innate immunity; intestinal epithelial cells; intestine;
              macrophages; microbiome; mononuclear phagocytes; type I
              interferon;phamb",
  language = "en"
}

@ARTICLE{Wu2016-fe,
  title    = "{MaxBin} 2.0: an automated binning algorithm to recover genomes
              from multiple metagenomic datasets",
  author   = "Wu, Yu-Wei and Simmons, Blake A and Singer, Steven W",
  abstract = "UNLABELLED: The recovery of genomes from metagenomic datasets is
              a critical step to defining the functional roles of the
              underlying uncultivated populations. We previously developed
              MaxBin, an automated binning approach for high-throughput
              recovery of microbial genomes from metagenomes. Here we present
              an expanded binning algorithm, MaxBin 2.0, which recovers genomes
              from co-assembly of a collection of metagenomic datasets. Tests
              on simulated datasets revealed that MaxBin 2.0 is highly accurate
              in recovering individual genomes, and the application of MaxBin
              2.0 to several metagenomes from environmental samples
              demonstrated that it could achieve two complementary goals:
              recovering more bacterial genomes compared to binning a single
              sample as well as comparing the microbial community composition
              between different sampling environments. AVAILABILITY AND
              IMPLEMENTATION: MaxBin 2.0 is freely available at
              http://sourceforge.net/projects/maxbin/ under BSD license.",
  journal  = "Bioinformatics",
  volume   =  32,
  number   =  4,
  pages    = "605--607",
  month    =  feb,
  year     =  2016,
  language = "en"
}

@ARTICLE{Dance_undated-vk,
  title   = "The incredible diversity of viruses",
  author  = "{Dance}",
  journal = "Nature"
}

@ARTICLE{Gregory2020-gu,
  title    = "The Gut Virome Database Reveals {Age-Dependent} Patterns of
              Virome Diversity in the Human Gut",
  author   = "Gregory, Ann C and Zablocki, Olivier and Zayed, Ahmed A and
              Howell, Allison and Bolduc, Benjamin and Sullivan, Matthew B",
  abstract = "The gut microbiome profoundly affects human health and disease,
              and their infecting viruses are likely as important, but often
              missed because of reference database limitations. Here, we (1)
              built a human Gut Virome Database (GVD) from 2,697 viral particle
              or microbial metagenomes from 1,986 individuals representing 16
              countries, (2) assess its effectiveness, and (3) report a
              meta-analysis that reveals age-dependent patterns across healthy
              Westerners. The GVD contains 33,242 unique viral populations
              (approximately species-level taxa) and improves average viral
              detection rates over viral RefSeq and IMG/VR nearly 182-fold and
              2.6-fold, respectively. GVD meta-analyses show highly
              personalized viromes, reveal that inter-study variability from
              technical artifacts is larger than any ``disease'' effect at the
              population level, and document how viral diversity changes from
              human infancy into senescence. Together, this compact
              foundational resource, these standardization guidelines, and
              these meta-analysis findings provide a systematic toolkit to help
              maximize our understanding of viral roles in health and disease.",
  journal  = "Cell Host Microbe",
  volume   =  28,
  number   =  5,
  pages    = "724--740.e8",
  month    =  nov,
  year     =  2020,
  keywords = "bacteriophage; database; dysbiosis; gut microbiome; human health;
              lifespan; virome; virus",
  language = "en"
}

@ARTICLE{Sullivan2003-nr,
  title    = "Cyanophages infecting the oceanic cyanobacterium Prochlorococcus",
  author   = "Sullivan, Matthew B and Waterbury, John B and Chisholm, Sallie W",
  abstract = "Prochlorococcus is the numerically dominant phototroph in the
              tropical and subtropical oceans, accounting for half of the
              photosynthetic biomass in some areas. Here we report the
              isolation of cyanophages that infect Prochlorococcus, and show
              that although some are host-strain-specific, others cross-infect
              with closely related marine Synechococcus as well as between
              high-light- and low-light-adapted Prochlorococcus isolates,
              suggesting a mechanism for horizontal gene transfer.
              High-light-adapted Prochlorococcus hosts yielded Podoviridae
              exclusively, which were extremely host-specific, whereas
              low-light-adapted Prochlorococcus and all strains of
              Synechococcus yielded primarily Myoviridae, which has a broad
              host range. Finally, both Prochlorococcus and Synechococcus
              strain-specific cyanophage titres were low ( 10(5) cells x
              ml(-1)). These low titres in areas of high total host cell
              abundance seem to be a feature of open ocean ecosystems. We
              hypothesize that gradients in cyanobacterial population
              diversity, growth rates, and/or the incidence of lysogeny
              underlie these trends.",
  journal  = "Nature",
  volume   =  424,
  number   =  6952,
  pages    = "1047--1051",
  month    =  aug,
  year     =  2003,
  language = "en"
}

@ARTICLE{Sutton2019-od,
  title    = "Gut Bacteriophage: Current Understanding and Challenges",
  author   = "Sutton, Thomas D S and Hill, Colin",
  abstract = "The gut microbiome is widely accepted to have a significant
              impact on human health yet, despite years of research on this
              complex ecosystem, the contributions of different forces driving
              microbial population structure remain to be fully elucidated. The
              viral component of the human gut microbiome is dominated by
              bacteriophage, which are known to play crucial roles in shaping
              microbial composition, driving bacterial diversity, and
              facilitating horizontal gene transfer. Bacteriophage are also one
              of the most poorly understood components of the human gut
              microbiome, with the vast majority of viral sequences sharing
              little to no homology to reference databases. If we are to
              understand the dynamics of bacteriophage populations, their
              interaction with the human microbiome and ultimately their
              influence on human health, we will depend heavily on sequence
              based approaches and in silico tools. This is complicated by the
              fact that, as with any research field in its infancy, methods of
              analyses vary and this can impede our ability to compare the
              outputs of different studies. Here, we discuss the major findings
              to date regarding the human virome and reflect on our current
              understanding of how gut bacteriophage shape the microbiome. We
              consider whether or not the virome field is built on unstable
              foundations and if so, how can we provide a solid basis for
              future experimentation. The virome is a challenging yet crucial
              piece of the human microbiome puzzle. In order to develop our
              understanding, we will discuss the need to underpin future
              studies with robust research methods and suggest some solutions
              to existing challenges.",
  journal  = "Front. Endocrinol.",
  volume   =  10,
  pages    = "784",
  month    =  nov,
  year     =  2019,
  keywords = "bacteriophage; microbiome; microbiota; phage-host interactions;
              virome",
  language = "en"
}

@ARTICLE{Nissen2020-ed,
  title     = "Metagenomic data stratied using articial intelligence",
  author    = "Nissen, Jakob Nybo",
  publisher = "DTU Health Technology",
  year      =  2020,
  language  = "en"
}

@UNPUBLISHED{Hockenberry2020-ip,
  title    = "{BACPHLIP}: Predicting bacteriophage lifestyle from conserved
              protein domains",
  author   = "Hockenberry, Adam J and Wilke, Claus O",
  abstract = "Motivation Bacteriophages are broadly classified into two
              distinct lifestyles: temperate (lysogenic) and virulent (lytic).
              Temperate phages are capable of a latent phase of infection
              within a host cell, whereas virulent phages directly replicate
              and lyse host cells upon infection. Accurate lifestyle
              identification is critical for determining the role of individual
              phage species within ecosystems and their effect on host
              evolution. Results Here, we present BACPHLIP, a BACterioPHage
              LIfestyle Predictor. BACPHLIP detects the presence of a set of
              conserved protein domains within an input genome and uses this
              data to predict lifestyle via a Random Forest classifier. The
              classifier was trained on 634 phage genomes. On an independent
              test set of 423 phages, BACPHLIP has an accuracy of 98\%, greatly
              exceeding that of the best existing available tool (79\%).
              Availability BACPHLIP is freely available on GitHub () and the
              code used to build and test the classifier is provided in a
              separate repository (). \#\#\# Competing Interest Statement The
              authors have declared no competing interest.",
  journal  = "Cold Spring Harbor Laboratory",
  pages    = "2020.05.13.094805",
  month    =  may,
  year     =  2020,
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Sczyrba2017-ay,
  title     = "Critical Assessment of Metagenome Interpretation---a benchmark
               of metagenomics software",
  author    = "Sczyrba, Alexander and Hofmann, Peter and Belmann, Peter and
               Koslicki, David and Janssen, Stefan and Dr{\"o}ge, Johannes and
               Gregor, Ivan and Majda, Stephan and Fiedler, Jessika and Dahms,
               Eik and Bremges, Andreas and Fritz, Adrian and Garrido-Oter,
               Ruben and J{\o}rgensen, Tue Sparholt and Shapiro, Nicole and
               Blood, Philip D and Gurevich, Alexey and Bai, Yang and Turaev,
               Dmitrij and DeMaere, Matthew Z and Chikhi, Rayan and Nagarajan,
               Niranjan and Quince, Christopher and Meyer, Fernando and
               Balvo{\v c}i{\=u}t{\.e}, Monika and Hansen, Lars Hestbjerg and
               S{\o}rensen, S{\o}ren J and Chia, Burton K H and Denis, Bertrand
               and Froula, Jeff L and Wang, Zhong and Egan, Robert and Don
               Kang, Dongwan and Cook, Jeffrey J and Deltel, Charles and
               Beckstette, Michael and Lemaitre, Claire and Peterlongo, Pierre
               and Rizk, Guillaume and Lavenier, Dominique and Wu, Yu-Wei and
               Singer, Steven W and Jain, Chirag and Strous, Marc and
               Klingenberg, Heiner and Meinicke, Peter and Barton, Michael D
               and Lingner, Thomas and Lin, Hsin-Hung and Liao, Yu-Chieh and
               Silva, Genivaldo Gueiros Z and Cuevas, Daniel A and Edwards,
               Robert A and Saha, Surya and Piro, Vitor C and Renard, Bernhard
               Y and Pop, Mihai and Klenk, Hans-Peter and G{\"o}ker, Markus and
               Kyrpides, Nikos C and Woyke, Tanja and Vorholt, Julia A and
               Schulze-Lefert, Paul and Rubin, Edward M and Darling, Aaron E
               and Rattei, Thomas and McHardy, Alice C",
  abstract  = "The Critical Assessment of Metagenome Interpretation (CAMI)
               community initiative presents results from its first challenge,
               a rigorous benchmarking of software for metagenome assembly,
               binning and taxonomic profiling. Methods for assembly, taxonomic
               profiling and binning are key to interpreting metagenome data,
               but a lack of consensus about benchmarking complicates
               performance assessment. The Critical Assessment of Metagenome
               Interpretation (CAMI) challenge has engaged the global developer
               community to benchmark their programs on highly complex and
               realistic data sets, generated from ∼700 newly sequenced
               microorganisms and ∼600 novel viruses and plasmids and
               representing common experimental setups. Assembly and genome
               binning programs performed well for species represented by
               individual genomes but were substantially affected by the
               presence of related strains. Taxonomic profiling and binning
               programs were proficient at high taxonomic ranks, with a notable
               performance decrease below family level. Parameter settings
               markedly affected performance, underscoring their importance for
               program reproducibility. The CAMI results highlight current
               challenges but also provide a roadmap for software selection to
               answer specific research questions.",
  journal   = "Nat. Methods",
  publisher = "Nature Publishing Group",
  volume    =  14,
  number    =  11,
  pages     = "1063--1071",
  month     =  oct,
  year      =  2017,
  language  = "en"
}

@ARTICLE{Lander2001-vu,
  title    = "Initial sequencing and analysis of the human genome",
  author   = "Lander, E S and Linton, L M and Birren, B and Nusbaum, C and
              Zody, M C and Baldwin, J and Devon, K and Dewar, K and Doyle, M
              and FitzHugh, W and Funke, R and Gage, D and Harris, K and
              Heaford, A and Howland, J and Kann, L and Lehoczky, J and LeVine,
              R and McEwan, P and McKernan, K and Meldrim, J and Mesirov, J P
              and Miranda, C and Morris, W and Naylor, J and Raymond, C and
              Rosetti, M and Santos, R and Sheridan, A and Sougnez, C and
              Stange-Thomann, Y and Stojanovic, N and Subramanian, A and Wyman,
              D and Rogers, J and Sulston, J and Ainscough, R and Beck, S and
              Bentley, D and Burton, J and Clee, C and Carter, N and Coulson, A
              and Deadman, R and Deloukas, P and Dunham, A and Dunham, I and
              Durbin, R and French, L and Grafham, D and Gregory, S and
              Hubbard, T and Humphray, S and Hunt, A and Jones, M and Lloyd, C
              and McMurray, A and Matthews, L and Mercer, S and Milne, S and
              Mullikin, J C and Mungall, A and Plumb, R and Ross, M and
              Shownkeen, R and Sims, S and Waterston, R H and Wilson, R K and
              Hillier, L W and McPherson, J D and Marra, M A and Mardis, E R
              and Fulton, L A and Chinwalla, A T and Pepin, K H and Gish, W R
              and Chissoe, S L and Wendl, M C and Delehaunty, K D and Miner, T
              L and Delehaunty, A and Kramer, J B and Cook, L L and Fulton, R S
              and Johnson, D L and Minx, P J and Clifton, S W and Hawkins, T
              and Branscomb, E and Predki, P and Richardson, P and Wenning, S
              and Slezak, T and Doggett, N and Cheng, J F and Olsen, A and
              Lucas, S and Elkin, C and Uberbacher, E and Frazier, M and Gibbs,
              R A and Muzny, D M and Scherer, S E and Bouck, J B and Sodergren,
              E J and Worley, K C and Rives, C M and Gorrell, J H and Metzker,
              M L and Naylor, S L and Kucherlapati, R S and Nelson, D L and
              Weinstock, G M and Sakaki, Y and Fujiyama, A and Hattori, M and
              Yada, T and Toyoda, A and Itoh, T and Kawagoe, C and Watanabe, H
              and Totoki, Y and Taylor, T and Weissenbach, J and Heilig, R and
              Saurin, W and Artiguenave, F and Brottier, P and Bruls, T and
              Pelletier, E and Robert, C and Wincker, P and Smith, D R and
              Doucette-Stamm, L and Rubenfield, M and Weinstock, K and Lee, H M
              and Dubois, J and Rosenthal, A and Platzer, M and Nyakatura, G
              and Taudien, S and Rump, A and Yang, H and Yu, J and Wang, J and
              Huang, G and Gu, J and Hood, L and Rowen, L and Madan, A and Qin,
              S and Davis, R W and Federspiel, N A and Abola, A P and Proctor,
              M J and Myers, R M and Schmutz, J and Dickson, M and Grimwood, J
              and Cox, D R and Olson, M V and Kaul, R and Raymond, C and
              Shimizu, N and Kawasaki, K and Minoshima, S and Evans, G A and
              Athanasiou, M and Schultz, R and Roe, B A and Chen, F and Pan, H
              and Ramser, J and Lehrach, H and Reinhardt, R and McCombie, W R
              and de la Bastide, M and Dedhia, N and Bl{\"o}cker, H and
              Hornischer, K and Nordsiek, G and Agarwala, R and Aravind, L and
              Bailey, J A and Bateman, A and Batzoglou, S and Birney, E and
              Bork, P and Brown, D G and Burge, C B and Cerutti, L and Chen, H
              C and Church, D and Clamp, M and Copley, R R and Doerks, T and
              Eddy, S R and Eichler, E E and Furey, T S and Galagan, J and
              Gilbert, J G and Harmon, C and Hayashizaki, Y and Haussler, D and
              Hermjakob, H and Hokamp, K and Jang, W and Johnson, L S and
              Jones, T A and Kasif, S and Kaspryzk, A and Kennedy, S and Kent,
              W J and Kitts, P and Koonin, E V and Korf, I and Kulp, D and
              Lancet, D and Lowe, T M and McLysaght, A and Mikkelsen, T and
              Moran, J V and Mulder, N and Pollara, V J and Ponting, C P and
              Schuler, G and Schultz, J and Slater, G and Smit, A F and Stupka,
              E and Szustakowki, J and Thierry-Mieg, D and Thierry-Mieg, J and
              Wagner, L and Wallis, J and Wheeler, R and Williams, A and Wolf,
              Y I and Wolfe, K H and Yang, S P and Yeh, R F and Collins, F and
              Guyer, M S and Peterson, J and Felsenfeld, A and Wetterstrand, K
              A and Patrinos, A and Morgan, M J and de Jong, P and Catanese, J
              J and Osoegawa, K and Shizuya, H and Choi, S and Chen, Y J and
              Szustakowki, J and {International Human Genome Sequencing
              Consortium}",
  abstract = "The human genome holds an extraordinary trove of information
              about human development, physiology, medicine and evolution. Here
              we report the results of an international collaboration to
              produce and make freely available a draft sequence of the human
              genome. We also present an initial analysis of the data,
              describing some of the insights that can be gleaned from the
              sequence.",
  journal  = "Nature",
  volume   =  409,
  number   =  6822,
  pages    = "860--921",
  month    =  feb,
  year     =  2001,
  language = "en"
}

@UNPUBLISHED{Roux2020-mr,
  title    = "Ecology and molecular targets of hypermutation in the global
              microbiome",
  author   = "Roux, Simon and Paul, Blair G and Bagby, Sarah C and Allen,
              Michelle A and Attwood, Graeme and Cavicchioli, Ricardo and
              Chistoserdova, Ludmila and Hallam, Steven J and Hernandez, Maria
              E and Hess, Matthias and Liu, Wen-Tso and O'Malley, Michelle A
              and Peng, Xuefeng and Rich, Virginia I and Saleska, Scott and
              Eloe-Fadrosh, Emiley A",
  abstract = "Changes in the sequence of an organism's genome, i.e. mutations,
              are the raw material of evolution[1][1]. The frequency and
              location of mutations can be constrained by specific molecular
              mechanisms, such as Diversity-generating retroelements
              (DGRs)[2][2]--[4][3]. DGRs introduce mutations in specific target
              genes, and were characterized from several cultivated bacteria
              and bacteriophages[2][2]. Whilst a larger diversity of DGR loci
              has been identified in genomic data from environmental samples,
              i.e. metagenomes, the ecological role of these DGRs and their
              associated evolutionary drivers remain poorly
              understood[5][4]--[7][5]. Here we built and analyzed an extensive
              dataset of >30,000 metagenome-derived DGRs, and determine that
              DGRs have a single evolutionary origin and a universal bias
              towards adenine mutations. We further identified six major
              lineages of DGRs, each associated with a specific ecological
              niche defined as a genome type, i.e. whether the DGR is encoded
              on a viral or cellular genome, a limited set of taxa and
              environments, and a distinct type of target. Finally, we leverage
              read mapping and metagenomic time series to demonstrate that DGRs
              are consistently and broadly active, and responsible for >10\% of
              all amino acid changes in some organisms at a conservative
              estimate. Overall, these results highlight the strong constraints
              under which DGRs diversify and expand, and elucidate several
              distinct roles these elements play in natural communities and in
              shaping microbial community structure and function in our
              environment. [1]: \#ref-1 [2]: \#ref-2 [3]: \#ref-4 [4]: \#ref-5
              [5]: \#ref-7",
  journal  = "Cold Spring Harbor Laboratory",
  pages    = "2020.04.01.020958",
  month    =  apr,
  year     =  2020,
  language = "en"
}

@ARTICLE{Lloyd-Price2016-qf,
  title    = "The healthy human microbiome",
  author   = "Lloyd-Price, Jason and Abu-Ali, Galeb and Huttenhower, Curtis",
  abstract = "Humans are virtually identical in their genetic makeup, yet the
              small differences in our DNA give rise to tremendous phenotypic
              diversity across the human population. By contrast, the
              metagenome of the human microbiome-the total DNA content of
              microbes inhabiting our bodies-is quite a bit more variable, with
              only a third of its constituent genes found in a majority of
              healthy individuals. Understanding this variability in the
              ``healthy microbiome'' has thus been a major challenge in
              microbiome research, dating back at least to the 1960s,
              continuing through the Human Microbiome Project and beyond.
              Cataloguing the necessary and sufficient sets of microbiome
              features that support health, and the normal ranges of these
              features in healthy populations, is an essential first step to
              identifying and correcting microbial configurations that are
              implicated in disease. Toward this goal, several population-scale
              studies have documented the ranges and diversity of both
              taxonomic compositions and functional potentials normally
              observed in the microbiomes of healthy populations, along with
              possible driving factors such as geography, diet, and lifestyle.
              Here, we review several definitions of a 'healthy microbiome'
              that have emerged, the current understanding of the ranges of
              healthy microbial diversity, and gaps such as the
              characterization of molecular function and the development of
              ecological therapies to be addressed in the future.",
  journal  = "Genome Med.",
  volume   =  8,
  number   =  1,
  pages    = "51",
  month    =  apr,
  year     =  2016,
  language = "en"
}

@ARTICLE{Thompson2011-oc,
  title    = "Phage auxiliary metabolic genes and the redirection of
              cyanobacterial host carbon metabolism",
  author   = "Thompson, Luke R and Zeng, Qinglu and Kelly, Libusha and Huang,
              Katherine H and Singer, Alexander U and Stubbe, Joanne and
              Chisholm, Sallie W",
  abstract = "Cyanophages infecting the marine cyanobacteria Prochlorococcus
              and Synechococcus encode and express genes for the photosynthetic
              light reactions. Sequenced cyanophage genomes lack Calvin cycle
              genes, however, suggesting that photosynthetic energy harvested
              via phage proteins is not used for carbon fixation. We report
              here that cyanophages carry and express a Calvin cycle inhibitor,
              CP12, whose host homologue directs carbon flux from the Calvin
              cycle to the pentose phosphate pathway (PPP). Phage CP12 was
              coexpressed with phage genes involved in the light reactions,
              deoxynucleotide biosynthesis, and the PPP, including a
              transaldolase gene that is the most prevalent PPP gene in
              cyanophages. Phage transaldolase was purified to homogeneity from
              several strains and shown to be functional in vitro, suggesting
              that it might facilitate increased flux through this key reaction
              in the host PPP, augmenting production of NADPH and ribose
              5-phosphate. Kinetic measurements of phage and host
              transaldolases revealed that the phage enzymes have k(cat)/K(m)
              values only approximately one third of the corresponding host
              enzymes. The lower efficiency of phage transaldolase may be a
              tradeoff for other selective advantages such as reduced gene
              size: we show that more than half of host-like cyanophage genes
              are significantly shorter than their host homologues. Consistent
              with decreased Calvin cycle activity and increased PPP and light
              reaction activity under infection, the host NADPH/NADP ratio
              increased two-fold in infected cells. We propose that
              phage-augmented NADPH production fuels deoxynucleotide
              biosynthesis for phage replication, and that the selection
              pressures molding phage genomes involve fitness advantages
              conferred through mobilization of host energy stores.",
  journal  = "Proc. Natl. Acad. Sci. U. S. A.",
  volume   =  108,
  number   =  39,
  pages    = "E757--64",
  month    =  sep,
  year     =  2011,
  language = "en"
}

@ARTICLE{Dolgin2019-yz,
  title    = "The secret social lives of viruses",
  author   = "Dolgin, Elie",
  journal  = "Nature",
  volume   =  570,
  number   =  7761,
  pages    = "290--292",
  month    =  jun,
  year     =  2019,
  keywords = "Infection; Medical research; Molecular biology; Virology",
  language = "en"
}

@ARTICLE{Federici2022-ny,
  title    = "Targeted suppression of human {IBD-associated} gut microbiota
              commensals by phage consortia for treatment of intestinal
              inflammation",
  author   = "Federici, Sara and Kredo-Russo, Sharon and Vald{\'e}s-Mas, Rafael
              and Kviatcovsky, Denise and Weinstock, Eyal and Matiuhin, Yulia
              and Silberberg, Yael and Atarashi, Koji and Furuichi, Munehiro
              and Oka, Akihiko and Liu, Bo and Fibelman, Morine and Weiner,
              Iddo Nadav and Khabra, Efrat and Cullin, Nyssa and Ben-Yishai,
              Noa and Inbar, Dana and Ben-David, Hava and Nicenboim, Julian and
              Kowalsman, Noga and Lieb, Wolfgang and Kario, Edith and Cohen,
              Tal and Geffen, Yael Friedman and Zelcbuch, Lior and Cohen, Ariel
              and Rappo, Urania and Gahali-Sass, Inbar and Golembo, Myriam and
              Lev, Vered and Dori-Bachash, Mally and Shapiro, Hagit and Moresi,
              Claudia and Cuevas-Sierra, Amanda and Mohapatra, Gayatree and
              Kern, Lara and Zheng, Danping and Nobs, Samuel Philip and Suez,
              Jotham and Stettner, Noa and Harmelin, Alon and Zak, Naomi and
              Puttagunta, Sailaja and Bassan, Merav and Honda, Kenya and Sokol,
              Harry and Bang, Corinna and Franke, Andre and Schramm, Christoph
              and Maharshak, Nitsan and Sartor, Ryan Balfour and Sorek, Rotem
              and Elinav, Eran",
  abstract = "Human gut commensals are increasingly suggested to impact
              non-communicable diseases, such as inflammatory bowel diseases
              (IBD), yet their targeted suppression remains a daunting unmet
              challenge. In four geographically distinct IBD cohorts (n = 537),
              we identify a clade of Klebsiella pneumoniae (Kp) strains,
              featuring a unique antibiotics resistance and mobilome signature,
              to be strongly associated with disease exacerbation and severity.
              Transfer of clinical IBD-associated Kp strains into
              colitis-prone, germ-free, and colonized mice enhances intestinal
              inflammation. Stepwise generation of a lytic five-phage
              combination, targeting sensitive and resistant IBD-associated Kp
              clade members through distinct mechanisms, enables effective Kp
              suppression in colitis-prone mice, driving an attenuated
              inflammation and disease severity. Proof-of-concept assessment of
              Kp-targeting phages in an artificial human gut and in healthy
              volunteers demonstrates gastric acid-dependent phage resilience,
              safety, and viability in the lower gut. Collectively, we
              demonstrate the feasibility of orally administered combination
              phage therapy in avoiding resistance, while effectively
              inhibiting non-communicable disease-contributing pathobionts.",
  journal  = "Cell",
  volume   =  185,
  number   =  16,
  pages    = "2879--2898.e24",
  month    =  aug,
  year     =  2022,
  keywords = "Crohn's disease; Klebsiella pneumoniae; inflammatory bowel
              diseases; microbiome; microbiota; phage therapy; resistome;
              ulcerative colitis",
  language = "en"
}

@MISC{Silveira2016-ni,
  title   = "{Piggyback-the-Winner} in host-associated microbial communities",
  author  = "Silveira, Cynthia B and Rohwer, Forest L",
  journal = "npj Biofilms and Microbiomes",
  volume  =  2,
  number  =  1,
  year    =  2016
}

@ARTICLE{Ren2017-rf,
  title    = "{VirFinder}: a novel k-mer based tool for identifying viral
              sequences from assembled metagenomic data",
  author   = "Ren, Jie and Ahlgren, Nathan A and Lu, Yang Young and Fuhrman,
              Jed A and Sun, Fengzhu",
  abstract = "Identifying viral sequences in mixed metagenomes containing both
              viral and host contigs is a critical first step in analyzing the
              viral component of samples. Current tools for distinguishing
              prokaryotic virus and host contigs primarily use gene-based
              similarity approaches. Such approaches can significantly limit
              results especially for short contigs that have few predicted
              proteins or lack proteins with similarity to previously known
              viruses.",
  journal  = "Microbiome",
  volume   =  5,
  number   =  1,
  pages    = "69",
  month    =  jul,
  year     =  2017
}

@ARTICLE{Dion2021-zc,
  title    = "Streamlining {CRISPR} spacer-based bacterial host predictions to
              decipher the viral dark matter",
  author   = "Dion, Mo{\"\i}ra B and Plante, Pier-Luc and Zufferey, Edwige and
              Shah, Shiraz A and Corbeil, Jacques and Moineau, Sylvain",
  abstract = "Thousands of new phages have recently been discovered thanks to
              viral metagenomics. These phages are extremely diverse and their
              genome sequences often do not resemble any known phages. To
              appreciate their ecological impact, it is important to determine
              their bacterial hosts. CRISPR spacers can be used to predict
              hosts of unknown phages, as spacers represent biological records
              of past phage-bacteria interactions. However, no guidelines have
              been established to standardize host prediction based on CRISPR
              spacers. Additionally, there are no tools that use spacers to
              perform host predictions on large viral datasets. Here, we
              developed a set of tools that includes all the necessary steps
              for predicting the hosts of uncharacterized phages. We created a
              database of >11 million spacers and a program to execute host
              predictions on large viral datasets. Our host prediction approach
              uses biological criteria inspired by how CRISPR-Cas naturally
              work as adaptive immune systems, which make the results easy to
              interpret. We evaluated the performance using 9484 phages with
              known hosts and obtained a recall of 49\% and a precision of
              69\%. We also found that this host prediction method yielded
              higher performance for phages that infect gut-associated
              bacteria, suggesting it is well suited for gut-virome
              characterization.",
  journal  = "Nucleic Acids Res.",
  volume   =  49,
  number   =  6,
  pages    = "3127--3138",
  month    =  apr,
  year     =  2021,
  language = "en"
}

@MISC{Guerin2021-bg,
  title   = "Isolation and characterisation of {$\Phi$crAss002}, a crAss-like
             phage from the human gut that infects Bacteroides xylanisolvens",
  author  = "Guerin, Emma and Shkoporov, Andrey N and Stockdale, Stephen R and
             Comas, Joan Colom and Khokhlova, Ekaterina V and Clooney, Adam G
             and Daly, Karen M and Draper, Lorraine A and Stephens, Niamh and
             Scholz, Dimitri and Paul Ross, R and Hill, Colin",
  journal = "Microbiome",
  volume  =  9,
  number  =  1,
  year    =  2021
}

@ARTICLE{Samson2013-lm,
  title    = "Revenge of the phages: defeating bacterial defences",
  author   = "Samson, Julie E and Magad{\'a}n, Alfonso H and Sabri, Mourad and
              Moineau, Sylvain",
  abstract = "Bacteria and their viral predators (bacteriophages) are locked in
              a constant battle. In order to proliferate in phage-rich
              environments, bacteria have an impressive arsenal of defence
              mechanisms, and in response, phages have evolved
              counter-strategies to evade these antiviral systems. In this
              Review, we describe the various tactics that are used by phages
              to overcome bacterial resistance mechanisms, including adsorption
              inhibition, restriction-modification, CRISPR-Cas (clustered
              regularly interspaced short palindromic repeats-CRISPR-associated
              proteins) systems and abortive infection. Furthermore, we
              consider how these observations have enhanced our knowledge of
              phage biology, evolution and phage-host interactions.",
  journal  = "Nat. Rev. Microbiol.",
  volume   =  11,
  number   =  10,
  pages    = "675--687",
  month    =  oct,
  year     =  2013,
  language = "en"
}

@ARTICLE{Lloyd-Price2019-cw,
  title    = "Multi-omics of the gut microbial ecosystem in inflammatory bowel
              diseases",
  author   = "Lloyd-Price, Jason and Arze, Cesar and Ananthakrishnan, Ashwin N
              and Schirmer, Melanie and Avila-Pacheco, Julian and Poon, Tiffany
              W and Andrews, Elizabeth and Ajami, Nadim J and Bonham, Kevin S
              and Brislawn, Colin J and Casero, David and Courtney, Holly and
              Gonzalez, Antonio and Graeber, Thomas G and Hall, A Brantley and
              Lake, Kathleen and Landers, Carol J and Mallick, Himel and
              Plichta, Damian R and Prasad, Mahadev and Rahnavard, Gholamali
              and Sauk, Jenny and Shungin, Dmitry and V{\'a}zquez-Baeza,
              Yoshiki and White, Richard A and Bishai, Jason and Bullock, Kevin
              and Deik, Amy and Dennis, Courtney and Kaplan, Jess L and
              Khalili, Hamed and McIver, Lauren J and Moran, Christopher J and
              Nguyen, Long and Pierce, Kerry A and Schwager, Randall and
              Sirota-Madi, Alexandra and Stevens, Betsy W and Tan, William and
              ten Hoeve, Johanna J and Weingart, George and Wilson, Robin G and
              Yajnik, Vijay and Braun, Jonathan and Denson, Lee A and Jansson,
              Janet K and Knight, Rob and Kugathasan, Subra and McGovern,
              Dermot P B and Petrosino, Joseph F and Stappenbeck, Thaddeus S
              and Winter, Harland S and Clish, Clary B and Franzosa, Eric A and
              Vlamakis, Hera and Xavier, Ramnik J and Huttenhower, Curtis and
              {IBDMDB Investigators}",
  abstract = "Inflammatory bowel diseases, which include Crohn's disease and
              ulcerative colitis, affect several million individuals worldwide.
              Crohn's disease and ulcerative colitis are complex diseases that
              are heterogeneous at the clinical, immunological, molecular,
              genetic, and microbial levels. Individual contributing factors
              have been the focus of extensive research. As part of the
              Integrative Human Microbiome Project (HMP2 or iHMP), we followed
              132 subjects for one year each to generate integrated
              longitudinal molecular profiles of host and microbial activity
              during disease (up to 24 time points each; in total 2,965 stool,
              biopsy, and blood specimens). Here we present the results, which
              provide a comprehensive view of functional dysbiosis in the gut
              microbiome during inflammatory bowel disease activity. We
              demonstrate a characteristic increase in facultative anaerobes at
              the expense of obligate anaerobes, as well as molecular
              disruptions in microbial transcription (for example, among
              clostridia), metabolite pools (acylcarnitines, bile acids, and
              short-chain fatty acids), and levels of antibodies in host serum.
              Periods of disease activity were also marked by increases in
              temporal variability, with characteristic taxonomic, functional,
              and biochemical shifts. Finally, integrative analysis identified
              microbial, biochemical, and host factors central to this
              dysregulation. The study's infrastructure resources, results, and
              data, which are available through the Inflammatory Bowel Disease
              Multi'omics Database (http://ibdmdb.org), provide the most
              comprehensive description to date of host and microbial
              activities in inflammatory bowel diseases.",
  journal  = "Nature",
  volume   =  569,
  number   =  7758,
  pages    = "655--662",
  month    =  may,
  year     =  2019
}

@ARTICLE{Alley2019-el,
  title    = "Unified rational protein engineering with sequence-based deep
              representation learning",
  author   = "Alley, Ethan C and Khimulya, Grigory and Biswas, Surojit and
              AlQuraishi, Mohammed and Church, George M",
  abstract = "Rational protein engineering requires a holistic understanding of
              protein function. Here, we apply deep learning to unlabeled
              amino-acid sequences to distill the fundamental features of a
              protein into a statistical representation that is semantically
              rich and structurally, evolutionarily and biophysically grounded.
              We show that the simplest models built on top of this unified
              representation (UniRep) are broadly applicable and generalize to
              unseen regions of sequence space. Our data-driven approach
              predicts the stability of natural and de novo designed proteins,
              and the quantitative function of molecularly diverse mutants,
              competitively with the state-of-the-art methods. UniRep further
              enables two orders of magnitude efficiency improvement in a
              protein engineering task. UniRep is a versatile summary of
              fundamental protein features that can be applied across protein
              engineering informatics.",
  journal  = "Nat. Methods",
  volume   =  16,
  number   =  12,
  pages    = "1315--1322",
  month    =  dec,
  year     =  2019,
  language = "en"
}

@ARTICLE{Toro2019-zp,
  title    = "Multiple origins of reverse transcriptases linked to {CRISPR-Cas}
              systems",
  author   = "Toro, Nicol{\'a}s and Mart{\'\i}nez-Abarca, Francisco and Mestre,
              Mario Rodr{\'\i}guez and Gonz{\'a}lez-Delgado, Alejandro",
  abstract = "Prokaryotic genomes harbour a plethora of uncharacterized reverse
              transcriptases (RTs). RTs phylogenetically related to those
              encoded by group-II introns have been found associated with type
              III CRISPR-Cas systems, adjacent or fused at the C-terminus to
              Cas1. It is thought that these RTs may have a relevant function
              in the CRISPR immune response mediating spacer acquisition from
              RNA molecules. The origin and relationships of these RTs and the
              ways in which the various protein domains evolved remain matters
              of debate. We carried out a large survey of annotated RTs in
              databases (198,760 sequences) and constructed a large dataset of
              unique representative sequences (9,141). The combined
              phylogenetic reconstruction and identification of the RTs and
              their various protein domains in the vicinity of CRISPR
              adaptation and effector modules revealed three different origins
              for these RTs, consistent with their emergence on multiple
              occasions: a larger group that have evolved from group-II intron
              RTs, and two minor lineages that may have arisen more recently
              from Retron/retron-like sequences and Abi-P2 RTs, the latter
              associated with type I-C systems. We also identified a particular
              group of RTs associated with CRISPR-cas loci in clade 12, fused
              C-terminally to an archaeo-eukaryotic primase (AEP), a protein
              domain (AE-Prim\_S\_like) forming a particular family within the
              AEP proper clade. Together, these data provide new insight into
              the evolution of CRISPR-Cas/RT systems.",
  journal  = "RNA Biol.",
  volume   =  16,
  number   =  10,
  pages    = "1486--1493",
  month    =  oct,
  year     =  2019,
  keywords = "Abi; CRISPR; Cas; archaeo-eukaryotic primase;
              diversity-generating retroelement; group II intron; retron;
              reverse transcriptase",
  language = "en"
}

@ARTICLE{Sutton2019-zv,
  title    = "Choice of assembly software has a critical impact on virome
              characterisation",
  author   = "Sutton, Thomas D S and Clooney, Adam G and Ryan, Feargal J and
              Ross, R Paul and Hill, Colin",
  abstract = "The viral component of microbial communities plays a vital role
              in driving bacterial diversity, facilitating nutrient turnover
              and shaping community composition. Despite their importance, the
              vast majority of viral sequences are poorly annotated and share
              little or no homology to reference databases. As a result,
              investigation of the viral metagenome (virome) relies heavily on
              de novo assembly of short sequencing reads to recover
              compositional and functional information. Metagenomic assembly is
              particularly challenging for virome data, often resulting in
              fragmented assemblies and poor recovery of viral community
              members. Despite the essential role of assembly in virome
              analysis and difficulties posed by these data, current assembly
              comparisons have been limited to subsections of virome studies or
              bacterial datasets.",
  journal  = "Microbiome",
  volume   =  7,
  number   =  1,
  pages    = "12",
  month    =  jan,
  year     =  2019
}

@ARTICLE{Olm2017-lf,
  title    = "dRep: a tool for fast and accurate genomic comparisons that
              enables improved genome recovery from metagenomes through
              de-replication",
  author   = "Olm, Matthew R and Brown, Christopher T and Brooks, Brandon and
              Banfield, Jillian F",
  abstract = "The number of microbial genomes sequenced each year is expanding
              rapidly, in part due to genome-resolved metagenomic studies that
              routinely recover hundreds of draft-quality genomes. Rapid
              algorithms have been developed to comprehensively compare large
              genome sets, but they are not accurate with draft-quality
              genomes. Here we present dRep, a program that reduces the
              computational time for pairwise genome comparisons by
              sequentially applying a fast, inaccurate estimation of genome
              distance, and a slow, accurate measure of average nucleotide
              identity. dRep achieves a 28 $\times$ increase in speed with
              perfect recall and precision when benchmarked against previously
              developed algorithms. We demonstrate the use of dRep for genome
              recovery from time-series datasets. Each metagenome was assembled
              separately, and dRep was used to identify groups of essentially
              identical genomes and select the best genome from each replicate
              set. This resulted in recovery of significantly more and
              higher-quality genomes compared to the set recovered using
              co-assembly.",
  journal  = "ISME J.",
  volume   =  11,
  number   =  12,
  pages    = "2864--2868",
  month    =  dec,
  year     =  2017,
  language = "en"
}

@ARTICLE{Shkoporov2019-ru,
  title    = "Bacteriophages of the Human Gut: The ``Known Unknown'' of the
              Microbiome",
  author   = "Shkoporov, Andrey N and Hill, Colin",
  abstract = "The human gut microbiome is a dense and taxonomically diverse
              consortium of microorganisms. While the bacterial components of
              the microbiome have received considerable attention,
              comparatively little is known about the composition and
              physiological significance of human gut-associated bacteriophage
              populations (phageome). By extrapolating our knowledge of
              phage-host interactions from other environments, one could expect
              that >1012 viruses reside in the human gut, and we can predict
              that they play important roles in regulating the complex
              microbial networks operating in this habitat. Before delving into
              their function, we need to first overcome the challenges
              associated with studying and characterizing the phageome. In this
              Review, we summarize the available methods and main findings
              regarding taxonomic composition, community structure, and
              population dynamics in the human gut phageome. We also discuss
              the main challenges in the field and identify promising avenues
              for future research.",
  journal  = "Cell Host Microbe",
  volume   =  25,
  number   =  2,
  pages    = "195--209",
  month    =  feb,
  year     =  2019,
  keywords = "bacteriophages; gut microbiota; human microbiome; phageome;
              virome"
}

@ARTICLE{Kieft2020-ip,
  title    = "{VIBRANT}: automated recovery, annotation and curation of
              microbial viruses, and evaluation of viral community function
              from genomic sequences",
  author   = "Kieft, Kristopher and Zhou, Zhichao and Anantharaman, Karthik",
  abstract = "BACKGROUND: Viruses are central to microbial community structure
              in all environments. The ability to generate large metagenomic
              assemblies of mixed microbial and viral sequences provides the
              opportunity to tease apart complex microbiome dynamics, but these
              analyses are currently limited by the tools available for
              analyses of viral genomes and assessing their metabolic impacts
              on microbiomes. DESIGN: Here we present VIBRANT, the first method
              to utilize a hybrid machine learning and protein similarity
              approach that is not reliant on sequence features for automated
              recovery and annotation of viruses, determination of genome
              quality and completeness, and characterization of viral community
              function from metagenomic assemblies. VIBRANT uses neural
              networks of protein signatures and a newly developed v-score
              metric that circumvents traditional boundaries to maximize
              identification of lytic viral genomes and integrated proviruses,
              including highly diverse viruses. VIBRANT highlights viral
              auxiliary metabolic genes and metabolic pathways, thereby serving
              as a user-friendly platform for evaluating viral community
              function. VIBRANT was trained and validated on reference virus
              datasets as well as microbiome and virome data. RESULTS: VIBRANT
              showed superior performance in recovering higher quality viruses
              and concurrently reduced the false identification of non-viral
              genome fragments in comparison to other virus identification
              programs, specifically VirSorter, VirFinder, and MARVEL. When
              applied to 120,834 metagenome-derived viral sequences
              representing several human and natural environments, VIBRANT
              recovered an average of 94\% of the viruses, whereas VirFinder,
              VirSorter, and MARVEL achieved less powerful performance,
              averaging 48\%, 87\%, and 71\%, respectively. Similarly, VIBRANT
              identified more total viral sequence and proteins when applied to
              real metagenomes. When compared to PHASTER, Prophage Hunter, and
              VirSorter for the ability to extract integrated provirus regions
              from host scaffolds, VIBRANT performed comparably and even
              identified proviruses that the other programs did not. To
              demonstrate applications of VIBRANT, we studied viromes
              associated with Crohn's disease to show that specific viral
              groups, namely Enterobacteriales-like viruses, as well as
              putative dysbiosis associated viral proteins are more abundant
              compared to healthy individuals, providing a possible viral link
              to maintenance of diseased states. CONCLUSIONS: The ability to
              accurately recover viruses and explore viral impacts on microbial
              community metabolism will greatly advance our understanding of
              microbiomes, host-microbe interactions, and ecosystem dynamics.
              Video Abstract.",
  journal  = "Microbiome",
  volume   =  8,
  number   =  1,
  pages    = "90",
  month    =  jun,
  year     =  2020,
  keywords = "Auxiliary metabolism; Bacteriophage; Machine learning;
              Metagenome; Software; Virome; Virus",
  language = "en"
}

@ARTICLE{Strazar2021-fu,
  title    = "Gut microbiome-mediated metabolism effects on immunity in rural
              and urban African populations",
  author   = "Stra{\v z}ar, Martin and Temba, Godfrey S and Vlamakis, Hera and
              Kullaya, Vesla I and Lyamuya, Furaha and Mmbaga, Blandina T and
              Joosten, Leo A B and van der Ven, Andre J A M and Netea, Mihai G
              and de Mast, Quirijn and Xavier, Ramnik J",
  abstract = "The human gut microbiota is increasingly recognized as an
              important factor in modulating innate and adaptive immunity
              through release of ligands and metabolites that translocate into
              circulation. Urbanizing African populations harbor large
              intestinal diversity due to a range of lifestyles, providing the
              necessary variation to gauge immunomodulatory factors. Here, we
              uncover a gradient of intestinal microbial compositions from
              rural through urban Tanzanian, towards European samples,
              manifested both in relative abundance and genomic variation
              observed in stool metagenomics. The rural population shows
              increased Bacteroidetes, led by Prevotella copri, but also
              presence of fungi. Measured ex vivo cytokine responses were
              significantly associated with 34 immunomodulatory microbes, which
              have a larger impact on circulating metabolites than
              non-significant microbes. Pathway effects on cytokines, notably
              TNF-$\alpha$ and IFN-$\gamma$, differential metabolome analysis
              and enzyme copy number enrichment converge on histidine and
              arginine metabolism as potential immunomodulatory pathways
              mediated by Bifidobacterium longum and Akkermansia muciniphila.",
  journal  = "Nat. Commun.",
  volume   =  12,
  number   =  1,
  pages    = "4845",
  month    =  aug,
  year     =  2021,
  language = "en"
}

@ARTICLE{Carlson2019-lm,
  title    = "Global estimates of mammalian viral diversity accounting for host
              sharing",
  author   = "Carlson, Colin J and Zipfel, Casey M and Garnier, Romain and
              Bansal, Shweta",
  abstract = "Present estimates suggest there are over 1 million virus species
              found in mammals alone, with about half a million posing a
              possible threat to human health. Although previous estimates
              assume linear scaling between host and virus diversity, we show
              that ecological network theory predicts a non-linear
              relationship, produced by patterns of host sharing among virus
              species. To account for host sharing, we fit a power law scaling
              relationship for host-virus species interaction networks. We
              estimate that there are about 40,000 virus species in mammals
              (including ~10,000 viruses with zoonotic potential), a reduction
              of two orders of magnitude from present projections of viral
              diversity. We expect that the increasing availability of
              host-virus association data will improve the precision of these
              estimates and their use in the sampling and surveillance of
              pathogens with pandemic potential. We suggest host sharing should
              be more widely included in macroecological approaches to
              estimating biodiversity.",
  journal  = "Nat Ecol Evol",
  volume   =  3,
  number   =  7,
  pages    = "1070--1075",
  month    =  jul,
  year     =  2019,
  language = "en"
}

@MISC{Roux2019-lt,
  title   = "Cryptic inoviruses revealed as pervasive in bacteria and archaea
             across Earth's biomes",
  author  = "Roux, Simon and Krupovic, Mart and Daly, Rebecca A and Borges,
             Adair L and Nayfach, Stephen and Schulz, Frederik and Sharrar,
             Allison and Matheus Carnevali, Paula B and Cheng, Jan-Fang and
             Ivanova, Natalia N and Bondy-Denomy, Joseph and Wrighton, Kelly C
             and Woyke, Tanja and Visel, Axel and Kyrpides, Nikos C and
             Eloe-Fadrosh, Emiley A",
  journal = "Nature Microbiology",
  volume  =  4,
  number  =  11,
  pages   = "1895--1906",
  year    =  2019
}

@ARTICLE{Hugenholtz2021-fk,
  title    = "Prokaryotic taxonomy and nomenclature in the age of big sequence
              data",
  author   = "Hugenholtz, Philip and Chuvochina, Maria and Oren, Aharon and
              Parks, Donovan H and Soo, Rochelle M",
  abstract = "The classification of life forms into a hierarchical system
              (taxonomy) and the application of names to this hierarchy
              (nomenclature) is at a turning point in microbiology. The
              unprecedented availability of genome sequences means that a
              taxonomy can be built upon a comprehensive evolutionary
              framework, a longstanding goal of taxonomists. However, there is
              resistance to adopting a single framework to preserve taxonomic
              freedom, and ever increasing numbers of genomes derived from
              uncultured prokaryotes threaten to overwhelm current
              nomenclatural practices, which are based on characterised
              isolates. The challenge ahead then is to reach a consensus on the
              taxonomic framework and to adapt and scale the existing
              nomenclatural code, or create a new code, to systematically
              incorporate uncultured taxa into the chosen framework.",
  journal  = "ISME J.",
  volume   =  15,
  number   =  7,
  pages    = "1879--1892",
  month    =  jul,
  year     =  2021,
  language = "en"
}

@ARTICLE{Martino2022-ns,
  title    = "Microbiota succession throughout life from the cradle to the
              grave",
  author   = "Martino, Cameron and Dilmore, Amanda Hazel and Burcham, Zachary M
              and Metcalf, Jessica L and Jeste, Dilip and Knight, Rob",
  abstract = "Associations between age and the human microbiota are robust and
              reproducible. The microbial composition at several body sites can
              predict human chronological age relatively accurately. Although
              it is largely unknown why specific microorganisms are more
              abundant at certain ages, human microbiota research has
              elucidated a series of microbial community transformations that
              occur between birth and death. In this Review, we explore
              microbial succession in the healthy human microbiota from the
              cradle to the grave. We discuss the stages from primary
              succession at birth, to disruptions by disease or antibiotic use,
              to microbial expansion at death. We address how these successions
              differ by body site and by domain (bacteria, fungi or viruses).
              We also review experimental tools that microbiota researchers use
              to conduct this work. Finally, we discuss future directions for
              studying the microbiota's relationship with age, including
              designing consistent, well-powered, longitudinal studies,
              performing robust statistical analyses and improving
              characterization of non-bacterial microorganisms.",
  journal  = "Nat. Rev. Microbiol.",
  month    =  jul,
  year     =  2022,
  language = "en"
}

@ARTICLE{Wick2017-as,
  title    = "Unicycler: Resolving bacterial genome assemblies from short and
              long sequencing reads",
  author   = "Wick, Ryan R and Judd, Louise M and Gorrie, Claire L and Holt,
              Kathryn E",
  abstract = "The Illumina DNA sequencing platform generates accurate but short
              reads, which can be used to produce accurate but fragmented
              genome assemblies. Pacific Biosciences and Oxford Nanopore
              Technologies DNA sequencing platforms generate long reads that
              can produce complete genome assemblies, but the sequencing is
              more expensive and error-prone. There is significant interest in
              combining data from these complementary sequencing technologies
              to generate more accurate ``hybrid'' assemblies. However, few
              tools exist that truly leverage the benefits of both types of
              data, namely the accuracy of short reads and the structural
              resolving power of long reads. Here we present Unicycler, a new
              tool for assembling bacterial genomes from a combination of short
              and long reads, which produces assemblies that are accurate,
              complete and cost-effective. Unicycler builds an initial assembly
              graph from short reads using the de novo assembler SPAdes and
              then simplifies the graph using information from short and long
              reads. Unicycler uses a novel semi-global aligner to align long
              reads to the assembly graph. Tests on both synthetic and real
              reads show Unicycler can assemble larger contigs with fewer
              misassemblies than other hybrid assemblers, even when long-read
              depth and accuracy are low. Unicycler is open source (GPLv3) and
              available at github.com/rrwick/Unicycler.",
  journal  = "PLoS Comput. Biol.",
  volume   =  13,
  number   =  6,
  pages    = "e1005595",
  month    =  jun,
  year     =  2017,
  language = "en"
}

@ARTICLE{Touchon2017-fw,
  title    = "Embracing the enemy: the diversification of microbial gene
              repertoires by phage-mediated horizontal gene transfer",
  author   = "Touchon, Marie and Moura de Sousa, Jorge A and Rocha, Eduardo Pc",
  abstract = "Bacteriophages and archaeal viruses contribute, through lysogenic
              conversion or transduction, to the horizontal transfer of genetic
              material between microbial genomes. Recent genomics,
              metagenomics, and single cell studies have shown that lysogenic
              conversion is widespread and provides hosts with adaptive traits
              often associated with biotic interactions. The quantification of
              the evolutionary impact of transduction has lagged behind and
              requires further theoretical and experimental work. Nevertheless,
              recent studies suggested that generalized transduction plays a
              role in the transfer of antibiotic resistance genes and in the
              acquisition of novel genes during intra-specific bacterial
              competition. The characteristics of transduction and lysogenic
              conversion complement those of other mechanisms of transfer, and
              could play a key role in the spread of adaptive genes between
              communities.",
  journal  = "Curr. Opin. Microbiol.",
  volume   =  38,
  pages    = "66--73",
  month    =  aug,
  year     =  2017,
  language = "en"
}

@ARTICLE{Shkoporov2022-of,
  title    = "Mutualistic interplay between bacteriophages and bacteria in the
              human gut",
  author   = "Shkoporov, Andrey N and Turkington, Christopher J and Hill, Colin",
  abstract = "Bacteriophages (phages) are often described as obligate predators
              of their bacterial hosts, and phage predation is one of the
              leading forces controlling the density and distribution of
              bacterial populations. Every 48 h half of all bacteria on Earth
              are killed by phages. Efficient killing also forms the basis of
              phage therapy in humans and animals and the use of phages as food
              preservatives. In turn, bacteria have a plethora of resistance
              systems against phage attack, but very few bacterial species, if
              any, have entirely escaped phage predation. However, in complex
              communities and environments such as the human gut, this
              antagonistic model of attack and counter-defence does not fully
              describe the scope of phage-bacterium interactions. In this
              Review, we explore some of the more mutualistic aspects of
              phage-bacterium interactions in the human gut, and we suggest
              that the relationship between phages and their bacterial hosts in
              the gut is best characterized not as a fight to the death between
              enemies but rather as a mutualistic relationship between
              partners.",
  journal  = "Nat. Rev. Microbiol.",
  month    =  jun,
  year     =  2022,
  language = "en"
}

@ARTICLE{Garmaeva2019-ox,
  title    = "Studying the gut virome in the metagenomic era: challenges and
              perspectives",
  author   = "Garmaeva, Sanzhima and Sinha, Trishla and Kurilshikov, Alexander
              and Fu, Jingyuan and Wijmenga, Cisca and Zhernakova, Alexandra",
  abstract = "The human gut harbors a complex ecosystem of microorganisms,
              including bacteria and viruses. With the rise of next-generation
              sequencing technologies, we have seen a quantum leap in the study
              of human-gut-inhabiting bacteria, yet the viruses that infect
              these bacteria, known as bacteriophages, remain underexplored. In
              this review, we focus on what is known about the role of
              bacteriophages in human health and the technical challenges
              involved in studying the gut virome, of which they are a major
              component. Lastly, we discuss what can be learned from studies of
              bacteriophages in other ecosystems.",
  journal  = "BMC Biol.",
  volume   =  17,
  number   =  1,
  pages    = "84",
  month    =  oct,
  year     =  2019
}

@ARTICLE{Vatanen2022-vg,
  title    = "Transcription shifts in gut bacteria shared between mothers and
              their infants",
  author   = "Vatanen, Tommi and Sakwinska, O and Wilson, B and Combremont, S
              and Cutfield, W S and Chan, S Y and Godfrey, K M and {NiPPeR
              Study Group} and O'Sullivan, Justin M",
  abstract = "The infant gut microbiome contains a portion of bacteria that
              originate from the maternal gut. In the infant gut these bacteria
              encounter a new metabolic environment that differs from the adult
              gut, consequently requiring adjustments in their activities. We
              used pilot community RNA sequencing data (metatranscriptomes)
              from ten mother-infant dyads participating in the NiPPeR Study to
              characterize bacterial gene expression shifts following
              mother-to-infant transmission. Maternally-derived bacterial
              strains exhibited large scale gene expression shifts following
              the transmission to the infant gut, with 12,564 activated and
              14,844 deactivated gene families. The implicated genes were most
              numerous and the magnitude shifts greatest in Bacteroides spp.
              This pilot study demonstrates environment-dependent,
              strain-specific shifts in gut bacteria function and underscores
              the importance of metatranscriptomic analysis in microbiome
              studies.",
  journal  = "Sci. Rep.",
  volume   =  12,
  number   =  1,
  pages    = "1276",
  month    =  jan,
  year     =  2022,
  language = "en"
}

@ARTICLE{Hurwitz2016-wk,
  title    = "Viral metabolic reprogramming in marine ecosystems",
  author   = "Hurwitz, Bonnie L and U'Ren, Jana M",
  abstract = "Marine viruses often contain host-derived metabolic genes (i.e.,
              auxiliary metabolic genes; AMGs), which are hypothesized to
              increase viral replication by augmenting key steps in host
              metabolism. Currently described AMGs encompass a wide variety of
              metabolic functions, including amino acid and carbohydrate
              metabolism, energy production, and iron-sulfur cluster assembly
              and modification, and their community-wide gene content and
              abundance vary as a function of environmental conditions. Here,
              we describe different AMGs classes, their hypothesized role in
              redirecting host carbon metabolism, and their ecological
              importance. Focusing on metagenomic ocean surveys, we propose a
              new model where a suite of phage-encoded genes activate host
              pathways that respond rapidly to environmental cues, presumably
              resulting in rapid changes to host metabolic flux for phage
              production.",
  journal  = "Curr. Opin. Microbiol.",
  volume   =  31,
  pages    = "161--168",
  month    =  jun,
  year     =  2016,
  language = "en"
}

@ARTICLE{De_Sordi2019-ag,
  title     = "``I will survive'': A tale of bacteriophage-bacteria coevolution
               in the gut",
  author    = "De Sordi, Luisa and Louren{\c c}o, Marta and Debarbieux, Laurent",
  abstract  = "ABSTRACTViruses that infect bacteria, or bacteriophages, are
               among the most abundant entities in the gut microbiome. However,
               their role and the mechanisms by which they infect bacteria in
               the intestinal tract remain poorly understood. We recently
               reported that intestinal bacteria are an evolutionary force,
               driving the expansion of the bacteriophage host range by
               boosting the genetic variability of these viruses. Here, we
               expand these observations by studying antagonistic
               bacteriophage-bacteria coevolution dynamics and revealing that
               bacterial genetic variability is also increased under the
               pressure of bacteriophage predation. We propose a model showing
               how the expansion of bacteriophage-bacteria infection networks
               is relative to the opportunities for coevolution encountered in
               the intestinal tract. Our data suggest that predator-prey
               dynamics are perpetuated and differentiated in parallel, to
               generate and maintain intestinal microbial diversity and
               equilibrium.",
  journal   = "Gut Microbes",
  publisher = "Taylor \& Francis",
  volume    =  10,
  number    =  1,
  pages     = "92--99",
  month     =  jan,
  year      =  2019
}

@ARTICLE{Wei2022-rh,
  title    = "Reduced bacterial mortality and enhanced viral productivity
              during sinking in the ocean",
  author   = "Wei, Wei and Chen, Xiaowei and Weinbauer, Markus G and Jiao,
              Nianzhi and Zhang, Rui",
  abstract = "Particle sinking is an important process in the ocean,
              influencing the biogeochemical cycle and driving the long-term
              preservation of carbon into the deep sea via the biological pump.
              However, as an important component of marine ecosystems, the role
              of viruses during sinking is still poorly understood. Therefore,
              we performed a series of transplantation experiments in the South
              China Sea to simulate environmental changes during sinking and
              investigate their effects on viral eco-dynamics and life
              strategy. Our study demonstrated increased viral production but
              decreased virus-mediated bacterial mortality after
              transplantation. A larger burst size and switch from the
              lysogenic to lytic strategy were shown to contribute to enhanced
              viral productivity. We provide experimental evidence that surface
              viral ecological characteristics changed dramatically after
              transplantation into deep-sea waters, indicating a potential
              importance of viruses during vertical sinking in the ocean. This
              effect probably provides positive feedback on the efficiency of
              the biological pump.",
  journal  = "ISME J.",
  volume   =  16,
  number   =  6,
  pages    = "1668--1675",
  month    =  jun,
  year     =  2022,
  language = "en"
}

@ARTICLE{Koonin1996-vp,
  title    = "Sequencing and analysis of bacterial genomes",
  author   = "Koonin, E V and Mushegian, A R and Rudd, K E",
  abstract = "The complete sequences of two small bacterial genomes have
              recently become available, and those of several more species
              should follow within the next two years. Sequence comparisons
              show that the most bacterial proteins are highly conserved in
              evolution, allowing predictions to be made about the functions of
              most products of an uncharacterized genome. Bacterial genomes
              differ vastly in their gene repertoires. Although genes for
              components of the translation and transcription machinery, and
              for molecular chaperones, are typically maintained, many
              regulatory and metabolic systems are absent in bacteria with
              small genomes. Mycoplasma genitalium, with the smallest known
              genome of any cellular life form, lacks virtually all known
              regulatory genes, and its gene expression may be regulated
              differently than in other bacteria. Genome organization is
              evolutionarily labile: extensive gene shuffling leaves only very
              few conserved gene arrays in distantly related bacteria.",
  journal  = "Curr. Biol.",
  volume   =  6,
  number   =  4,
  pages    = "404--416",
  month    =  apr,
  year     =  1996,
  language = "en"
}

@ARTICLE{Oppenheim2005-ys,
  title    = "Switches in bacteriophage lambda development",
  author   = "Oppenheim, Amos B and Kobiler, Oren and Stavans, Joel and Court,
              Donald L and Adhya, Sankar",
  abstract = "The lysis-lysogeny decision of bacteriophage lambda (lambda) is a
              paradigm for developmental genetic networks. There are three key
              features, which characterize the network. First, after infection
              of the host bacterium, a decision between lytic or lysogenic
              development is made that is dependent upon environmental signals
              and the number of infecting phages per cell. Second, the
              lysogenic prophage state is very stable. Third, the prophage
              enters lytic development in response to DNA-damaging agents. The
              CI and Cro regulators define the lysogenic and lytic states,
              respectively, as a bistable genetic switch. Whereas CI maintains
              a stable lysogenic state, recent studies indicate that Cro sets
              the lytic course not by directly blocking CI expression but
              indirectly by lowering levels of CII which activates cI
              transcription. We discuss how a relatively simple phage like
              lambda employs a complex genetic network in decision-making
              processes, providing a challenge for theoretical modeling.",
  journal  = "Annu. Rev. Genet.",
  volume   =  39,
  pages    = "409--429",
  year     =  2005,
  language = "en"
}

@ARTICLE{Amarasinghe2020-cn,
  title    = "Opportunities and challenges in long-read sequencing data
              analysis",
  author   = "Amarasinghe, Shanika L and Su, Shian and Dong, Xueyi and Zappia,
              Luke and Ritchie, Matthew E and Gouil, Quentin",
  abstract = "Long-read technologies are overcoming early limitations in
              accuracy and throughput, broadening their application domains in
              genomics. Dedicated analysis tools that take into account the
              characteristics of long-read data are thus required, but the fast
              pace of development of such tools can be overwhelming. To assist
              in the design and analysis of long-read sequencing projects, we
              review the current landscape of available tools and present an
              online interactive database, long-read-tools.org, to facilitate
              their browsing. We further focus on the principles of error
              correction, base modification detection, and long-read
              transcriptomics analysis and highlight the challenges that
              remain.",
  journal  = "Genome Biol.",
  volume   =  21,
  number   =  1,
  pages    = "30",
  month    =  feb,
  year     =  2020,
  keywords = "Data analysis; Long-read sequencing; Oxford Nanopore; PacBio",
  language = "en"
}

@ARTICLE{Marcos-Zambrano2021-eg,
  title    = "Applications of Machine Learning in Human Microbiome Studies: A
              Review on Feature Selection, Biomarker Identification, Disease
              Prediction and Treatment",
  author   = "Marcos-Zambrano, Laura Judith and Karaduzovic-Hadziabdic, Kanita
              and Loncar Turukalo, Tatjana and Przymus, Piotr and Trajkovik,
              Vladimir and Aasmets, Oliver and Berland, Magali and Gruca,
              Aleksandra and Hasic, Jasminka and Hron, Karel and Klammsteiner,
              Thomas and Kolev, Mikhail and Lahti, Leo and Lopes, Marta B and
              Moreno, Victor and Naskinova, Irina and Org, Elin and
              Paci{\^e}ncia, In{\^e}s and Papoutsoglou, Georgios and Shigdel,
              Rajesh and Stres, Blaz and Vilne, Baiba and Yousef, Malik and
              Zdravevski, Eftim and Tsamardinos, Ioannis and Carrillo de Santa
              Pau, Enrique and Claesson, Marcus J and Moreno-Indias, Isabel and
              Truu, Jaak",
  abstract = "The number of microbiome-related studies has notably increased
              the availability of data on human microbiome composition and
              function. These studies provide the essential material to deeply
              explore host-microbiome associations and their relation to the
              development and progression of various complex diseases. Improved
              data-analytical tools are needed to exploit all information from
              these biological datasets, taking into account the peculiarities
              of microbiome data, i.e., compositional, heterogeneous and sparse
              nature of these datasets. The possibility of predicting
              host-phenotypes based on taxonomy-informed feature selection to
              establish an association between microbiome and predict disease
              states is beneficial for personalized medicine. In this regard,
              machine learning (ML) provides new insights into the development
              of models that can be used to predict outputs, such as
              classification and prediction in microbiology, infer host
              phenotypes to predict diseases and use microbial communities to
              stratify patients by their characterization of state-specific
              microbial signatures. Here we review the state-of-the-art ML
              methods and respective software applied in human microbiome
              studies, performed as part of the COST Action ML4Microbiome
              activities. This scoping review focuses on the application of ML
              in microbiome studies related to association and clinical use for
              diagnostics, prognostics, and therapeutics. Although the data
              presented here is more related to the bacterial community, many
              algorithms could be applied in general, regardless of the feature
              type. This literature and software review covering this broad
              topic is aligned with the scoping review methodology. The manual
              identification of data sources has been complemented with: (1)
              automated publication search through digital libraries of the
              three major publishers using natural language processing (NLP)
              Toolkit, and (2) an automated identification of relevant software
              repositories on GitHub and ranking of the related research papers
              relying on learning to rank approach.",
  journal  = "Front. Microbiol.",
  volume   =  12,
  pages    = "634511",
  month    =  feb,
  year     =  2021,
  keywords = "biomarker identification; disease prediction; feature selection;
              machine learning; microbiome",
  language = "en"
}

@ARTICLE{Wilmanski2021-ov,
  title    = "Gut microbiome pattern reflects healthy ageing and predicts
              survival in humans",
  author   = "Wilmanski, Tomasz and Diener, Christian and Rappaport, Noa and
              Patwardhan, Sushmita and Wiedrick, Jack and Lapidus, Jodi and
              Earls, John C and Zimmer, Anat and Glusman, Gustavo and Robinson,
              Max and Yurkovich, James T and Kado, Deborah M and Cauley, Jane A
              and Zmuda, Joseph and Lane, Nancy E and Magis, Andrew T and
              Lovejoy, Jennifer C and Hood, Leroy and Gibbons, Sean M and
              Orwoll, Eric S and Price, Nathan D",
  abstract = "The gut microbiome has important effects on human health, yet its
              importance in human ageing remains unclear. In the present study,
              we demonstrate that, starting in mid-to-late adulthood, gut
              microbiomes become increasingly unique to individuals with age.
              We leverage three independent cohorts comprising over 9,000
              individuals and find that compositional uniqueness is strongly
              associated with microbially produced amino acid derivatives
              circulating in the bloodstream. In older age (over ~80 years),
              healthy individuals show continued microbial drift towards a
              unique compositional state, whereas this drift is absent in less
              healthy individuals. The identified microbiome pattern of healthy
              ageing is characterized by a depletion of core genera found
              across most humans, primarily Bacteroides. Retaining a high
              Bacteroides dominance into older age, or having a low gut
              microbiome uniqueness measure, predicts decreased survival in a
              4-year follow-up. Our analysis identifies increasing
              compositional uniqueness of the gut microbiome as a component of
              healthy ageing, which is characterized by distinct microbial
              metabolic outputs in the blood.",
  journal  = "Nat Metab",
  volume   =  3,
  number   =  2,
  pages    = "274--286",
  month    =  feb,
  year     =  2021,
  language = "en"
}

@ARTICLE{Zhou2019-nc,
  title     = "Longitudinal multi-omics of host--microbe dynamics in
               prediabetes",
  author    = "Zhou, Wenyu and Sailani, M Reza and Contrepois, K{\'e}vin and
               Zhou, Yanjiao and Ahadi, Sara and Leopold, Shana R and Zhang,
               Martin J and Rao, Varsha and Avina, Monika and Mishra, Tejaswini
               and Johnson, Jethro and Lee-McMullen, Brittany and Chen, Songjie
               and Metwally, Ahmed A and Tran, Thi Dong Binh and Nguyen, Hoan
               and Zhou, Xin and Albright, Brandon and Hong, Bo-Young and
               Petersen, Lauren and Bautista, Eddy and Hanson, Blake and Chen,
               Lei and Spakowicz, Daniel and Bahmani, Amir and Salins, Denis
               and Leopold, Benjamin and Ashland, Melanie and Dagan-Rosenfeld,
               Orit and Rego, Shannon and Limcaoco, Patricia and Colbert,
               Elizabeth and Allister, Candice and Perelman, Dalia and Craig,
               Colleen and Wei, Eric and Chaib, Hassan and Hornburg, Daniel and
               Dunn, Jessilyn and Liang, Liang and Rose, Sophia Miryam
               Sch{\"u}ssler-Fiorenza and Kukurba, Kim and Piening, Brian and
               Rost, Hannes and Tse, David and McLaughlin, Tracey and
               Sodergren, Erica and Weinstock, George M and Snyder, Michael",
  abstract  = "Type 2 diabetes mellitus (T2D) is a growing health problem, but
               little is known about its early disease stages, its effects on
               biological processes or the transition to clinical T2D. To
               understand the earliest stages of T2D better, we obtained
               samples from 106 healthy individuals and individuals with
               prediabetes over approximately four years and performed deep
               profiling of transcriptomes, metabolomes, cytokines, and
               proteomes, as well as changes in the microbiome. This rich
               longitudinal data set revealed many insights: first, healthy
               profiles are distinct among individuals while displaying diverse
               patterns of intra- and/or inter-personal variability. Second,
               extensive host and microbial changes occur during respiratory
               viral infections and immunization, and immunization triggers
               potentially protective responses that are distinct from
               responses to respiratory viral infections. Moreover, during
               respiratory viral infections, insulin-resistant participants
               respond differently than insulin-sensitive participants. Third,
               global co-association analyses among the thousands of profiled
               molecules reveal specific host--microbe interactions that differ
               between insulin-resistant and insulin-sensitive individuals.
               Last, we identified early personal molecular signatures in one
               individual that preceded the onset of T2D, including the
               inflammation markers interleukin-1 receptor agonist (IL-1RA) and
               high-sensitivity C-reactive protein (CRP) paired with
               xenobiotic-induced immune signalling. Our study reveals insights
               into pathways and responses that differ between
               glucose-dysregulated and healthy individuals during health and
               disease and provides an open-access data resource to enable
               further research into healthy, prediabetic and T2D states. Deep
               profiling of transcriptomes, metabolomes, cytokines, and
               proteomes, alongside changes in the microbiome, in samples from
               individuals with and without prediabetes reveal insights into
               inter-individual variability and associations between changes in
               the microbiome and other factors.",
  journal   = "Nature",
  publisher = "Nature Publishing Group",
  volume    =  569,
  number    =  7758,
  pages     = "663--671",
  month     =  may,
  year      =  2019,
  language  = "en"
}

@UNPUBLISHED{Schwartz2021-ow,
  title    = "Phage-encoded sigma factors alter bacterial dormancy",
  author   = "Schwartz, D A and Lehmkuhl, B K and Lennon, J T",
  abstract = "By entering a reversible state of reduced metabolic activity,
              dormant microorganisms are able to tolerate suboptimal conditions
              that would otherwise reduce their fitness. Dormancy may also
              benefit bacteria by serving as a refuge from parasitic
              infections. Here we focus on dormancy in the Firmicutes , where
              endospore development is transcriptionally regulated by the
              expression of sigma factors. A disruption of this process could
              influence the survivorship and reproduction of phages that infect
              spore-forming hosts with implications for coevolutionary
              dynamics. Here, we characterized the distribution and diversity
              of sigma factors in nearly 3,500 phage genomes. Homologs of
              sporulation-specific sigma factors were identified in phages that
              infect spore-forming hosts. Unlike sigma factors required for
              phage reproduction, the sporulation-like sigma factors were
              non-essential for lytic infection. However, when expressed in the
              spore-forming Bacillus subtilis , sigma factors from phages
              activated the bacterial sporulation gene network and reduced
              spore yield. Our findings suggest that the acquisition of
              host-like transcriptional regulators may allow phages to
              manipulate a complex and ancient trait in one of the most
              abundant cell types on Earth. \#\#\# Competing Interest Statement
              The authors have declared no competing interest.",
  journal  = "bioRxiv",
  pages    = "2021.11.12.468384",
  month    =  nov,
  year     =  2021,
  language = "en"
}

@ARTICLE{Moss2020-ot,
  title    = "Complete, closed bacterial genomes from microbiomes using
              nanopore sequencing",
  author   = "Moss, Eli L and Maghini, Dylan G and Bhatt, Ami S",
  abstract = "Microbial genomes can be assembled from short-read sequencing
              data, but the assembly contiguity of these metagenome-assembled
              genomes is constrained by repeat elements. Correct assignment of
              genomic positions of repeats is crucial for understanding the
              effect of genome structure on genome function. We applied
              nanopore sequencing and our workflow, named Lathe, which
              incorporates long-read assembly and short-read error correction,
              to assemble closed bacterial genomes from complex microbiomes. We
              validated our approach with a synthetic mixture of 12 bacterial
              species. Seven genomes were completely assembled into single
              contigs and three genomes were assembled into four or fewer
              contigs. Next, we used our methods to analyze metagenomics data
              from 13 human stool samples. We assembled 20 circular genomes,
              including genomes of Prevotella copri and a candidate Cibiobacter
              sp. Despite the decreased nucleotide accuracy compared with
              alternative sequencing and assembly approaches, our methods
              improved assembly contiguity, allowing for investigation of the
              role of repeat elements in microbial function and adaptation.",
  journal  = "Nat. Biotechnol.",
  volume   =  38,
  number   =  6,
  pages    = "701--707",
  month    =  jun,
  year     =  2020,
  language = "en"
}

@ARTICLE{Turnbaugh2007-nw,
  title    = "The human microbiome project",
  author   = "Turnbaugh, Peter J and Ley, Ruth E and Hamady, Micah and
              Fraser-Liggett, Claire M and Knight, Rob and Gordon, Jeffrey I",
  abstract = "A strategy to understand the microbial components of the human
              genetic and metabolic landscape and how they contribute to normal
              physiology and predisposition to disease.",
  journal  = "Nature",
  volume   =  449,
  number   =  7164,
  pages    = "804--810",
  month    =  oct,
  year     =  2007,
  language = "en"
}

@ARTICLE{Jamet2017-pv,
  title    = "A widespread family of polymorphic toxins encoded by temperate
              phages",
  author   = "Jamet, Anne and Touchon, Marie and Ribeiro-Gon{\c c}alves, Bruno
              and Carri{\c c}o, Jo{\~a}o Andr{\'e} and Charbit, Alain and
              Nassif, Xavier and Ramirez, Mario and Rocha, Eduardo P C",
  abstract = "BACKGROUND: Polymorphic toxins (PTs) are multi-domain bacterial
              exotoxins belonging to distinct families that share common
              features in terms of domain organization. PTs are found in all
              major bacterial clades, including many toxic effectors of type V
              and type VI secretion systems. PTs modulate the dynamics of
              microbial communities by killing or inhibiting the growth of
              bacterial competitors lacking protective immunity proteins.
              RESULTS: In this work, we identified a novel widespread family of
              PTs, named MuF toxins, which were exclusively encoded within
              temperate phages and their prophages. By analyzing the predicted
              proteomes of 1845 bacteriophages and 2464 bacterial genomes, we
              found that MuF-containing proteins were frequently part of the
              DNA packaging module of tailed phages. Interestingly, MuF toxins
              were abundant in the human gut microbiome. CONCLUSIONS: Our
              results uncovered the presence of the MuF toxin family in the
              temperate phages of Firmicutes. The MuF toxin family is likely to
              play an important role in the ecology of the human microbiota
              where pathogens and commensal species belonging to the Firmicutes
              are abundant. We propose that MuF toxins could be delivered by
              phages into host bacteria and either influence the lysogeny
              decision or serve as bacterial weapons by inhibiting the growth
              of competing bacteria.",
  journal  = "BMC Biol.",
  volume   =  15,
  number   =  1,
  pages    = "75",
  month    =  aug,
  year     =  2017,
  keywords = "Bacterial genomics; Bacterial toxins; Phages",
  language = "en"
}

@ARTICLE{Jumper2021-dd,
  title    = "Highly accurate protein structure prediction with {AlphaFold}",
  author   = "Jumper, John and Evans, Richard and Pritzel, Alexander and Green,
              Tim and Figurnov, Michael and Ronneberger, Olaf and
              Tunyasuvunakool, Kathryn and Bates, Russ and {\v Z}{\'\i}dek,
              Augustin and Potapenko, Anna and Bridgland, Alex and Meyer,
              Clemens and Kohl, Simon A A and Ballard, Andrew J and Cowie,
              Andrew and Romera-Paredes, Bernardino and Nikolov, Stanislav and
              Jain, Rishub and Adler, Jonas and Back, Trevor and Petersen, Stig
              and Reiman, David and Clancy, Ellen and Zielinski, Michal and
              Steinegger, Martin and Pacholska, Michalina and Berghammer, Tamas
              and Bodenstein, Sebastian and Silver, David and Vinyals, Oriol
              and Senior, Andrew W and Kavukcuoglu, Koray and Kohli, Pushmeet
              and Hassabis, Demis",
  abstract = "Proteins are essential to life, and understanding their structure
              can facilitate a mechanistic understanding of their function.
              Through an enormous experimental effort1-4, the structures of
              around 100,000 unique proteins have been determined5, but this
              represents a small fraction of the billions of known protein
              sequences6,7. Structural coverage is bottlenecked by the months
              to years of painstaking effort required to determine a single
              protein structure. Accurate computational approaches are needed
              to address this gap and to enable large-scale structural
              bioinformatics. Predicting the three-dimensional structure that a
              protein will adopt based solely on its amino acid sequence-the
              structure prediction component of the 'protein folding
              problem'8-has been an important open research problem for more
              than 50 years9. Despite recent progress10-14, existing methods
              fall far short of atomic accuracy, especially when no homologous
              structure is available. Here we provide the first computational
              method that can regularly predict protein structures with atomic
              accuracy even in cases in which no similar structure is known. We
              validated an entirely redesigned version of our neural
              network-based model, AlphaFold, in the challenging 14th Critical
              Assessment of protein Structure Prediction (CASP14)15,
              demonstrating accuracy competitive with experimental structures
              in a majority of cases and greatly outperforming other methods.
              Underpinning the latest version of AlphaFold is a novel machine
              learning approach that incorporates physical and biological
              knowledge about protein structure, leveraging multi-sequence
              alignments, into the design of the deep learning algorithm.",
  journal  = "Nature",
  volume   =  596,
  number   =  7873,
  pages    = "583--589",
  month    =  aug,
  year     =  2021,
  language = "en"
}

@ARTICLE{Chaumeil2019-ce,
  title    = "{GTDB-Tk}: a toolkit to classify genomes with the Genome Taxonomy
              Database",
  author   = "Chaumeil, Pierre-Alain and Mussig, Aaron J and Hugenholtz, Philip
              and Parks, Donovan H",
  abstract = "SUMMARY: The GTDB Toolkit (GTDB-Tk) provides objective taxonomic
              assignments for bacterial and archaeal genomes based on the
              Genome Taxonomy Database (GTDB). GTDB-Tk is computationally
              efficient and able to classify thousands of draft genomes in
              parallel. Here we demonstrate the accuracy of the GTDB-Tk
              taxonomic assignments by evaluating its performance on a
              phylogenetically diverse set of 10,156 bacterial and archaeal
              metagenome-assembled genomes. AVAILABILITY: GTDB-Tk is
              implemented in Python and licensed under the GNU General Public
              License v3.0. Source code and documentation are available at:
              https://github.com/ecogenomics/gtdbtk. SUPPLEMENTARY INFORMATION:
              Supplementary data are available at Bioinformatics online.",
  journal  = "Bioinformatics",
  month    =  nov,
  year     =  2019,
  language = "en"
}

@ARTICLE{De_Jonge2019-yw,
  title    = "Molecular and Evolutionary Determinants of Bacteriophage Host
              Range",
  author   = "de Jonge, Patrick A and Nobrega, Franklin L and Brouns, Stan J J
              and Dutilh, Bas E",
  abstract = "The host range of a bacteriophage is the taxonomic diversity of
              hosts it can successfully infect. Host range, one of the central
              traits to understand in phages, is determined by a range of
              molecular interactions between phage and host throughout the
              infection cycle. While many well studied model phages seem to
              exhibit a narrow host range, recent ecological and metagenomics
              studies indicate that phages may have specificities that range
              from narrow to broad. There is a growing body of studies on the
              molecular mechanisms that enable phages to infect multiple hosts.
              These mechanisms, and their evolution, are of considerable
              importance to understanding phage ecology and the various
              clinical, industrial, and biotechnological applications of phage.
              Here we review knowledge of the molecular mechanisms that
              determine host range, provide a framework defining broad host
              range in an evolutionary context, and highlight areas for
              additional research.",
  journal  = "Trends Microbiol.",
  volume   =  27,
  number   =  1,
  pages    = "51--63",
  month    =  jan,
  year     =  2019,
  keywords = "bacteriophage; broad-host-range phages; phage therapy;
              specificity; virus--host interaction",
  language = "en"
}

@ARTICLE{Daubin2003-hx,
  title    = "The source of laterally transferred genes in bacterial genomes",
  author   = "Daubin, Vincent and Lerat, Emmanuelle and Perri{\`e}re, Guy",
  abstract = "BACKGROUND: Laterally transferred genes have often been
              identified on the basis of compositional features that
              distinguish them from ancestral genes in the genome. These genes
              are usually A+T-rich, arguing either that there is a bias towards
              acquiring genes from donor organisms having low G+C contents or
              that genes acquired from organisms of similar genomic base
              compositions go undetected in these analyses. RESULTS: By
              examining the genome contents of closely related, fully sequenced
              bacteria, we uncovered genes confined to a single genome and
              examined the sequence features of these acquired genes. The
              analysis shows that few transfer events are overlooked by
              compositional analyses. Most observed lateral gene transfers do
              not correspond to free exchange of regular genes among bacterial
              genomes, but more probably represent the constituents of phages
              or other selfish elements. CONCLUSIONS: Although bacteria tend to
              acquire large amounts of DNA, the origin of these genes remains
              obscure. We have shown that contrary to what is often supposed,
              their composition cannot be explained by a previous genomic
              context. In contrast, these genes fit the description of recently
              described genes in lambdoid phages, named 'morons'. Therefore,
              results from genome content and compositional approaches to
              detect lateral transfers should not be cited as evidence for
              genetic exchange between distantly related bacteria.",
  journal  = "Genome Biol.",
  volume   =  4,
  number   =  9,
  pages    = "R57",
  month    =  aug,
  year     =  2003,
  language = "en"
}

@ARTICLE{Graham2018-me,
  title    = "Antigen discovery and specification of immunodominance
              hierarchies for {MHCII-restricted} epitopes",
  author   = "Graham, Daniel B and Luo, Chengwei and O'Connell, Daniel J and
              Lefkovith, Ariel and Brown, Eric M and Yassour, Moran and Varma,
              Mukund and Abelin, Jennifer G and Conway, Kara L and Jasso,
              Guadalupe J and Matar, Caline G and Carr, Steven A and Xavier,
              Ramnik J",
  abstract = "Identifying immunodominant T cell epitopes remains a significant
              challenge in the context of infectious disease, autoimmunity, and
              immuno-oncology. To address the challenge of antigen discovery,
              we developed a quantitative proteomic approach that enabled
              unbiased identification of major histocompatibility complex class
              II (MHCII)--associated peptide epitopes and biochemical features
              of antigenicity. On the basis of these data, we trained a deep
              neural network model for genome-scale predictions of
              immunodominant MHCII-restricted epitopes. We named this model
              bacteria originated T cell antigen (BOTA) predictor. In
              validation studies, BOTA accurately predicted novel CD4 T cell
              epitopes derived from the model pathogen Listeria monocytogenes
              and the commensal microorganism Muribaculum intestinale. To
              conclusively define immunodominant T cell epitopes predicted by
              BOTA, we developed a high-throughput approach to screen
              DNA-encoded peptide--MHCII libraries for functional recognition
              by T cell receptors identified from single-cell RNA sequencing.
              Collectively, these studies provide a framework for defining the
              immunodominance landscape across a broad range of immune
              pathologies.",
  journal  = "Nat. Med.",
  volume   =  24,
  number   =  11,
  pages    = "1762--1772",
  month    =  nov,
  year     =  2018
}

@ARTICLE{Gulyaeva2022-ww,
  title    = "Discovery, diversity, and functional associations of crAss-like
              phages in human gut metagenomes from four Dutch cohorts",
  author   = "Gulyaeva, Anastasia and Garmaeva, Sanzhima and Ruigrok, Renate A
              A A and Wang, Daoming and Riksen, Niels P and Netea, Mihai G and
              Wijmenga, Cisca and Weersma, Rinse K and Fu, Jingyuan and Vila,
              Arnau Vich and Kurilshikov, Alexander and Zhernakova, Alexandra",
  abstract = "The crAss-like phages are a diverse group of related viruses that
              includes some of the most abundant viruses of the human gut. To
              explore their diversity and functional role in human population
              and clinical cohorts, we analyze gut metagenomic data collected
              from 1,950 individuals from the Netherlands. We identify 1,556
              crAss-like phage genomes, including 125 species-level and 32
              genus-level clusters absent from the reference databases used.
              Analysis of their genomic features shows that closely related
              crAss-like phages can possess strikingly divergent regions
              responsible for transcription, presumably acquired through
              recombination. Prediction of crAss-like phage hosts points
              primarily to bacteria of the phylum Bacteroidetes, consistent
              with previous reports. Finally, we explore the temporal stability
              of crAss-like phages over a 4-year period and identify
              associations between the abundance of crAss-like phages and
              several human phenotypes, including depletion of crAss-like
              phages in inflammatory bowel disease patients.",
  journal  = "Cell Rep.",
  volume   =  38,
  number   =  2,
  pages    = "110204",
  month    =  jan,
  year     =  2022,
  keywords = "IBD; crAss-like phages; human gut virome; metagenomics;
              population cohorts",
  language = "en"
}

@ARTICLE{Roux2015-gi,
  title    = "{VirSorter}: mining viral signal from microbial genomic data",
  author   = "Roux, Simon and Enault, Francois and Hurwitz, Bonnie L and
              Sullivan, Matthew B",
  abstract = "Viruses of microbes impact all ecosystems where microbes drive
              key energy and substrate transformations including the oceans,
              humans and industrial fermenters. However, despite this
              recognized importance, our understanding of viral diversity and
              impacts remains limited by too few model systems and reference
              genomes. One way to fill these gaps in our knowledge of viral
              diversity is through the detection of viral signal in microbial
              genomic data. While multiple approaches have been developed and
              applied for the detection of prophages (viral genomes integrated
              in a microbial genome), new types of microbial genomic data are
              emerging that are more fragmented and larger scale, such as
              Single-cell Amplified Genomes (SAGs) of uncultivated organisms or
              genomic fragments assembled from metagenomic sequencing. Here, we
              present VirSorter, a tool designed to detect viral signal in
              these different types of microbial sequence data in both a
              reference-dependent and reference-independent manner, leveraging
              probabilistic models and extensive virome data to maximize
              detection of novel viruses. Performance testing shows that
              VirSorter's prophage prediction capability compares to that of
              available prophage predictors for complete genomes, but is
              superior in predicting viral sequences outside of a host genome
              (i.e., from extrachromosomal prophages, lytic infections, or
              partially assembled prophages). Furthermore, VirSorter
              outperforms existing tools for fragmented genomic and metagenomic
              datasets, and can identify viral signal in assembled sequence
              (contigs) as short as 3kb, while providing near-perfect
              identification (>95\% Recall and 100\% Precision) on contigs of
              at least 10kb. Because VirSorter scales to large datasets, it can
              also be used in ``reverse'' to more confidently identify viral
              sequence in viral metagenomes by sorting away cellular DNA
              whether derived from gene transfer agents, generalized
              transduction or contamination. Finally, VirSorter is made
              available through the iPlant Cyberinfrastructure that provides a
              web-based user interface interconnected with the required
              computing resources. VirSorter thus complements existing prophage
              prediction softwares to better leverage fragmented, SAG and
              metagenomic datasets in a way that will scale to modern
              sequencing. Given these features, VirSorter should enable the
              discovery of new viruses in microbial datasets, and further our
              understanding of uncultivated viral communities across diverse
              ecosystems.",
  journal  = "PeerJ",
  volume   =  3,
  pages    = "e985",
  month    =  may,
  year     =  2015,
  keywords = "Bacteriophage; Metagenomics; Prophage; Single-cell amplified
              genome; Viral metagenomics; Virus",
  language = "en"
}

@ARTICLE{Fang2021-af,
  title    = "Slimy partners: the mucus barrier and gut microbiome in
              ulcerative colitis",
  author   = "Fang, Jian and Wang, Hui and Zhou, Yuping and Zhang, Hui and
              Zhou, Huiting and Zhang, Xiaohong",
  abstract = "Ulcerative colitis (UC) is a chronic recurrent intestinal
              inflammatory disease characterized by high incidence and young
              onset age. Recently, there have been some interesting findings in
              the pathogenesis of UC. The mucus barrier, which is composed of a
              mucin complex rich in O-glycosylation, not only provides
              nutrients and habitat for intestinal microbes but also
              orchestrates the taming of germs. In turn, the gut microbiota
              modulates the production and secretion of mucins and
              stratification of the mucus layers. Active bidirectional
              communication between the microbiota and its 'slimy' partner, the
              mucus barrier, seems to be a continually performed concerto,
              maintaining homeostasis of the gut ecological microenvironment.
              Any abnormalities may induce a disorder in the gut community,
              thereby causing inflammatory damage. Our review mainly focuses on
              the complicated communication between the mucus barrier and gut
              microbiome to explore a promising new avenue for UC therapy.",
  journal  = "Exp. Mol. Med.",
  volume   =  53,
  number   =  5,
  pages    = "772--787",
  month    =  may,
  year     =  2021,
  language = "en"
}

@ARTICLE{Parks2015-cs,
  title    = "{CheckM}: assessing the quality of microbial genomes recovered
              from isolates, single cells, and metagenomes",
  author   = "Parks, Donovan H and Imelfort, Michael and Skennerton, Connor T
              and Hugenholtz, Philip and Tyson, Gene W",
  abstract = "Large-scale recovery of genomes from isolates, single cells, and
              metagenomic data has been made possible by advances in
              computational methods and substantial reductions in sequencing
              costs. Although this increasing breadth of draft genomes is
              providing key information regarding the evolutionary and
              functional diversity of microbial life, it has become impractical
              to finish all available reference genomes. Making robust
              biological inferences from draft genomes requires accurate
              estimates of their completeness and contamination. Current
              methods for assessing genome quality are ad hoc and generally
              make use of a limited number of ``marker'' genes conserved across
              all bacterial or archaeal genomes. Here we introduce CheckM, an
              automated method for assessing the quality of a genome using a
              broader set of marker genes specific to the position of a genome
              within a reference genome tree and information about the
              collocation of these genes. We demonstrate the effectiveness of
              CheckM using synthetic data and a wide range of isolate-,
              single-cell-, and metagenome-derived genomes. CheckM is shown to
              provide accurate estimates of genome completeness and
              contamination and to outperform existing approaches. Using
              CheckM, we identify a diverse range of errors currently impacting
              publicly available isolate genomes and demonstrate that genomes
              obtained from single cells and metagenomic data vary
              substantially in quality. In order to facilitate the use of draft
              genomes, we propose an objective measure of genome quality that
              can be used to select genomes suitable for specific gene- and
              genome-centric analyses of microbial communities.",
  journal  = "Genome Res.",
  volume   =  25,
  number   =  7,
  pages    = "1043--1055",
  month    =  jul,
  year     =  2015,
  keywords = "omictools;phamb",
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Lane2015-yo,
  title     = "The unseen world: reflections on Leeuwenhoek (1677) 'Concerning
               little animals'",
  author    = "Lane, Nick",
  abstract  = "Leeuwenhoek's 1677 paper, the famous 'letter on the protozoa',
               gives the first detailed description of protists and bacteria
               living in a range of environments. The colloquial, diaristic
               style conceals the workings of a startlingly original
               experimental mind. Later scientists could not match the
               resolution and clarity of Leeuwenhoek's microscopes, so his
               discoveries were doubted or even dismissed over the following
               centuries, limiting their direct influence on the history of
               biology; but work in the twentieth century confirmed
               Leeuwenhoek's discovery of bacterial cells, with a resolution of
               less than 1 µm. Leeuwenhoek delighted most in the forms,
               interactions and behaviour of his little 'animalcules', which
               inhabited a previously unimagined microcosmos. In these
               reflections on the scientific reach of Leeuwenhoek's ideas and
               observations, I equate his questions with the preoccupations of
               our genomic era: what is the nature of Leeuwenhoek's
               animalcules, where do they come from, how do they relate to each
               other? Even with the powerful tools of modern biology, the
               answers are far from resolved-these questions still challenge
               our understanding of microbial evolution. This commentary was
               written to celebrate the 350th anniversary of the journal
               Philosophical Transactions of the Royal Society.",
  journal   = "Philos. Trans. R. Soc. Lond. B Biol. Sci.",
  publisher = "The Royal Society",
  volume    =  370,
  number    =  1666,
  pages     = "20140344",
  month     =  apr,
  year      =  2015,
  keywords  = "Leeuwenhoek; animalcule; bacteria; eukaryote; protozoa; tree of
               life",
  language  = "en"
}

@ARTICLE{Johansson2013-bj,
  title    = "The gastrointestinal mucus system in health and disease",
  author   = "Johansson, Malin E V and Sj{\"o}vall, Henrik and Hansson, Gunnar
              C",
  abstract = "Mucins--large, highly glycosylated proteins--are important for
              the luminal protection of the gastrointestinal tract. Enterocytes
              have their apical surface covered by transmembrane mucins and
              goblet cells produce the secreted gel-forming mucins that form
              mucus. The small intestine has a single unattached mucus layer,
              which in cystic fibrosis becomes attached, accounting for the
              intestinal manifestations of this disease. The stomach and colon
              have two layers of mucus; the inner layer is attached and the
              outer layer is less dense and unattached. In the colon, the outer
              mucus layer is the habitat for commensal bacteria. The inner
              mucus layer is impervious to bacteria and is renewed every hour
              by surface goblet cells. The crypt goblet cells have the ability
              to restitute the mucus layer by secretion, for example after an
              ischaemic challenge. Proteases of certain parasites and some
              bacteria can cleave mucins and dissolve the mucus as part of
              their pathogenicity. The inner mucus layer can, however, also
              become penetrable to bacteria by several other mechanisms,
              including aberrations in the immune system. When bacteria reach
              the epithelial surface, the immune system is activated and
              inflammation is triggered. This mechanism might occur in some
              types of ulcerative colitis.",
  journal  = "Nat. Rev. Gastroenterol. Hepatol.",
  volume   =  10,
  number   =  6,
  pages    = "352--361",
  month    =  jun,
  year     =  2013,
  language = "en"
}

@MISC{Hooper2012-ib,
  title   = "Interactions Between the Microbiota and the Immune System",
  author  = "Hooper, Lora V and Littman, Dan R and Macpherson, Andrew J",
  journal = "Science",
  volume  =  336,
  number  =  6086,
  pages   = "1268--1273",
  year    =  2012
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Barr2015-pp,
  title    = "Subdiffusive motion of bacteriophage in mucosal surfaces
              increases the frequency of bacterial encounters",
  author   = "Barr, Jeremy J and Auro, Rita and Sam-Soon, Nicholas and
              Kassegne, Sam and Peters, Gregory and Bonilla, Natasha and Hatay,
              Mark and Mourtada, Sarah and Bailey, Barbara and Youle, Merry and
              Felts, Ben and Baljon, Arlette and Nulton, Jim and Salamon, Peter
              and Rohwer, Forest",
  abstract = "Bacteriophages (phages) defend mucosal surfaces against bacterial
              infections. However, their complex interactions with their
              bacterial hosts and with the mucus-covered epithelium remain
              mostly unexplored. Our previous work demonstrated that T4 phage
              with Hoc proteins exposed on their capsid adhered to mucin
              glycoproteins and protected mucus-producing tissue culture cells
              in vitro. On this basis, we proposed our bacteriophage adherence
              to mucus (BAM) model of immunity. Here, to test this model, we
              developed a microfluidic device (chip) that emulates a mucosal
              surface experiencing constant fluid flow and mucin secretion
              dynamics. Using mucus-producing human cells and Escherichia coli
              in the chip, we observed similar accumulation and persistence of
              mucus-adherent T4 phage and nonadherent T4∆hoc phage in the
              mucus. Nevertheless, T4 phage reduced bacterial colonization of
              the epithelium >4,000-fold compared with T4∆hoc phage. This
              suggests that phage adherence to mucus increases encounters with
              bacterial hosts by some other mechanism. Phages are traditionally
              thought to be completely dependent on normal diffusion, driven by
              random Brownian motion, for host contact. We demonstrated that T4
              phage particles displayed subdiffusive motion in mucus, whereas
              T4∆hoc particles displayed normal diffusion. Experiments and
              modeling indicate that subdiffusive motion increases phage-host
              encounters when bacterial concentration is low. By concentrating
              phages in an optimal mucus zone, subdiffusion increases their
              host encounters and antimicrobial action. Our revised BAM model
              proposes that the fundamental mechanism of mucosal immunity is
              subdiffusion resulting from adherence to mucus. These findings
              suggest intriguing possibilities for engineering phages to
              manipulate and personalize the mucosal microbiome.",
  journal  = "Proc. Natl. Acad. Sci. U. S. A.",
  volume   =  112,
  number   =  44,
  pages    = "13675--13680",
  month    =  nov,
  year     =  2015,
  keywords = "BAM; mucus; search strategy; subdiffusion; virus",
  language = "en"
}

@ARTICLE{Yahara2021-jx,
  title    = "Long-read metagenomics using {PromethION} uncovers oral
              bacteriophages and their interaction with host bacteria",
  author   = "Yahara, Koji and Suzuki, Masato and Hirabayashi, Aki and Suda,
              Wataru and Hattori, Masahira and Suzuki, Yutaka and Okazaki,
              Yusuke",
  abstract = "Bacteriophages (phages), or bacterial viruses, are very diverse
              and highly abundant worldwide, including as a part of the human
              microbiomes. Although a few metagenomic studies have focused on
              oral phages, they relied on short-read sequencing. Here, we
              conduct a long-read metagenomic study of human saliva using
              PromethION. Our analyses, which integrate both PromethION and
              HiSeq data of >30 Gb per sample with low human DNA contamination,
              identify hundreds of viral contigs; 0-43.8\% and 12.5-56.3\% of
              the confidently predicted phages and prophages, respectively, do
              not cluster with those reported previously. Our analyses
              demonstrate enhanced scaffolding, and the ability to place a
              prophage in its host genomic context and enable its taxonomic
              classification. Our analyses also identify a Streptococcus
              phage/prophage group and nine jumbo phages/prophages. 86\% of the
              phage/prophage group and 67\% of the jumbo phages/prophages
              contain remote homologs of antimicrobial resistance genes.
              Pan-genome analysis of the phages/prophages reveals remarkable
              diversity, identifying 0.3\% and 86.4\% of the genes as core and
              singletons, respectively. Furthermore, our study suggests that
              oral phages present in human saliva are under selective pressure
              to escape CRISPR immunity. Our study demonstrates the power of
              long-read metagenomics utilizing PromethION in uncovering
              bacteriophages and their interaction with host bacteria.",
  journal  = "Nat. Commun.",
  volume   =  12,
  number   =  1,
  pages    = "27",
  month    =  jan,
  year     =  2021,
  language = "en"
}

@ARTICLE{Zhao2017-uf,
  title    = "Intestinal virome changes precede autoimmunity in type {I}
              diabetes-susceptible children",
  author   = "Zhao, Guoyan and Vatanen, Tommi and Droit, Lindsay and Park,
              Arnold and Kostic, Aleksandar D and Poon, Tiffany W and Vlamakis,
              Hera and Siljander, Heli and H{\"a}rk{\"o}nen, Taina and
              H{\"a}m{\"a}l{\"a}inen, Anu-Maaria and Peet, Aleksandr and
              Tillmann, Vallo and Ilonen, Jorma and Wang, David and Knip,
              Mikael and Xavier, Ramnik J and Virgin, Herbert W",
  abstract = "Viruses have long been considered potential triggers of
              autoimmune diseases. Here we defined the intestinal virome from
              birth to the development of autoimmunity in children at risk for
              type 1 diabetes (T1D). A total of 220 virus-enriched preparations
              from serially collected fecal samples from 11 children (cases)
              who developed serum autoantibodies associated with T1D (of whom
              five developed clinical T1D) were compared with samples from
              controls. Intestinal viromes of case subjects were less diverse
              than those of controls. Among eukaryotic viruses, we identified
              significant enrichment of Circoviridae-related sequences in
              samples from controls in comparison with cases. Enterovirus,
              kobuvirus, parechovirus, parvovirus, and rotavirus sequences were
              frequently detected but were not associated with autoimmunity.
              For bacteriophages, we found higher Shannon diversity and
              richness in controls compared with cases and observed that
              changes in the intestinal virome over time differed between cases
              and controls. Using Random Forests analysis, we identified
              disease-associated viral bacteriophage contigs after subtraction
              of age-associated contigs. These disease-associated contigs were
              statistically linked to specific components of the bacterial
              microbiome. Thus, changes in the intestinal virome preceded
              autoimmunity in this cohort. Specific components of the virome
              were both directly and inversely associated with the development
              of human autoimmune disease.",
  journal  = "Proc. Natl. Acad. Sci. U. S. A.",
  volume   =  114,
  number   =  30,
  pages    = "E6166--E6175",
  month    =  jul,
  year     =  2017,
  keywords = "Circoviridae; bacteriophages; microbiome; type 1 diabetes;
              virome;phamb;phamb;1st\_regular\_assessment",
  language = "en"
}

@UNPUBLISHED{Shkoporov2018-ij,
  title    = "{$\Phi$CrAss001}, a member of the most abundant bacteriophage
              family in the human gut, infects Bacteroides",
  author   = "Shkoporov, Andrey N and Khokhlova, Ekaterina V and Brian
              Fitzgerald, C and Stockdale, Stephen R and Draper, Lorraine A and
              Paul Ross, R and Hill, Colin",
  abstract = "Abstract $\Phi$CrAss001, isolated from human faecal material, is
              the first member of the extensive crAssphage family to be grown
              in pure culture. The bacteriophage infects the human gut symbiont
              Bacteroides intestinalis, confirming in silico predictions of the
              likely host. Genome analysis demonstrated that the phage DNA is
              102 kb in size, has an unusual genome organisation and does not
              possess any obvious genes for lysogeny. In addition, electron
              microscopy confirms that $\varphi$crAss001 has a podovirus-like
              morphology. Despite the absence of lysogeny genes,
              $\varphi$crAss001 replicates in a way that does not disrupt
              proliferation of the host bacterium and is able to maintain
              itself in continuous host culture.",
  journal  = "Cold Spring Harbor Laboratory",
  pages    = "354837",
  month    =  jun,
  year     =  2018,
  language = "en"
}

@ARTICLE{Wang2010-sy,
  title    = "Cryptic prophages help bacteria cope with adverse environments",
  author   = "Wang, Xiaoxue and Kim, Younghoon and Ma, Qun and Hong, Seok Hoon
              and Pokusaeva, Karina and Sturino, Joseph M and Wood, Thomas K",
  abstract = "Phages are the most abundant entity in the biosphere and
              outnumber bacteria by a factor of 10. Phage DNA may also
              constitute 20\% of bacterial genomes; however, its role is ill
              defined. Here, we explore the impact of cryptic prophages on cell
              physiology by precisely deleting all nine prophage elements (166
              kbp) using Escherichia coli. We find that cryptic prophages
              contribute significantly to resistance to sub-lethal
              concentrations of quinolone and $\beta$-lactam antibiotics
              primarily through proteins that inhibit cell division (for
              example, KilR of rac and DicB of Qin). Moreover, the prophages
              are beneficial for withstanding osmotic, oxidative and acid
              stresses, for increasing growth, and for influencing biofilm
              formation. Prophage CPS-53 proteins YfdK, YfdO and YfdS enhanced
              resistance to oxidative stress, prophages e14, CPS-53 and CP4-57
              increased resistance to acid, and e14 and rac proteins increased
              early biofilm formation. Therefore, cryptic prophages provide
              multiple benefits to the host for surviving adverse environmental
              conditions.",
  journal  = "Nat. Commun.",
  volume   =  1,
  pages    = "147",
  year     =  2010,
  language = "en"
}

@ARTICLE{Zund2021-hp,
  title    = "High throughput sequencing provides exact genomic locations of
              inducible prophages and accurate phage-to-host ratios in gut
              microbial strains",
  author   = "Z{\"u}nd, Mirjam and Ruscheweyh, Hans-Joachim and Field,
              Christopher M and Meyer, Natalie and Cuenca, Miguelangel and
              Hoces, Daniel and Hardt, Wolf-Dietrich and Sunagawa, Shinichi",
  abstract = "BACKGROUND: Temperate phages influence the density, diversity and
              function of bacterial populations. Historically, they have been
              described as carriers of toxins. More recently, they have also
              been recognised as direct modulators of the gut microbiome, and
              indirectly of host health and disease. Despite recent advances in
              studying prophages using non-targeted sequencing approaches,
              methodological challenges in identifying inducible prophages in
              bacterial genomes and quantifying their activity have limited our
              understanding of prophage-host interactions. RESULTS: We present
              methods for using high-throughput sequencing data to locate
              inducible prophages, including those previously undiscovered, to
              quantify prophage activity and to investigate their replication.
              We first used the well-established Salmonella enterica serovar
              Typhimurium/p22 system to validate our methods for (i)
              quantifying phage-to-host ratios and (ii) accurately locating
              inducible prophages in the reference genome based on
              phage-to-host ratio differences and read alignment alterations
              between induced and non-induced prophages. Investigating
              prophages in bacterial strains from a murine gut model microbiota
              known as Oligo-MM12 or sDMDMm2, we located five novel inducible
              prophages in three strains, quantified their activity and showed
              signatures of lateral transduction potential for two of them.
              Furthermore, we show that the methods were also applicable to
              metagenomes of induced faecal samples from Oligo-MM12 mice,
              including for strains with a relative abundance below 1\%,
              illustrating its potential for the discovery of inducible
              prophages also in more complex metagenomes. Finally, we show that
              predictions of prophage locations in reference genomes of the
              strains we studied were variable and inconsistent for four
              bioinformatic tools we tested, which highlights the importance of
              their experimental validation. CONCLUSIONS: This study
              demonstrates that the integration of experimental induction and
              bioinformatic analysis presented here is a powerful approach to
              accurately locate inducible prophages using high-throughput
              sequencing data and to quantify their activity. The ability to
              generate such quantitative information will be critical in
              helping us to gain better insights into the factors that
              determine phage activity and how prophage-bacteria interactions
              influence our microbiome and impact human health. Video abstract.",
  journal  = "Microbiome",
  volume   =  9,
  number   =  1,
  pages    = "77",
  month    =  mar,
  year     =  2021,
  keywords = "Gut microbiota; High-throughput sequencing; Phage activity; Phage
              replication; Phage-to-host ratio; Prophage induction; Prophage
              localisation",
  language = "en"
}

@ARTICLE{Fraser2009-nf,
  title    = "The bacterial species challenge: making sense of genetic and
              ecological diversity",
  author   = "Fraser, Christophe and Alm, Eric J and Polz, Martin F and Spratt,
              Brian G and Hanage, William P",
  abstract = "The Bacteria and Archaea are the most genetically diverse
              superkingdoms of life, and techniques for exploring that
              diversity are only just becoming widespread. Taxonomists classify
              these organisms into species in much the same way as they
              classify eukaryotes, but differences in their biology-including
              horizontal gene transfer between distantly related taxa and
              variable rates of homologous recombination-mean that we still do
              not understand what a bacterial species is. This is not merely a
              semantic question; evolutionary theory should be able to explain
              why species exist at all levels of the tree of life, and we need
              to be able to define species for practical applications in
              industry, agriculture, and medicine. Recent studies have
              emphasized the need to combine genetic diversity and distinct
              ecology in an attempt to define species in a coherent and
              convincing fashion. The resulting data may help to discriminate
              among the many theories of prokaryotic species that have been
              produced to date.",
  journal  = "Science",
  volume   =  323,
  number   =  5915,
  pages    = "741--746",
  month    =  feb,
  year     =  2009,
  language = "en"
}

@ARTICLE{Rasmussen2020-pn,
  title    = "Faecal virome transplantation decreases symptoms of type 2
              diabetes and obesity in a murine model",
  author   = "Rasmussen, Torben S{\o}lbeck and Mentzel, Caroline M{\"a}rta
              Junker and Kot, Witold and Castro-Mej{\'\i}a, Josu{\'e} Leonardo
              and Zuffa, Simone and Swann, Jonathan Richard and Hansen, Lars
              Hestbjerg and Vogensen, Finn Kvist and Hansen, Axel Kornerup and
              Nielsen, Dennis Sandris",
  abstract = "OBJECTIVE: Development of obesity and type 2 diabetes (T2D) are
              associated with gut microbiota (GM) changes. The gut viral
              community is predominated by bacteriophages (phages), which are
              viruses that attack bacteria in a host-specific manner. The
              antagonistic behaviour of phages has the potential to alter the
              GM. As a proof-of-concept, we demonstrate the efficacy of faecal
              virome transplantation (FVT) from lean donors for shifting the
              phenotype of obese mice into closer resemblance of lean mice.
              DESIGN: The FVT consisted of viromes with distinct profiles
              extracted from the caecal content of mice from different vendors
              that were fed a low-fat (LF) diet for 14 weeks. Male C57BL/6NTac
              mice were divided into five groups: LF (as diet control),
              high-fat (HF) diet, HF+ampicillin (Amp), HF+Amp+FVT and HF+FVT.
              At weeks 6 and 7 of the study, the HF+FVT and HF+Amp+FVT mice
              were treated with FVT by oral gavage. The Amp groups were treated
              with Amp 24 hours prior to first FVT treatment. RESULTS: Six
              weeks after first FVT, the HF+FVT mice showed a significant
              decrease in weight gain compared with the HF group. Further,
              glucose tolerance was comparable between the LF and HF+FVT mice,
              while the other HF groups all had impaired glucose tolerance.
              These observations were supported by significant shifts in GM
              composition, blood plasma metabolome and expression levels of
              genes associated with obesity and T2D development. CONCLUSIONS:
              Transfer of caecal viral communities from mice with a lean
              phenotype into mice with an obese phenotype led to reduced weight
              gain and normalised blood glucose parameters relative to lean
              mice. We hypothesise that this effect is mediated via FVT-induced
              GM changes.",
  journal  = "Gut",
  month    =  mar,
  year     =  2020,
  keywords = "diabetes mellitus; gut differentiation; intestinal microbiology;
              obesity;1st\_regular\_assessment",
  language = "en"
}

@ARTICLE{Albertsen2013-en,
  title    = "Genome sequences of rare, uncultured bacteria obtained by
              differential coverage binning of multiple metagenomes",
  author   = "Albertsen, Mads and Hugenholtz, Philip and Skarshewski, Adam and
              Nielsen, K{\aa}re L and Tyson, Gene W and Nielsen, Per H",
  abstract = "Reference genomes are required to understand the diverse roles of
              microorganisms in ecology, evolution, human and animal health,
              but most species remain uncultured. Here we present a sequence
              composition-independent approach to recover high-quality
              microbial genomes from deeply sequenced metagenomes. Multiple
              metagenomes of the same community, which differ in relative
              population abundances, were used to assemble 31 bacterial
              genomes, including rare (<1\% relative abundance) species, from
              an activated sludge bioreactor. Twelve genomes were assembled
              into complete or near-complete chromosomes. Four belong to the
              candidate bacterial phylum TM7 and represent the most complete
              genomes for this phylum to date (relative abundances,
              0.06-1.58\%). Reanalysis of published metagenomes reveals that
              differential coverage binning facilitates recovery of more
              complete and higher fidelity genome bins than other currently
              used methods, which are primarily based on sequence composition.
              This approach will be an important addition to the standard
              metagenome toolbox and greatly improve access to genomes of
              uncultured microorganisms.",
  journal  = "Nat. Biotechnol.",
  volume   =  31,
  number   =  6,
  pages    = "533--538",
  month    =  jun,
  year     =  2013,
  language = "en"
}

@ARTICLE{Adriaenssens2020-gb,
  title    = "Taxonomy of prokaryotic viruses: 2018-2019 update from the {ICTV}
              Bacterial and Archaeal Viruses Subcommittee",
  author   = "Adriaenssens, Evelien M and Sullivan, Matthew B and Knezevic,
              Petar and van Zyl, Leonardo J and Sarkar, B L and Dutilh, Bas E
              and Alfenas-Zerbini, Poliane and {\L}obocka, Ma{\l}gorzata and
              Tong, Yigang and Brister, James Rodney and Moreno Switt, Andrea I
              and Klumpp, Jochen and Aziz, Ramy Karam and Barylski, Jakub and
              Uchiyama, Jumpei and Edwards, Rob A and Kropinski, Andrew M and
              Petty, Nicola K and Clokie, Martha R J and Kushkina, Alla I and
              Morozova, Vera V and Duffy, Siobain and Gillis, Annika and
              Rumnieks, Janis and Kurtb{\"o}ke, {\.I}pek and Chanishvili, Nina
              and Goodridge, Lawrence and Wittmann, Johannes and Lavigne, Rob
              and Jang, Ho Bin and Prangishvili, David and Enault, Francois and
              Turner, Dann and Poranen, Minna M and Oksanen, Hanna M and
              Krupovic, Mart",
  abstract = "This article is a summary of the activities of the ICTV's
              Bacterial and Archaeal Viruses Subcommittee for the years 2018
              and 2019. Highlights include the creation of a new order, 10
              families, 22 subfamilies, 424 genera and 964 species. Some of our
              concerns about the ICTV's ability to adjust to and incorporate
              new DNA- and protein-based taxonomic tools are discussed.",
  journal  = "Arch. Virol.",
  volume   =  165,
  number   =  5,
  pages    = "1253--1260",
  month    =  may,
  year     =  2020,
  language = "en"
}

@ARTICLE{Aggarwala2017-nz,
  title    = "Viral communities of the human gut: metagenomic analysis of
              composition and dynamics",
  author   = "Aggarwala, Varun and Liang, Guanxiang and Bushman, Frederic D",
  abstract = "BACKGROUND: The numerically most abundant biological entities on
              Earth are viruses. Vast populations prey on the cellular
              microbiota in all habitats, including the human gut. MAIN BODY:
              Here we review approaches for studying the human virome, and some
              recent results on movement of viral sequences between bacterial
              cells and eukaryotic hosts. We first overview biochemical and
              bioinformatic methods, emphasizing that specific choices in the
              methods used can have strong effects on the results obtained. We
              then review studies characterizing the virome of the healthy
              human gut, which reveal that most of the viruses detected are
              typically uncharacterized phage - the viral dark matter - and
              that viruses that infect human cells are encountered only rarely.
              We then review movement of phage between bacterial cells during
              antibiotic treatment. Here a radical proposal for extensive
              movement of antibiotic genes on phage has been challenged by a
              careful reanalysis of the metagenomic annotation methods used. We
              then review two recent studies of movement of whole phage
              communities between human individuals during fecal microbial
              transplantation, which emphasize the possible role of lysogeny in
              dispersal. SHORT CONCLUSION: Methods for studying the human gut
              virome are improving, yielding interesting data on movement of
              phage genes between cells and mammalian host organisms. However,
              viral populations are vast, and studies of their composition and
              function are just beginning.",
  journal  = "Mob. DNA",
  volume   =  8,
  pages    = "12",
  month    =  oct,
  year     =  2017,
  keywords = "Bacteriophage; DNA; Metagenomics; Microbiome; Transduction;
              Virome; Virus",
  language = "en"
}

@ARTICLE{Kingma2013-ng,
  title         = "{Auto-Encoding} Variational Bayes",
  author        = "Kingma, Diederik P and Welling, Max",
  abstract      = "How can we perform efficient inference and learning in
                   directed probabilistic models, in the presence of continuous
                   latent variables with intractable posterior distributions,
                   and large datasets? We introduce a stochastic variational
                   inference and learning algorithm that scales to large
                   datasets and, under some mild differentiability conditions,
                   even works in the intractable case. Our contributions is
                   two-fold. First, we show that a reparameterization of the
                   variational lower bound yields a lower bound estimator that
                   can be straightforwardly optimized using standard stochastic
                   gradient methods. Second, we show that for i.i.d. datasets
                   with continuous latent variables per datapoint, posterior
                   inference can be made especially efficient by fitting an
                   approximate inference model (also called a recognition
                   model) to the intractable posterior using the proposed lower
                   bound estimator. Theoretical advantages are reflected in
                   experimental results.",
  month         =  dec,
  year          =  2013,
  archivePrefix = "arXiv",
  primaryClass  = "stat.ML",
  eprint        = "1312.6114v10"
}

@ARTICLE{Johansson2014-hk,
  title    = "Mucus layers in inflammatory bowel disease",
  author   = "Johansson, Malin E V",
  abstract = "The intestinal epithelium is covered with mucus with the main
              structural building block being the densely O-glycosylated MUC2
              mucin. The intestinal epithelium is exposed to ingested material,
              our digestive machinery, and large amounts of microorganisms.
              Mucus is the first line of defense and aids to limit exposure to
              all these threats to the epithelium. In the small intestine,
              mucus acts as a matrix, which contains antimicrobial products,
              such as defensins and immunoglobulin A that limit epithelial
              exposure to the luminal bacteria. In the colon, the stratified
              inner mucus layer acts as a physical barrier excluding bacteria
              from the epithelium. Bacterial penetration of this normally
              restricted zone is observed in many colitis models and also in
              patients with ulcerative colitis. Mucus defects that allow
              bacteria to reach the epithelium and to stimulate an immune
              system response can lead to the development of intestinal
              inflammation. The current state of our knowledge concerning the
              function of the mucus layers and the main mucin component, MUC2,
              in inflammatory bowel disease is described in this review.",
  journal  = "Inflamm. Bowel Dis.",
  volume   =  20,
  number   =  11,
  pages    = "2124--2131",
  month    =  nov,
  year     =  2014,
  language = "en"
}

@MISC{Malik2017-st,
  title   = "Do Viruses Exchange Genes across Superkingdoms of Life?",
  author  = "Malik, Shahana S and Azem-e-Zahra, Syeda and Kim, Kyung Mo and
             Caetano-Anoll{\'e}s, Gustavo and Nasir, Arshan",
  journal = "Frontiers in Microbiology",
  volume  =  8,
  year    =  2017
}

@ARTICLE{Fullmer2015-yb,
  title    = "The pan-genome as a shared genomic resource: mutual cheating,
              cooperation and the black queen hypothesis",
  author   = "Fullmer, Matthew S and Soucy, Shannon M and Gogarten, Johann
              Peter",
  journal  = "Front. Microbiol.",
  volume   =  6,
  pages    = "728",
  month    =  jul,
  year     =  2015,
  keywords = "black queen hypothesis; gene transfer; pan-genome; red queen
              hypothesis; social cheating",
  language = "en"
}

@ARTICLE{Sereika2022-ii,
  title    = "Oxford Nanopore R10.4 long-read sequencing enables the generation
              of near-finished bacterial genomes from pure cultures and
              metagenomes without short-read or reference polishing",
  author   = "Sereika, Mantas and Kirkegaard, Rasmus Hansen and Karst, S{\o}ren
              Michael and Michaelsen, Thomas Yssing and S{\o}rensen, Emil Aarre
              and Wollenberg, Rasmus Dam and Albertsen, Mads",
  abstract = "Long-read Oxford Nanopore sequencing has democratized microbial
              genome sequencing and enables the recovery of highly contiguous
              microbial genomes from isolates or metagenomes. However, to
              obtain near-finished genomes it has been necessary to include
              short-read polishing to correct insertions and deletions derived
              from homopolymer regions. Here, we show that Oxford Nanopore
              R10.4 can be used to generate near-finished microbial genomes
              from isolates or metagenomes without short-read or reference
              polishing.",
  journal  = "Nat. Methods",
  volume   =  19,
  number   =  7,
  pages    = "823--826",
  month    =  jul,
  year     =  2022,
  language = "en"
}

@ARTICLE{Delahaye2021-ys,
  title    = "Sequencing {DNA} with nanopores: Troubles and biases",
  author   = "Delahaye, Clara and Nicolas, Jacques",
  abstract = "Oxford Nanopore Technologies' (ONT) long read sequencers offer
              access to longer DNA fragments than previous sequencer
              generations, at the cost of a higher error rate. While many
              papers have studied read correction methods, few have addressed
              the detailed characterization of observed errors, a task
              complicated by frequent changes in chemistry and software in ONT
              technology. The MinION sequencer is now more stable and this
              paper proposes an up-to-date view of its error landscape, using
              the most mature flowcell and basecaller. We studied Nanopore
              sequencing error biases on both bacterial and human DNA reads. We
              found that, although Nanopore sequencing is expected not to
              suffer from GC bias, it is a crucial parameter with respect to
              errors. In particular, low-GC reads have fewer errors than
              high-GC reads (about 6\% and 8\% respectively). The error profile
              for homopolymeric regions or regions with short repeats, the
              source of about half of all sequencing errors, also depends on
              the GC rate and mainly shows deletions, although there are some
              reads with long insertions. Another interesting finding is that
              the quality measure, although over-estimated, offers valuable
              information to predict the error rate as well as the abundance of
              reads. We supplemented this study with an analysis of a rapeseed
              RNA read set and shown a higher level of errors with a higher
              level of deletion in these data. Finally, we have implemented an
              open source pipeline for long-term monitoring of the error
              profile, which enables users to easily compute various analysis
              presented in this work, including for future developments of the
              sequencing device. Overall, we hope this work will provide a
              basis for the design of better error-correction methods.",
  journal  = "PLoS One",
  volume   =  16,
  number   =  10,
  pages    = "e0257521",
  month    =  oct,
  year     =  2021,
  language = "en"
}

@ARTICLE{Payne2021-xt,
  title     = "Identification and classification of antiviral defence systems
               in bacteria and archaea with {PADLOC} reveals new system types",
  author    = "Payne, Leighton J and Todeschini, Thomas C and Wu, Yi and Perry,
               Benjamin J and Ronson, Clive W and Fineran, Peter C and Nobrega,
               Franklin L and Jackson, Simon A",
  abstract  = "Abstract. To provide protection against viral infection and
               limit the uptake of mobile genetic elements, bacteria and
               archaea have evolved many diverse defence",
  journal   = "Nucleic Acids Res.",
  publisher = "Oxford Academic",
  volume    =  49,
  number    =  19,
  pages     = "10868--10878",
  month     =  oct,
  year      =  2021,
  keywords  = "antiviral agents; archaea; bacteriophages; genes; genome;
               bacteria; adenosine triphosphatases; synteny; unconsciousness;
               interspersed repetitive sequences; methyltransferase; crispr;
               immune response; virus diseases; infections",
  language  = "en"
}

@ARTICLE{Hertel2015-lu,
  title    = "Genome-based identification of active prophage regions by next
              generation sequencing in Bacillus licheniformis {DSM13}",
  author   = "Hertel, Robert and Rodr{\'\i}guez, David Pintor and
              Hollensteiner, Jacqueline and Dietrich, Sascha and Leimbach,
              Andreas and Hoppert, Michael and Liesegang, Heiko and Volland,
              Sonja",
  abstract = "Prophages are viruses, which have integrated their genomes into
              the genome of a bacterial host. The status of the prophage genome
              can vary from fully intact with the potential to form infective
              particles to a remnant state where only a few phage genes
              persist. Prophages have impact on the properties of their host
              and are therefore of great interest for genomic research and
              strain design. Here we present a genome- and next generation
              sequencing (NGS)-based approach for identification and activity
              evaluation of prophage regions. Seven prophage or prophage-like
              regions were identified in the genome of Bacillus licheniformis
              DSM13. Six of these regions show similarity to members of the
              Siphoviridae phage family. The remaining region encodes the B.
              licheniformis orthologue of the PBSX prophage from Bacillus
              subtilis. Analysis of isolated phage particles (induced by
              mitomycin C) from the wild-type strain and prophage deletion
              mutant strains revealed activity of the prophage regions BLi\_Pp2
              (PBSX-like), BLi\_Pp3 and BLi\_Pp6. In contrast to BLi\_Pp2 and
              BLi\_Pp3, neither phage DNA nor phage particles of BLi\_Pp6 could
              be visualized. However, the ability of prophage BLi\_Pp6 to
              generate particles could be confirmed by sequencing of
              particle-protected DNA mapping to prophage locus BLi\_Pp6. The
              introduced NGS-based approach allows the investigation of
              prophage regions and their ability to form particles. Our results
              show that this approach increases the sensitivity of prophage
              activity analysis and can complement more conventional approaches
              such as transmission electron microscopy (TEM).",
  journal  = "PLoS One",
  volume   =  10,
  number   =  3,
  pages    = "e0120759",
  month    =  mar,
  year     =  2015,
  language = "en"
}

@ARTICLE{Nissen2021-tt,
  title    = "Improved metagenome binning and assembly using deep variational
              autoencoders",
  author   = "Nissen, Jakob Nybo and Johansen, Joachim and Alles{\o}e, Rosa
              Lundbye and S{\o}nderby, Casper Kaae and Armenteros, Jose Juan
              Almagro and Gr{\o}nbech, Christopher Heje and Jensen, Lars Juhl
              and Nielsen, Henrik Bj{\o}rn and Petersen, Thomas Nordahl and
              Winther, Ole and Rasmussen, Simon",
  abstract = "Despite recent advances in metagenomic binning, reconstruction of
              microbial species from metagenomics data remains challenging.
              Here we develop variational autoencoders for metagenomic binning
              (VAMB), a program that uses deep variational autoencoders to
              encode sequence coabundance and k-mer distribution information
              before clustering. We show that a variational autoencoder is able
              to integrate these two distinct data types without any previous
              knowledge of the datasets. VAMB outperforms existing
              state-of-the-art binners, reconstructing 29-98\% and 45\% more
              near-complete (NC) genomes on simulated and real data,
              respectively. Furthermore, VAMB is able to separate closely
              related strains up to 99.5\% average nucleotide identity (ANI),
              and reconstructed 255 and 91 NC Bacteroides vulgatus and
              Bacteroides dorei sample-specific genomes as two distinct
              clusters from a dataset of 1,000 human gut microbiome samples. We
              use 2,606 NC bins from this dataset to show that species of the
              human gut microbiome have different geographical distribution
              patterns. VAMB can be run on standard hardware and is freely
              available at https://github.com/RasmussenLab/vamb .",
  journal  = "Nat. Biotechnol.",
  month    =  jan,
  year     =  2021,
  language = "en"
}

@ARTICLE{Alberti2017-qc,
  title    = "Viral to metazoan marine plankton nucleotide sequences from the
              Tara Oceans expedition",
  author   = "Alberti, Adriana and Poulain, Julie and Engelen, Stefan and
              Labadie, Karine and Romac, Sarah and Ferrera, Isabel and Albini,
              Guillaume and Aury, Jean-Marc and Belser, Caroline and Bertrand,
              Alexis and Cruaud, Corinne and Da Silva, Corinne and Dossat,
              Carole and Gavory, Fr{\'e}d{\'e}rick and Gas, Shahinaz and Guy,
              Julie and Haquelle, Maud and Jacoby, E'krame and Jaillon, Olivier
              and Lemainque, Arnaud and Pelletier, Eric and Samson, Ga{\"e}lle
              and Wessner, Mark and {Genoscope Technical Team} and Acinas,
              Silvia G and Royo-Llonch, Marta and Cornejo-Castillo, Francisco M
              and Logares, Ramiro and Fern{\'a}ndez-G{\'o}mez, Beatriz and
              Bowler, Chris and Cochrane, Guy and Amid, Clara and Hoopen, Petra
              Ten and De Vargas, Colomban and Grimsley, Nigel and Desgranges,
              Elodie and Kandels-Lewis, Stefanie and Ogata, Hiroyuki and
              Poulton, Nicole and Sieracki, Michael E and Stepanauskas, Ramunas
              and Sullivan, Matthew B and Brum, Jennifer R and Duhaime, Melissa
              B and Poulos, Bonnie T and Hurwitz, Bonnie L and {Tara Oceans
              Consortium Coordinators} and Pesant, St{\'e}phane and Karsenti,
              Eric and Wincker, Patrick",
  abstract = "A unique collection of oceanic samples was gathered by the Tara
              Oceans expeditions (2009-2013), targeting plankton organisms
              ranging from viruses to metazoans, and providing rich
              environmental context measurements. Thanks to recent advances in
              the field of genomics, extensive sequencing has been performed
              for a deep genomic analysis of this huge collection of samples. A
              strategy based on different approaches, such as metabarcoding,
              metagenomics, single-cell genomics and metatranscriptomics, has
              been chosen for analysis of size-fractionated plankton
              communities. Here, we provide detailed procedures applied for
              genomic data generation, from nucleic acids extraction to
              sequence production, and we describe registries of genomics
              datasets available at the European Nucleotide Archive (ENA,
              www.ebi.ac.uk/ena). The association of these metadata to the
              experimental procedures applied for their generation will help
              the scientific community to access these data and facilitate
              their analysis. This paper complements other efforts to provide a
              full description of experiments and open science resources
              generated from the Tara Oceans project, further extending their
              value for the study of the world's planktonic ecosystems.",
  journal  = "Sci Data",
  volume   =  4,
  pages    = "170093",
  month    =  aug,
  year     =  2017,
  keywords = "phamb;1st\_regular\_assessment",
  language = "en"
}

@ARTICLE{Kang2019-su,
  title    = "{MetaBAT} 2: an adaptive binning algorithm for robust and
              efficient genome reconstruction from metagenome assemblies",
  author   = "Kang, Dongwan D and Li, Feng and Kirton, Edward and Thomas,
              Ashleigh and Egan, Rob and An, Hong and Wang, Zhong",
  abstract = "We previously reported on MetaBAT, an automated metagenome
              binning software tool to reconstruct single genomes from
              microbial communities for subsequent analyses of uncultivated
              microbial species. MetaBAT has become one of the most popular
              binning tools largely due to its computational efficiency and
              ease of use, especially in binning experiments with a large
              number of samples and a large assembly. MetaBAT requires users to
              choose parameters to fine-tune its sensitivity and specificity.
              If those parameters are not chosen properly, binning accuracy can
              suffer, especially on assemblies of poor quality. Here, we
              developed MetaBAT 2 to overcome this problem. MetaBAT 2 uses a
              new adaptive binning algorithm to eliminate manual parameter
              tuning. We also performed extensive software engineering
              optimization to increase both computational and memory
              efficiency. Comparing MetaBAT 2 to alternative software tools on
              over 100 real world metagenome assemblies shows superior accuracy
              and computing speed. Binning a typical metagenome assembly takes
              only a few minutes on a single commodity workstation. We
              therefore recommend the community adopts MetaBAT 2 for their
              metagenome binning experiments. MetaBAT 2 is open source software
              and available at https://bitbucket.org/berkeleylab/metabat.",
  journal  = "PeerJ",
  volume   =  7,
  pages    = "e7359",
  month    =  jul,
  year     =  2019,
  keywords = "Clustering; Metagenome binning; Metagenomics",
  language = "en"
}

@ARTICLE{Manrique2016-vq,
  title    = "Healthy human gut phageome",
  author   = "Manrique, Pilar and Bolduc, Benjamin and Walk, Seth T and van der
              Oost, John and de Vos, Willem M and Young, Mark J",
  abstract = "The role of bacteriophages in influencing the structure and
              function of the healthy human gut microbiome is unknown. With few
              exceptions, previous studies have found a high level of
              heterogeneity in bacteriophages from healthy individuals. To
              better estimate and identify the shared phageome of humans, we
              analyzed a deep DNA sequence dataset of active bacteriophages and
              available metagenomic datasets of the gut bacteriophage community
              from healthy individuals. We found 23 shared bacteriophages in
              more than one-half of 64 healthy individuals from around the
              world. These shared bacteriophages were found in a significantly
              smaller percentage of individuals with gastrointestinal/irritable
              bowel disease. A network analysis identified 44 bacteriophage
              groups of which 9 (20\%) were shared in more than one-half of all
              64 individuals. These results provide strong evidence of a
              healthy gut phageome (HGP) in humans. The bacteriophage community
              in the human gut is a mixture of three classes: a set of core
              bacteriophages shared among more than one-half of all people, a
              common set of bacteriophages found in 20-50\% of individuals, and
              a set of bacteriophages that are either rarely shared or unique
              to a person. We propose that the core and common bacteriophage
              communities are globally distributed and comprise the HGP, which
              plays an important role in maintaining gut microbiome
              structure/function and thereby contributes significantly to human
              health.",
  journal  = "Proc. Natl. Acad. Sci. U. S. A.",
  volume   =  113,
  number   =  37,
  pages    = "10400--10405",
  month    =  sep,
  year     =  2016,
  keywords = "gut microbiome bacteriophage; gut microbiome viruses; human gut
              viral metagenome; shared microbiome viruses",
  language = "en"
}

@ARTICLE{Staley1985-zr,
  title    = "Measurement of in situ activities of nonphotosynthetic
              microorganisms in aquatic and terrestrial habitats",
  author   = "Staley, J T and Konopka, A",
  journal  = "Annu. Rev. Microbiol.",
  volume   =  39,
  pages    = "321--346",
  year     =  1985,
  language = "en"
}

@ARTICLE{Brown2021-dw,
  title    = "Gut microbiome {ADP-ribosyltransferases} are widespread
              phage-encoded fitness factors",
  author   = "Brown, Eric M and Arellano-Santoyo, Hugo and Temple, Emily R and
              Costliow, Zachary A and Pichaud, Matthieu and Hall, A Brantley
              and Liu, Kai and Durney, Michael A and Gu, Xiebin and Plichta,
              Damian R and Clish, Clary A and Porter, Jeffrey A and Vlamakis,
              Hera and Xavier, Ramnik J",
  abstract = "Bacterial ADP-ribosyltransferases (ADPRTs) have been described as
              toxins involved in pathogenesis through the modification of host
              proteins. Here, we report that ADPRTs are not pathogen restricted
              but widely prevalent in the human gut microbiome and often
              associated with phage elements. We validated their biochemical
              activity in a large clinical isolate collection and further
              examined Bxa, a highly abundant ADPRT in Bacteroides. Bxa is
              expressed, secreted, and enzymatically active in Bacteroides and
              can ADP-ribosylate non-muscle myosin II proteins. Addition of Bxa
              to epithelial cells remodeled the actin cytoskeleton and induced
              secretion of inosine. Bxa-encoding B. stercoris can use inosine
              as a carbon source and colonizes the gut to significantly greater
              numbers than a bxa-deleted strain in germ-free and altered
              Schaedler flora (ASF) mice. Colonization correlated with
              increased inosine concentrations in the feces and tissues.
              Altogether, our results show that ADPRTs are abundant in the
              microbiome and act as bacterial fitness factors.",
  journal  = "Cell Host Microbe",
  volume   =  29,
  number   =  9,
  pages    = "1351--1365.e11",
  month    =  sep,
  year     =  2021,
  keywords = "ADP-ribosylation; ADP-ribosyltransferases; Bacteriophages;
              Bacteroides; Microbiome; biofilms; cytoskeleton; fitness factor;
              gut colonization; inosine",
  language = "en"
}

@ARTICLE{Bepler2021-xn,
  title    = "Learning the protein language: Evolution, structure, and function",
  author   = "Bepler, Tristan and Berger, Bonnie",
  abstract = "Language models have recently emerged as a powerful
              machine-learning approach for distilling information from massive
              protein sequence databases. From readily available sequence data
              alone, these models discover evolutionary, structural, and
              functional organization across protein space. Using language
              models, we can encode amino-acid sequences into distributed
              vector representations that capture their structural and
              functional properties, as well as evaluate the evolutionary
              fitness of sequence variants. We discuss recent advances in
              protein language modeling and their applications to downstream
              protein property prediction problems. We then consider how these
              models can be enriched with prior biological knowledge and
              introduce an approach for encoding protein structural knowledge
              into the learned representations. The knowledge distilled by
              these models allows us to improve downstream function prediction
              through transfer learning. Deep protein language models are
              revolutionizing protein biology. They suggest new ways to
              approach protein and therapeutic design. However, further
              developments are needed to encode strong biological priors into
              protein language models and to increase their accessibility to
              the broader community.",
  journal  = "Cell Syst",
  volume   =  12,
  number   =  6,
  pages    = "654--669.e3",
  month    =  jun,
  year     =  2021,
  keywords = "contact prediction; deep neural networks; inductive bias;
              language models; natural language processing; protein sequences;
              proteins; transfer learning; transmembrane region prediction",
  language = "en"
}

@ARTICLE{Johansen2022-pa,
  title    = "Genome binning of viral entities from bulk metagenomics data",
  author   = "Johansen, Joachim and Plichta, Damian R and Nissen, Jakob Nybo
              and Jespersen, Marie Louise and Shah, Shiraz A and Deng, Ling and
              Stokholm, Jakob and Bisgaard, Hans and Nielsen, Dennis Sandris
              and S{\o}rensen, S{\o}ren J and Rasmussen, Simon",
  abstract = "Despite the accelerating number of uncultivated virus sequences
              discovered in metagenomics and their apparent importance for
              health and disease, the human gut virome and its interactions
              with bacteria in the gastrointestinal tract are not well
              understood. This is partly due to a paucity of whole-virome
              datasets and limitations in current approaches for identifying
              viral sequences in metagenomics data. Here, combining a
              deep-learning based metagenomics binning algorithm with paired
              metagenome and metavirome datasets, we develop Phages from
              Metagenomics Binning (PHAMB), an approach that allows the binning
              of thousands of viral genomes directly from bulk metagenomics
              data, while simultaneously enabling clustering of viral genomes
              into accurate taxonomic viral populations. When applied on the
              Human Microbiome Project 2 (HMP2) dataset, PHAMB recovered 6,077
              high-quality genomes from 1,024 viral populations, and identified
              viral-microbial host interactions. PHAMB can be advantageously
              applied to existing and future metagenomes to illuminate viral
              ecological dynamics with other microbiome constituents.",
  journal  = "Nat. Commun.",
  volume   =  13,
  number   =  1,
  pages    = "965",
  month    =  feb,
  year     =  2022,
  keywords = "Metagenome, Gastrointestinal Microbiome, Humans, Bacteriophages,
              Gastrointestinal Tract, Genome, Viral, Metagenomics,
              Virome;ptracker.bib",
  language = "eng"
}

@ARTICLE{Saeed2012-jg,
  title    = "Unsupervised discovery of microbial population structure within
              metagenomes using nucleotide base composition",
  author   = "Saeed, Isaam and Tang, Sen-Lin and Halgamuge, Saman K",
  abstract = "An approach to infer the unknown microbial population structure
              within a metagenome is to cluster nucleotide sequences based on
              common patterns in base composition, otherwise referred to as
              binning. When functional roles are assigned to the identified
              populations, a deeper understanding of microbial communities can
              be attained, more so than gene-centric approaches that explore
              overall functionality. In this study, we propose an unsupervised,
              model-based binning method with two clustering tiers, which uses
              a novel transformation of the oligonucleotide frequency-derived
              error gradient and GC content to generate coarse groups at the
              first tier of clustering; and tetranucleotide frequency to refine
              these groups at the secondary clustering tier. The proposed
              method has a demonstrated improvement over PhyloPythia, S-GSOM,
              TACOA and TaxSOM on all three benchmarks that were used for
              evaluation in this study. The proposed method is then applied to
              a pyrosequenced metagenomic library of mud volcano sediment
              sampled in southwestern Taiwan, with the inferred population
              structure validated against complementary sequencing of 16S
              ribosomal RNA marker genes. Finally, the proposed method was
              further validated against four publicly available metagenomes,
              including a highly complex Antarctic whale-fall bone sample,
              which was previously assumed to be too complex for binning prior
              to functional analysis.",
  journal  = "Nucleic Acids Res.",
  volume   =  40,
  number   =  5,
  pages    = "e34",
  month    =  mar,
  year     =  2012,
  language = "en"
}

@ARTICLE{Murray2021-ik,
  title     = "The Advantages and Challenges of Using Endolysins in a Clinical
               Setting",
  author    = "Murray, Ellen and Draper, Lorraine A and Ross, R Paul and Hill,
               Colin",
  abstract  = "Antibiotic-resistant pathogens are increasingly more prevalent
               and problematic. Traditional antibiotics are no longer a viable
               option for dealing with these multidrug-resistant microbes and
               so new approaches are needed. Bacteriophage-derived proteins
               such as endolysins could offer one effective solution.
               Endolysins are bacteriophage-encoded peptidoglycan hydrolases
               that act to lyse bacterial cells by targeting their cell's wall,
               particularly in Gram-positive bacteria due to their naturally
               exposed peptidoglycan layer. These lytic enzymes have received
               much interest from the scientific community in recent years for
               their specificity, mode of action, potential for engineering,
               and lack of resistance mechanisms. Over the past decade, a
               renewed interest in endolysin therapy has led to a number of
               successful applications. Recombinant endolysins have been shown
               to be effective against prominent pathogens such as MRSA,
               Listeria monocytogenes, Staphylococcus strains in biofilm
               formation, and Pseudomonas aeruginosa. Endolysins have also been
               studied in combination with other antimicrobials, giving a
               synergistic effect. Although endolysin therapy comes with some
               regulatory and logistical hurdles, the future looks promising,
               with the emergence of engineered ``next-generation'' lysins.
               This review will focus on the likelihood that endolysins will
               become a viable new antimicrobial therapy and the challenges
               that may have to be overcome along the way.",
  journal   = "Viruses",
  publisher = "Multidisciplinary Digital Publishing Institute",
  volume    =  13,
  number    =  4,
  pages     = "680",
  month     =  apr,
  year      =  2021,
  language  = "en"
}

@ARTICLE{Fritz2019-ej,
  title    = "{CAMISIM}: simulating metagenomes and microbial communities",
  author   = "Fritz, Adrian and Hofmann, Peter and Majda, Stephan and Dahms,
              Eik and Dr{\"o}ge, Johannes and Fiedler, Jessika and Lesker, Till
              R and Belmann, Peter and DeMaere, Matthew Z and Darling, Aaron E
              and Sczyrba, Alexander and Bremges, Andreas and McHardy, Alice C",
  abstract = "BACKGROUND: Shotgun metagenome data sets of microbial communities
              are highly diverse, not only due to the natural variation of the
              underlying biological systems, but also due to differences in
              laboratory protocols, replicate numbers, and sequencing
              technologies. Accordingly, to effectively assess the performance
              of metagenomic analysis software, a wide range of benchmark data
              sets are required. RESULTS: We describe the CAMISIM microbial
              community and metagenome simulator. The software can model
              different microbial abundance profiles, multi-sample time series,
              and differential abundance studies, includes real and simulated
              strain-level diversity, and generates second- and
              third-generation sequencing data from taxonomic profiles or de
              novo. Gold standards are created for sequence assembly, genome
              binning, taxonomic binning, and taxonomic profiling. CAMSIM
              generated the benchmark data sets of the first CAMI challenge.
              For two simulated multi-sample data sets of the human and mouse
              gut microbiomes, we observed high functional congruence to the
              real data. As further applications, we investigated the effect of
              varying evolutionary genome divergence, sequencing depth, and
              read error profiles on two popular metagenome assemblers,
              MEGAHIT, and metaSPAdes, on several thousand small data sets
              generated with CAMISIM. CONCLUSIONS: CAMISIM can simulate a wide
              variety of microbial communities and metagenome data sets
              together with standards of truth for method evaluation. All data
              sets and the software are freely available at
              https://github.com/CAMI-challenge/CAMISIM.",
  journal  = "Microbiome",
  volume   =  7,
  number   =  1,
  pages    = "17",
  month    =  feb,
  year     =  2019,
  keywords = "Benchmarking; CAMI; Genome binning; Metagenome assembly;
              Metagenomics software; Microbial community; Simulation; Taxonomic
              binning; Taxonomic profiling",
  language = "en"
}

@ARTICLE{Nielsen2014-vu,
  title    = "Identification and assembly of genomes and genetic elements in
              complex metagenomic samples without using reference genomes",
  author   = "Nielsen, H Bj{\o}rn and Almeida, Mathieu and Juncker, Agnieszka
              Sierakowska and Rasmussen, Simon and Li, Junhua and Sunagawa,
              Shinichi and Plichta, Damian R and Gautier, Laurent and Pedersen,
              Anders G and Le Chatelier, Emmanuelle and Pelletier, Eric and
              Bonde, Ida and Nielsen, Trine and Manichanh, Chaysavanh and
              Arumugam, Manimozhiyan and Batto, Jean-Michel and Quintanilha dos
              Santos, Marcelo B and Blom, Nikolaj and Borruel, Natalia and
              Burgdorf, Kristoffer S and Boumezbeur, Fouad and Casellas,
              Francesc and Dor{\'e}, Jo{\"e}l and Dworzynski, Piotr and
              Guarner, Francisco and Hansen, Torben and Hildebrand, Falk and
              Kaas, Rolf S and Kennedy, Sean and Kristiansen, Karsten and
              Kultima, Jens Roat and L{\'e}onard, Pierre and Levenez, Florence
              and Lund, Ole and Moumen, Bouziane and Le Paslier, Denis and
              Pons, Nicolas and Pedersen, Oluf and Prifti, Edi and Qin, Junjie
              and Raes, Jeroen and S{\o}rensen, S{\o}ren and Tap, Julien and
              Tims, Sebastian and Ussery, David W and Yamada, Takuji and
              Nielsen, H Bj{\o}rn and Almeida, Mathieu and Juncker, Agnieszka S
              and Rasmussen, Simon and Li, Junhua and Sunagawa, Shinichi and
              Plichta, Damian R and Gautier, Laurent and Pedersen, Anders G and
              Le Chatelier, Emmanuelle and Pelletier, Eric and Bonde, Ida and
              Nielsen, Trine and Manichanh, Chaysavanh and Arumugam,
              Manimozhiyan and Batto, Jean-Michel and Quintanilha dos Santos,
              Marcelo B and Blom, Nikolaj and Borruel, Natalia and Burgdorf,
              Kristoffer S and Boumezbeur, Fouad and Casellas, Francesc and
              Dor{\'e}, Jo{\"e}l and Dworzynski, Piotr and Guarner, Francisco
              and Hansen, Torben and Hildebrand, Falk and Kaas, Rolf S and
              Kennedy, Sean and Kristiansen, Karsten and Kultima, Jens Roat and
              Leonard, Pierre and Levenez, Florence and Lund, Ole and Moumen,
              Bouziane and Le Paslier, Denis and Pons, Nicolas and Pedersen,
              Oluf and Prifti, Edi and Qin, Junjie and Raes, Jeroen and
              S{\o}rensen, S{\o}ren and Tap, Julien and Tims, Sebastian and
              Ussery, David W and Yamada, Takuji and Renault, Pierre and
              Sicheritz-Ponten, Thomas and Bork, Peer and Wang, Jun and Brunak,
              S{\o}ren and Ehrlich, S Dusko and Jamet, Alexandre and
              M{\'e}rieux, Alexandre and Cultrone, Antonella and Torrejon,
              Antonio and Quinquis, Benoit and Brechot, Christian and Delorme,
              Christine and M'Rini, Christine and de Vos, Willem M and Maguin,
              Emmanuelle and Varela, Encarna and Guedon, Eric and Gwen, Falony
              and Haimet, Florence and Artiguenave, Fran{\c c}ois and
              Vandemeulebrouck, Gaetana and Denariaz, G{\'e}rard and Khaci,
              Ghalia and Blotti{\`e}re, Herv{\'e} and Knol, Jan and
              Weissenbach, Jean and van Hylckama Vlieg, Johan E T and Torben,
              J{\o}rgensen and Parkhill, Julian and Turner, Keith and van de
              Guchte, Maarten and Antolin, Maria and Rescigno, Maria and
              Kleerebezem, Michiel and Derrien, Muriel and Galleron, Nathalie
              and Sanchez, Nicolas and Grarup, Niels and Veiga, Patrick and
              Oozeer, Raish and Dervyn, Rozenn and Layec, S{\'e}verine and
              Bruls, Thomas and Winogradski, Yohanan and Erwin G, Zoetendal and
              Renault, Pierre and Sicheritz-Ponten, Thomas and Bork, Peer and
              Wang, Jun and Brunak, S{\o}ren and Ehrlich, S Dusko and {MetaHIT
              Consortium}",
  abstract = "Sequencing the microbial species present in complex metagenomic
              samples is made easier with a method that groups genes by
              co-abundance.",
  journal  = "Nat. Biotechnol.",
  volume   =  32,
  number   =  8,
  pages    = "822--828",
  month    =  aug,
  year     =  2014
}

@BOOK{Tungland2018-an,
  title     = "Human Microbiota in health and disease: From pathogenesis to
               therapy",
  author    = "Tungland, Bryan",
  publisher = "Academic Press",
  month     =  may,
  year      =  2018,
  address   = "San Diego, CA"
}

@ARTICLE{Kieft2021-hu,
  title    = "Ecology of inorganic sulfur auxiliary metabolism in widespread
              bacteriophages",
  author   = "Kieft, Kristopher and Zhou, Zhichao and Anderson, Rika E and
              Buchan, Alison and Campbell, Barbara J and Hallam, Steven J and
              Hess, Matthias and Sullivan, Matthew B and Walsh, David A and
              Roux, Simon and Anantharaman, Karthik",
  abstract = "Microbial sulfur metabolism contributes to biogeochemical cycling
              on global scales. Sulfur metabolizing microbes are infected by
              phages that can encode auxiliary metabolic genes (AMGs) to alter
              sulfur metabolism within host cells but remain poorly
              characterized. Here we identified 191 phages derived from twelve
              environments that encoded 227 AMGs for oxidation of sulfur and
              thiosulfate (dsrA, dsrC/tusE, soxC, soxD and soxYZ). Evidence for
              retention of AMGs during niche-differentiation of diverse phage
              populations provided evidence that auxiliary metabolism imparts
              measurable fitness benefits to phages with ramifications for
              ecosystem biogeochemistry. Gene abundance and expression profiles
              of AMGs suggested significant contributions by phages to sulfur
              and thiosulfate oxidation in freshwater lakes and oceans, and a
              sensitive response to changing sulfur concentrations in
              hydrothermal environments. Overall, our study provides
              fundamental insights on the distribution, diversity, and ecology
              of phage auxiliary metabolism associated with sulfur and
              reinforces the necessity of incorporating viral contributions
              into biogeochemical configurations.",
  journal  = "Nat. Commun.",
  volume   =  12,
  number   =  1,
  pages    = "3503",
  month    =  jun,
  year     =  2021,
  language = "en"
}

@ARTICLE{Haaber2016-kp,
  title    = "Bacterial viruses enable their host to acquire antibiotic
              resistance genes from neighbouring cells",
  author   = "Haaber, Jakob and Leisner, J{\o}rgen J and Cohn, Marianne T and
              Catalan-Moreno, Arancha and Nielsen, Jesper B and Westh, Henrik
              and Penad{\'e}s, Jos{\'e} R and Ingmer, Hanne",
  abstract = "Prophages are quiescent viruses located in the chromosomes of
              bacteria. In the human pathogen, Staphylococcus aureus, prophages
              are omnipresent and are believed to be responsible for the spread
              of some antibiotic resistance genes. Here we demonstrate that
              release of phages from a subpopulation of S. aureus cells enables
              the intact, prophage-containing population to acquire beneficial
              genes from competing, phage-susceptible strains present in the
              same environment. Phage infection kills competitor cells and bits
              of their DNA are occasionally captured in viral transducing
              particles. Return of such particles to the prophage-containing
              population can drive the transfer of genes encoding potentially
              useful traits such as antibiotic resistance. This process, which
              can be viewed as 'auto-transduction', allows S. aureus to
              efficiently acquire antibiotic resistance both in vitro and in an
              in vivo virulence model (wax moth larvae) and enables it to
              proliferate under strong antibiotic selection pressure. Our
              results may help to explain the rapid exchange of antibiotic
              resistance genes observed in S. aureus.",
  journal  = "Nat. Commun.",
  volume   =  7,
  pages    = "13333",
  month    =  nov,
  year     =  2016,
  language = "en"
}

@ARTICLE{Hirata2020-za,
  title    = "Associations of cardiovascular biomarkers and plasma albumin with
              exceptional survival to the highest ages",
  author   = "Hirata, Takumi and Arai, Yasumichi and Yuasa, Shinsuke and Abe,
              Yukiko and Takayama, Michiyo and Sasaki, Takashi and Kunitomi,
              Akira and Inagaki, Hiroki and Endo, Motoyoshi and Morinaga, Jun
              and Yoshimura, Kimio and Adachi, Tetsuo and Oike, Yuichi and
              Takebayashi, Toru and Okano, Hideyuki and Hirose, Nobuyoshi",
  abstract = "Supercentenarians (those aged $\geq$110 years) are approaching
              the current human longevity limit by preventing or surviving
              major illness. Identifying specific biomarkers conducive to
              exceptional survival might provide insights into
              counter-regulatory mechanisms against aging-related disease.
              Here, we report associations between cardiovascular
              disease-related biomarkers and survival to the highest ages using
              a unique dataset of 1,427 oldest individuals from three
              longitudinal cohort studies, including 36 supercentenarians, 572
              semi-supercentenarians (105-109 years), 288 centenarians (100-104
              years), and 531 very old people (85-99 years). During follow-up,
              1,000 participants (70.1\%) died. Overall, N-terminal pro-B-type
              natriuretic peptide (NT-proBNP), interleukin-6, cystatin C and
              cholinesterase are associated with all-cause mortality
              independent of traditional cardiovascular risk factors and plasma
              albumin. Of these, low NT-proBNP levels are statistically
              associated with a survival advantage to supercentenarian age.
              Only low albumin is associated with high mortality across age
              groups. These findings expand our knowledge on the biology of
              human longevity.",
  journal  = "Nat. Commun.",
  volume   =  11,
  number   =  1,
  pages    = "3820",
  month    =  jul,
  year     =  2020,
  language = "en"
}

@MISC{Barzilai2004-fd,
  title   = "Unique lipoprotein phenotype and genotype associated with
             exceptional longevity",
  author  = "Barzilai, N and Atzmon, G and Schechter, C",
  journal = "ACC Current Journal Review",
  volume  =  13,
  number  =  2,
  pages   = "22--23",
  year    =  2004
}

@ARTICLE{Stacy2021-dv,
  title    = "Infection trains the host for microbiota-enhanced resistance to
              pathogens",
  author   = "Stacy, Apollo and Andrade-Oliveira, Vinicius and McCulloch, John
              A and Hild, Benedikt and Oh, Ji Hoon and Perez-Chaparro, P
              Juliana and Sim, Choon K and Lim, Ai Ing and Link, Verena M and
              Enamorado, Michel and Trinchieri, Giorgio and Segre, Julia A and
              Rehermann, Barbara and Belkaid, Yasmine",
  abstract = "The microbiota shields the host against infections in a process
              known as colonization resistance. How infections themselves shape
              this fundamental process remains largely unknown. Here, we show
              that gut microbiota from previously infected hosts display
              enhanced resistance to infection. This long-term functional
              remodeling is associated with altered bile acid metabolism
              leading to the expansion of taxa that utilize the sulfonic acid
              taurine. Notably, supplying exogenous taurine alone is sufficient
              to induce this alteration in microbiota function and enhance
              resistance. Mechanistically, taurine potentiates the microbiota's
              production of sulfide, an inhibitor of cellular respiration,
              which is key to host invasion by numerous pathogens. As such,
              pharmaceutical sequestration of sulfide perturbs the microbiota's
              composition and promotes pathogen invasion. Together, this work
              reveals a process by which the host, triggered by infection, can
              deploy taurine as a nutrient to nourish and train the microbiota,
              promoting its resistance to subsequent infection.",
  journal  = "Cell",
  volume   =  184,
  number   =  3,
  pages    = "615--627.e17",
  month    =  feb,
  year     =  2021,
  keywords = "Citrobacter rodentium; Enterococcus faecalis; Klebsiella
              pneumoniae; aerobic respiration; bile acid; bismuth
              subsalicylate; colonization resistance; gut microbiome; hydrogen
              sulfide; taurine",
  language = "en"
}

@ARTICLE{Stewart2018-vm,
  title    = "Temporal development of the gut microbiome in early childhood
              from the {TEDDY} study",
  author   = "Stewart, Christopher J and Ajami, Nadim J and O'Brien, Jacqueline
              L and Hutchinson, Diane S and Smith, Daniel P and Wong, Matthew C
              and Ross, Matthew C and Lloyd, Richard E and Doddapaneni,
              Harshavardhan and Metcalf, Ginger A and Muzny, Donna and Gibbs,
              Richard A and Vatanen, Tommi and Huttenhower, Curtis and Xavier,
              Ramnik J and Rewers, Marian and Hagopian, William and Toppari,
              Jorma and Ziegler, Anette-G and She, Jin-Xiong and Akolkar, Beena
              and Lernmark, Ake and Hyoty, Heikki and Vehik, Kendra and
              Krischer, Jeffrey P and Petrosino, Joseph F",
  abstract = "The development of the microbiome from infancy to childhood is
              dependent on a range of factors, with microbial-immune crosstalk
              during this time thought to be involved in the pathobiology of
              later life diseases1-9 such as persistent islet autoimmunity and
              type 1 diabetes10-12. However, to our knowledge, no studies have
              performed extensive characterization of the microbiome in early
              life in a large, multi-centre population. Here we analyse
              longitudinal stool samples from 903 children between 3 and 46
              months of age by 16S rRNA gene sequencing (n = 12,005) and
              metagenomic sequencing (n = 10,867), as part of the The
              Environmental Determinants of Diabetes in the Young (TEDDY)
              study. We show that the developing gut microbiome undergoes three
              distinct phases of microbiome progression: a developmental phase
              (months 3-14), a transitional phase (months 15-30), and a stable
              phase (months 31-46). Receipt of breast milk, either exclusive or
              partial, was the most significant factor associated with the
              microbiome structure. Breastfeeding was associated with higher
              levels of Bifidobacterium species (B. breve and B. bifidum), and
              the cessation of breast milk resulted in faster maturation of the
              gut microbiome, as marked by the phylum Firmicutes. Birth mode
              was also significantly associated with the microbiome during the
              developmental phase, driven by higher levels of Bacteroides
              species (particularly B. fragilis) in infants delivered
              vaginally. Bacteroides was also associated with increased gut
              diversity and faster maturation, regardless of the birth mode.
              Environmental factors including geographical location and
              household exposures (such as siblings and furry pets) also
              represented important covariates. A nested case-control analysis
              revealed subtle associations between microbial taxonomy and the
              development of islet autoimmunity or type 1 diabetes. These data
              determine the structural and functional assembly of the
              microbiome in early life and provide a foundation for targeted
              mechanistic investigation into the consequences of
              microbial-immune crosstalk for long-term health.",
  journal  = "Nature",
  volume   =  562,
  number   =  7728,
  pages    = "583--588",
  month    =  oct,
  year     =  2018,
  language = "en"
}

@ARTICLE{Edwards2015-vc,
  title     = "Computational approaches to predict bacteriophage--host
               relationships",
  author    = "Edwards, Robert A and McNair, Katelyn and Faust, Karoline and
               Raes, Jeroen and Dutilh, Bas E",
  abstract  = "New viruses infecting bacteria are increasingly being discovered
               in many environments through sequence-based explorations. To
               understand their role in microbial",
  journal   = "FEMS Microbiol. Rev.",
  publisher = "Oxford Academic",
  volume    =  40,
  number    =  2,
  pages     = "258--272",
  month     =  dec,
  year      =  2015,
  keywords  = "bacteriophages; host (organism); viruses; metagenomics",
  language  = "en"
}

@UNPUBLISHED{Sutcliffe2022-ph,
  title    = "Bacteriophages Playing Nice: Lysogenic bacteriophage replication
              stable in the human gut microbiota",
  author   = "Sutcliffe, Steven G and Reyes, Alejandro and Maurice, Corinne F",
  abstract = "The human gut is a dense microbial community, of which bacteria
              and bacteriophages are the majority. Bacteriophages, viruses of
              bacteria, exist stably, without major fluctuations in the gut of
              healthy individuals. This stability appears to be due to an
              absence of `kill-the-winner' dynamics, and the existence of
              `piggy-back-the-winner' dynamics, where lysogenic replication
              rather than lytic replication occurs. Revisiting the deep-viral
              sequencing data of a healthy individual studied over 2.4 years,
              we were able to improve our understanding of how these dynamics
              occur in healthy individuals. We assembled prophages from
              bacterial metagenomic data and show that these prophages were
              continually switching from lysogenic to lytic replication.
              Prophages were the source of a stable extracellular phage
              population continually present in low abundance, in comparison to
              the lytic-phage population, where taxonomic diversity diverged
              over 2.4 years. The switch to lytic replication, or prophage
              induction, appears to occur mostly through spontaneous prophage
              induction. The observed phage dynamics of regular spontaneous
              induction are ecologically important as they allow prophages to
              maintain their ability to replicate, avoiding degradation and
              their loss from the gut microbiota. Significance Statement It has
              been eight years since Minot and colleagues published their
              landmark longitudinal study of phages in the gut. In the years
              following, the bioinformatic field improved in great strides,
              including the methods of bacterial-genome assembly,
              phage-identification, and prophage detection. We leveraged the
              unprecedented deep sequencing of phages in this dataset by adding
              bacterial assembly and prophage detection analyzes. We show
              clearly for the first time that `piggy-back-the-winner' dynamics
              are maintained in the gut through spontaneous prophage induction,
              and not widespread triggered prophage induction. These dynamics
              play an important ecological role by creating a stable
              subpopulation of phages, which could help explain how phages are
              maintained over the 2.4 years timeframe that this individual was
              studied. \#\#\# Competing Interest Statement The authors have
              declared no competing interest.",
  journal  = "bioRxiv",
  pages    = "2022.03.23.485530",
  month    =  mar,
  year     =  2022,
  language = "en"
}

@ARTICLE{Breitbart2018-sj,
  title    = "Phage puppet masters of the marine microbial realm",
  author   = "Breitbart, Mya and Bonnain, Chelsea and Malki, Kema and Sawaya,
              Natalie A",
  abstract = "Viruses numerically dominate our oceans; however, we have only
              just begun to document the diversity, host range and infection
              dynamics of marine viruses, as well as the subsequent effects of
              infection on both host cell metabolism and oceanic
              biogeochemistry. Bacteriophages (that is, phages: viruses that
              infect bacteria) are highly abundant and are known to play
              critical roles in bacterial mortality, biogeochemical cycling and
              horizontal gene transfer. This Review Article summarizes current
              knowledge of marine viral ecology and highlights the importance
              of phage particles to the dissolved organic matter pool, as well
              as the complex interactions between phages and their bacterial
              hosts. We emphasize the newly recognized roles of phages as
              puppet masters of their bacterial hosts, where phages are capable
              of altering the metabolism of infected bacteria through the
              expression of auxiliary metabolic genes and the redirection of
              host gene expression patterns. Finally, we propose the 'royal
              family model' as a hypothesis to describe successional patterns
              of bacteria and phages over time in marine systems, where despite
              high richness and significant seasonal differences, only a small
              number of phages appear to continually dominate a given marine
              ecosystem. Although further testing is required, this model
              provides a framework for assessing the specificity and ecological
              consequences of phage-host dynamics.",
  journal  = "Nat Microbiol",
  volume   =  3,
  number   =  7,
  pages    = "754--766",
  month    =  jul,
  year     =  2018,
  language = "en"
}

@MISC{Schroeder2019-ec,
  title   = "Fight them or feed them: how the intestinal mucus layer manages
             the gut microbiota",
  author  = "Schroeder, Bjoern O",
  journal = "Gastroenterology Report",
  volume  =  7,
  number  =  1,
  pages   = "3--12",
  year    =  2019
}

@ARTICLE{Roux2016-yu,
  title    = "Ecogenomics and potential biogeochemical impacts of globally
              abundant ocean viruses",
  author   = "Roux, Simon and Brum, Jennifer R and Dutilh, Bas E and Sunagawa,
              Shinichi and Duhaime, Melissa B and Loy, Alexander and Poulos,
              Bonnie T and Solonenko, Natalie and Lara, Elena and Poulain,
              Julie and Pesant, St{\'e}phane and Kandels-Lewis, Stefanie and
              Dimier, C{\'e}line and Picheral, Marc and Searson, Sarah and
              Cruaud, Corinne and Alberti, Adriana and Duarte, Carlos M and
              Gasol, Josep M and Vaqu{\'e}, Dolors and {Tara Oceans
              Coordinators} and Bork, Peer and Acinas, Silvia G and Wincker,
              Patrick and Sullivan, Matthew B",
  abstract = "Ocean microbes drive biogeochemical cycling on a global scale.
              However, this cycling is constrained by viruses that affect
              community composition, metabolic activity, and evolutionary
              trajectories. Owing to challenges with the sampling and
              cultivation of viruses, genome-level viral diversity remains
              poorly described and grossly understudied, with less than 1\% of
              observed surface-ocean viruses known. Here we assemble complete
              genomes and large genomic fragments from both surface- and
              deep-ocean viruses sampled during the Tara Oceans and Malaspina
              research expeditions, and analyse the resulting 'global ocean
              virome' dataset to present a global map of abundant,
              double-stranded DNA viruses complete with genomic and ecological
              contexts. A total of 15,222 epipelagic and mesopelagic viral
              populations were identified, comprising 867 viral clusters
              (defined as approximately genus-level groups). This roughly
              triples the number of known ocean viral populations and doubles
              the number of candidate bacterial and archaeal virus genera,
              providing a near-complete sampling of epipelagic communities at
              both the population and viral-cluster level. We found that 38 of
              the 867 viral clusters were locally or globally abundant,
              together accounting for nearly half of the viral populations in
              any global ocean virome sample. While two-thirds of these
              clusters represent newly described viruses lacking any cultivated
              representative, most could be computationally linked to dominant,
              ecologically relevant microbial hosts. Moreover, we identified
              243 viral-encoded auxiliary metabolic genes, of which only 95
              were previously known. Deeper analyses of four of these auxiliary
              metabolic genes (dsrC, soxYZ, P-II (also known as glnB) and amoC)
              revealed that abundant viruses may directly manipulate sulfur and
              nitrogen cycling throughout the epipelagic ocean. This viral
              catalog and functional analyses provide a necessary foundation
              for the meaningful integration of viruses into ecosystem models
              where they act as key players in nutrient cycling and trophic
              networks.",
  journal  = "Nature",
  volume   =  537,
  number   =  7622,
  pages    = "689--693",
  month    =  sep,
  year     =  2016,
  language = "en"
}

@ARTICLE{Callanan2020-xy,
  title     = "Expansion of known {ssRNA} phage genomes: From tens to over a
               thousand",
  author    = "Callanan, J and Stockdale, S R and Shkoporov, A and Draper, L A
               and Ross, R P and Hill, C",
  abstract  = "The first sequenced genome was that of the 3569-nucleotide
               single-stranded RNA (ssRNA) bacteriophage MS2. Despite the
               recent accumulation of vast amounts of DNA and RNA sequence
               data, only 12 representative ssRNA phage genome sequences are
               available from the NCBI Genome database (June 2019). The
               difficulty in detecting RNA phages in metagenomic datasets
               raises questions as to their abundance, taxonomic structure, and
               ecological importance. In this study, we iteratively applied
               profile hidden Markov models to detect conserved ssRNA phage
               proteins in 82 publicly available metatranscriptomic datasets
               generated from activated sludge and aquatic environments. We
               identified 15,611 nonredundant ssRNA phage sequences, including
               1015 near-complete genomes. This expansion in the number of
               known sequences enabled us to complete a phylogenetic assessment
               of both sequences identified in this study and known ssRNA phage
               genomes. Our expansion of these viruses from two environments
               suggests that they have been overlooked within microbiome
               studies.",
  journal   = "Sci Adv",
  publisher = "advances.sciencemag.org",
  volume    =  6,
  number    =  6,
  pages     = "eaay5981",
  month     =  feb,
  year      =  2020,
  language  = "en"
}

@ARTICLE{Wang2021-ne,
  title    = "{scGNN} is a novel graph neural network framework for single-cell
              {RNA-Seq} analyses",
  author   = "Wang, Juexin and Ma, Anjun and Chang, Yuzhou and Gong, Jianting
              and Jiang, Yuexu and Qi, Ren and Wang, Cankun and Fu, Hongjun and
              Ma, Qin and Xu, Dong",
  abstract = "Single-cell RNA-sequencing (scRNA-Seq) is widely used to reveal
              the heterogeneity and dynamics of tissues, organisms, and complex
              diseases, but its analyses still suffer from multiple grand
              challenges, including the sequencing sparsity and complex
              differential patterns in gene expression. We introduce the scGNN
              (single-cell graph neural network) to provide a hypothesis-free
              deep learning framework for scRNA-Seq analyses. This framework
              formulates and aggregates cell-cell relationships with graph
              neural networks and models heterogeneous gene expression patterns
              using a left-truncated mixture Gaussian model. scGNN integrates
              three iterative multi-modal autoencoders and outperforms existing
              tools for gene imputation and cell clustering on four benchmark
              scRNA-Seq datasets. In an Alzheimer's disease study with 13,214
              single nuclei from postmortem brain tissues, scGNN successfully
              illustrated disease-related neural development and the
              differential mechanism. scGNN provides an effective
              representation of gene expression and cell-cell relationships. It
              is also a powerful framework that can be applied to general
              scRNA-Seq analyses.",
  journal  = "Nat. Commun.",
  volume   =  12,
  number   =  1,
  pages    = "1882",
  month    =  mar,
  year     =  2021,
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Fluckiger2020-ay,
  title     = "Cross-reactivity between tumor {MHC} class I--restricted
               antigens and an enterococcal bacteriophage",
  author    = "Fluckiger, A and Daillere, R and Sassi, M and Sixt, B S and Liu,
               P and {others}",
  abstract  = "Intestinal microbiota have been proposed to induce
               commensal-specific memory T cells that cross-react with
               tumor-associated antigens. We identified major
               histocompatibility complex (MHC) class I--binding epitopes in
               the tail length tape measure protein (TMP) of a prophage found
               in the genome of the bacteriophage Enterococcus hirae. Mice
               bearing E. hirae harboring this prophage mounted a TMP-specific
               H-2K b--restricted CD8+ T lymphocyte response upon immunotherapy
               with cyclophosphamide or anti--PD-1 antibodies …",
  publisher = "science.sciencemag.org",
  year      =  2020
}

@ARTICLE{Hille2018-zk,
  title    = "The Biology of {CRISPR-Cas}: Backward and Forward",
  author   = "Hille, Frank and Richter, Hagen and Wong, Shi Pey and Bratovi{\v
              c}, Majda and Ressel, Sarah and Charpentier, Emmanuelle",
  abstract = "In bacteria and archaea, clustered regularly interspaced short
              palindromic repeats (CRISPR) and CRISPR-associated (Cas) proteins
              constitute an adaptive immune system against phages and other
              foreign genetic elements. Here, we review the biology of the
              diverse CRISPR-Cas systems and the major progress achieved in
              recent years in understanding the underlying mechanisms of the
              three stages of CRISPR-Cas immunity: adaptation, crRNA
              biogenesis, and interference. The ecology and regulation of
              CRISPR-Cas in the context of phage infection, the roles of these
              systems beyond immunity, and the open questions that propel the
              field forward are also discussed.",
  journal  = "Cell",
  volume   =  172,
  number   =  6,
  pages    = "1239--1259",
  month    =  mar,
  year     =  2018,
  language = "en"
}

@ARTICLE{Nr1985-yh,
  title    = "Analyzing natural microbial populations by {rRNA} sequences",
  author   = "Nr, Pace",
  journal  = "ASM News",
  volume   =  51,
  pages    = "4--12",
  year     =  1985
}

@ARTICLE{Chevallereau2022-lw,
  title    = "Interactions between bacterial and phage communities in natural
              environments",
  author   = "Chevallereau, Anne and Pons, Beno{\^\i}t J and van Houte, Stineke
              and Westra, Edze R",
  abstract = "We commonly acknowledge that bacterial viruses (phages) shape the
              composition and evolution of bacterial communities in nature and
              therefore have important roles in ecosystem functioning. This
              view stems from studies in the 1990s to the first decade of the
              twenty-first century that revealed high viral abundance, high
              viral diversity and virus-induced microbial death in aquatic
              ecosystems as well as an association between collapses in
              bacterial density and peaks in phage abundance. The recent surge
              in metagenomic analyses has provided deeper insight into the
              abundance, genomic diversity and spatio-temporal dynamics of
              phages in a wide variety of ecosystems, ranging from deep oceans
              to soil and the mammalian digestive tract. However, the causes
              and consequences of variations in phage community compositions
              remain poorly understood. In this Review, we explore current
              knowledge of the composition and evolution of phage communities,
              as well as their roles in controlling the population and
              evolutionary dynamics of bacterial communities. We discuss the
              need for greater ecological realism in laboratory studies to
              capture the complexity of microbial communities that thrive in
              natural environments.",
  journal  = "Nat. Rev. Microbiol.",
  volume   =  20,
  number   =  1,
  pages    = "49--62",
  month    =  jan,
  year     =  2022,
  language = "en"
}

@ARTICLE{Erez2017-pv,
  title     = "Communication between viruses guides lysis--lysogeny decisions",
  author    = "Erez, Zohar and Steinberger-Levy, Ida and Shamir, Maya and
               Doron, Shany and Stokar-Avihail, Avigail and Peleg, Yoav and
               Melamed, Sarah and Leavitt, Azita and Savidor, Alon and Albeck,
               Shira and Amitai, Gil and Sorek, Rotem",
  abstract  = "Temperate viruses can become dormant in their host cells, a
               process called lysogeny. In every infection, such viruses decide
               between the lytic and the lysogenic cycles, that is, whether to
               replicate and lyse their host or to lysogenize and keep the host
               viable. Here we show that viruses (phages) of the SPbeta group
               use a small-molecule communication system to coordinate
               lysis--lysogeny decisions. During infection of its Bacillus host
               cell, the phage produces a six amino-acids-long communication
               peptide that is released into the medium. In subsequent
               infections, progeny phages measure the concentration of this
               peptide and lysogenize if the concentration is sufficiently
               high. We found that different phages encode different versions
               of the communication peptide, demonstrating a phage-specific
               peptide communication code for lysogeny decisions. We term this
               communication system the `arbitrium' system, and further show
               that it is encoded by three phage genes: aimP, which produces
               the peptide; aimR, the intracellular peptide receptor; and aimX,
               a negative regulator of lysogeny. The arbitrium system enables a
               descendant phage to `communicate' with its predecessors, that
               is, to estimate the amount of recent previous infections and
               hence decide whether to employ the lytic or lysogenic cycle.
               Some phages---viruses that infect bacteria---encode peptides
               that are secreted from infected cells and that, beyond a certain
               threshold, stimulate other viruses to switch from the lytic
               (killing the host cell) to lysogenic (dormant) phase. Bacteria
               secrete signalling molecules that allow them to perceive their
               population density and change their behaviour accordingly. In an
               exciting turn of events, while searching for bacterial
               communication systems, Rotem Sorek and colleagues found that
               some phages---viruses that infect bacteria---encode peptides
               that are secreted from infected cells and sensed by the viral
               population. Beyond a certain threshold, the viruses switch from
               employing the lytic cycle, in which they kill the host cell, to
               the lysogenic cycle, in which they avoid killing off their
               hosts. This is the first viral communication system to have been
               described.",
  journal   = "Nature",
  publisher = "Nature Publishing Group",
  volume    =  541,
  number    =  7638,
  pages     = "488--493",
  month     =  jan,
  year      =  2017,
  language  = "en"
}

@ARTICLE{Sieber2018-il,
  title    = "Recovery of genomes from metagenomes via a dereplication,
              aggregation and scoring strategy",
  author   = "Sieber, Christian M K and Probst, Alexander J and Sharrar,
              Allison and Thomas, Brian C and Hess, Matthias and Tringe,
              Susannah G and Banfield, Jillian F",
  abstract = "Microbial communities are critical to ecosystem function. A key
              objective of metagenomic studies is to analyse organism-specific
              metabolic pathways and reconstruct community interaction
              networks. This requires accurate assignment of assembled genome
              fragments to genomes. Existing binning methods often fail to
              reconstruct a reasonable number of genomes and report many bins
              of low quality and completeness. Furthermore, the performance of
              existing algorithms varies between samples and biotopes. Here, we
              present a dereplication, aggregation and scoring strategy, DAS
              Tool, that combines the strengths of a flexible set of
              established binning algorithms. DAS Tool applied to a constructed
              community generated more accurate bins than any automated method.
              Indeed, when applied to environmental and host-associated samples
              of different complexity, DAS Tool recovered substantially more
              near-complete genomes, including previously unreported lineages,
              than any single binning method alone. The ability to reconstruct
              many near-complete genomes from metagenomics data will greatly
              advance genome-centric analyses of ecosystems.",
  journal  = "Nat Microbiol",
  volume   =  3,
  number   =  7,
  pages    = "836--843",
  month    =  jul,
  year     =  2018,
  language = "en"
}

@ARTICLE{Clooney2019-nn,
  title    = "{Whole-Virome} Analysis Sheds Light on Viral Dark Matter in
              Inflammatory Bowel Disease",
  author   = "Clooney, Adam G and Sutton, Thomas D S and Shkoporov, Andrey N
              and Holohan, Ross K and Daly, Karen M and O'Regan, Orla and Ryan,
              Feargal J and Draper, Lorraine A and Plevy, Scott E and Ross, R
              Paul and Hill, Colin",
  abstract = "The human gut virome is thought to significantly impact the
              microbiome and human health. However, most virome analyses have
              been performed on a limited fraction of known viruses. Using
              whole-virome analysis on a published keystone inflammatory bowel
              disease (IBD) cohort and an in-house ulcerative colitis dataset,
              we shed light on the composition of the human gut virome in IBD
              beyond this identifiable minority. We observe IBD-specific
              changes to the virome and increased numbers of temperate phage
              sequences in individuals with Crohn's disease. Unlike prior
              database-dependent methods, no changes in viral richness were
              observed. Among IBD subjects, the changes in virome composition
              reflected alterations in bacterial composition. Furthermore,
              incorporating both bacteriome and virome composition offered
              greater classification power between health and disease. This
              approach to analyzing whole virome across cohorts highlights
              significant IBD signals, which may be crucial for developing
              future biomarkers and therapeutics.",
  journal  = "Cell Host Microbe",
  volume   =  26,
  number   =  6,
  pages    = "764--778.e5",
  month    =  dec,
  year     =  2019,
  keywords = "16S; CD; Crohn's disease; IBD; UC; inflammatory bowel disease;
              phage; phageome; ulcerative colitis; virome; virus;phamb;phamb",
  language = "en"
}

@ARTICLE{Anantharaman2014-ui,
  title    = "Sulfur oxidation genes in diverse deep-sea viruses",
  author   = "Anantharaman, Karthik and Duhaime, Melissa B and Breier, John A
              and Wendt, Kathleen A and Toner, Brandy M and Dick, Gregory J",
  abstract = "Viruses are the most abundant biological entities in the oceans
              and a pervasive cause of mortality of microorganisms that drive
              biogeochemical cycles. Although the ecological and evolutionary
              effects of viruses on marine phototrophs are well recognized,
              little is known about their impact on ubiquitous marine
              lithotrophs. Here, we report 18 genome sequences of
              double-stranded DNA viruses that putatively infect widespread
              sulfur-oxidizing bacteria. Fifteen of these viral genomes contain
              auxiliary metabolic genes for the $\alpha$ and $\gamma$ subunits
              of reverse dissimilatory sulfite reductase (rdsr). This enzyme
              oxidizes elemental sulfur, which is abundant in the hydrothermal
              plumes studied here. Our findings implicate viruses as a key
              agent in the sulfur cycle and as a reservoir of genetic diversity
              for bacterial enzymes that underpin chemosynthesis in the deep
              oceans.",
  journal  = "Science",
  volume   =  344,
  number   =  6185,
  pages    = "757--760",
  month    =  may,
  year     =  2014,
  language = "en"
}

@ARTICLE{Adiliaghdam2022-po,
  title    = "Human enteric viruses autonomously shape inflammatory bowel
              disease phenotype through divergent innate immunomodulation",
  author   = "Adiliaghdam, Fatemeh and Amatullah, Hajera and Digumarthi,
              Sreehaas and Saunders, Tahnee L and Rahman, Raza-Ur and Wong, Lai
              Ping and Sadreyev, Ruslan and Droit, Lindsay and Paquette, Jean
              and Goyette, Philippe and Rioux, John D and Hodin, Richard and
              Mihindukulasuriya, Kathie A and Handley, Scott A and Jeffrey,
              Kate L",
  abstract = "Altered enteric microorganisms in concert with host genetics
              shape inflammatory bowel disease (IBD) phenotypes. However,
              insight is limited to bacteria and fungi. We found that
              eukaryotic viruses and bacteriophages (collectively, the virome),
              enriched from non-IBD, noninflamed human colon resections,
              actively elicited atypical anti-inflammatory innate immune
              programs. Conversely, ulcerative colitis or Crohn's disease colon
              resection viromes provoked inflammation, which was successfully
              dampened by non-IBD viromes. The IBD colon tissue virome was
              perturbed, including an increase in the enterovirus B species of
              eukaryotic picornaviruses, not previously detected in fecal
              virome studies. Mice humanized with non-IBD colon tissue viromes
              were protected from intestinal inflammation, whereas IBD virome
              mice exhibited exacerbated inflammation in a nucleic acid
              sensing--dependent fashion. Furthermore, there were detrimental
              consequences for IBD patient--derived intestinal epithelial cells
              bearing loss-of-function mutations within virus sensor MDA5 when
              exposed to viromes. Our results demonstrate that innate
              recognition of IBD or non-IBD human viromes autonomously
              influences intestinal homeostasis and disease phenotypes. Thus,
              perturbations in the intestinal virome, or an altered ability to
              sense the virome due to genetic variation, contribute to the
              induction of IBD. Harnessing the virome may offer therapeutic and
              biomarker potential. Human enteric viromes divergently shape host
              immunity and disease. The diverse set of DNA and RNA viruses that
              comprise the enteric virome are an often overlooked component of
              the complete gut microbiota ecosystem. Adiliaghdam et al.
              compared the composition and immunomodulatory function of the
              enteric virome from inflammatory bowel disease (IBD) patients and
              controls. Virus-like particles enriched from the site of
              inflammation---human colon resection specimens or ileostomy
              fluid---were tested for immunomodulatory effects on human
              macrophages or intestinal epithelial cells and introduced into
              recipient mice. IBD-associated enteric viromes promoted
              inflammation, spontaneously and after DSS-induced colitis, while
              viruses from non-IBD tissue were protective and also suppressed
              inflammatory properties of IBD enteric viromes. Viruses unique to
              IBD colon tissue included enteroviruses missed in previous fecal
              virome analyses. These findings illustrate how perturbations in
              enteric viromes are detected by innate immune system sensors with
              consequences for the maintenance of normal intestinal
              homeostasis.",
  journal  = "Science Immunology",
  volume   =  7,
  number   =  70,
  pages    = "eabn6660",
  year     =  2022
}

@ARTICLE{Nayfach2021-tq,
  title    = "Metagenomic compendium of 189,680 {DNA} viruses from the human
              gut microbiome",
  author   = "Nayfach, Stephen and P{\'a}ez-Espino, David and Call, Lee and
              Low, Soo Jen and Sberro, Hila and Ivanova, Natalia N and Proal,
              Amy D and Fischbach, Michael A and Bhatt, Ami S and Hugenholtz,
              Philip and Kyrpides, Nikos C",
  abstract = "Bacteriophages have important roles in the ecology of the human
              gut microbiome but are under-represented in reference databases.
              To address this problem, we assembled the Metagenomic Gut Virus
              catalogue that comprises 189,680 viral genomes from 11,810
              publicly available human stool metagenomes. Over 75\% of genomes
              represent double-stranded DNA phages that infect members of the
              Bacteroidia and Clostridia classes. Based on sequence clustering
              we identified 54,118 candidate viral species, 92\% of which were
              not found in existing databases. The Metagenomic Gut Virus
              catalogue improves detection of viruses in stool metagenomes and
              accounts for nearly 40\% of CRISPR spacers found in human gut
              Bacteria and Archaea. We also produced a catalogue of 459,375
              viral protein clusters to explore the functional potential of the
              gut virome. This revealed tens of thousands of
              diversity-generating retroelements, which use error-prone reverse
              transcription to mutate target genes and may be involved in the
              molecular arms race between phages and their bacterial hosts.",
  journal  = "Nat Microbiol",
  month    =  jun,
  year     =  2021,
  language = "en"
}

@ARTICLE{Nayfach2021-yf,
  title    = "{CheckV} assesses the quality and completeness of
              metagenome-assembled viral genomes",
  author   = "Nayfach, Stephen and Camargo, Antonio Pedro and Schulz, Frederik
              and Eloe-Fadrosh, Emiley and Roux, Simon and Kyrpides, Nikos C",
  abstract = "Millions of new viral sequences have been identified from
              metagenomes, but the quality and completeness of these sequences
              vary considerably. Here we present CheckV, an automated pipeline
              for identifying closed viral genomes, estimating the completeness
              of genome fragments and removing flanking host regions from
              integrated proviruses. CheckV estimates completeness by comparing
              sequences with a large database of complete viral genomes,
              including 76,262 identified from a systematic search of publicly
              available metagenomes, metatranscriptomes and metaviromes. After
              validation on mock datasets and comparison to existing methods,
              we applied CheckV to large and diverse collections of
              metagenome-assembled viral sequences, including IMG/VR and the
              Global Ocean Virome. This revealed 44,652 high-quality viral
              genomes (that is, >90\% complete), although the vast majority of
              sequences were small fragments, which highlights the challenge of
              assembling viral genomes from short-read metagenomes.
              Additionally, we found that removal of host contamination
              substantially improved the accurate identification of auxiliary
              metabolic genes and interpretation of viral-encoded functions.",
  journal  = "Nat. Biotechnol.",
  volume   =  39,
  number   =  5,
  pages    = "578--585",
  month    =  may,
  year     =  2021,
  language = "en"
}

@ARTICLE{Bichet2021-vj,
  title    = "Bacteriophage uptake by mammalian cell layers represents a
              potential sink that may impact phage therapy",
  author   = "Bichet, Marion C and Chin, Wai Hoe and Richards, William and Lin,
              Yu-Wei and Avellaneda-Franco, Laura and Hernandez, Catherine A
              and Oddo, Arianna and Chernyavskiy, Oleksandr and Hilsenstein,
              Volker and Neild, Adrian and Li, Jian and Voelcker, Nicolas Hans
              and Patwa, Ruzeen and Barr, Jeremy J",
  abstract = "It is increasingly apparent that bacteriophages, viruses that
              infect bacteria and more commonly referred to as simply phages,
              have tropisms outside their bacterial hosts. Using live tissue
              culture cell imaging, we demonstrate that cell type, phage size,
              and morphology play a major role in phage internalization. Uptake
              was validated under physiological conditions using a microfluidic
              device. Phages adhered to mammalian tissues, with adherent phages
              being subsequently internalized by macropinocytosis, with
              functional phages accumulating intracellularly. We incorporated
              these results into a pharmacokinetic model demonstrating the
              potential impact of phage accumulation by cell layers, which
              represents a potential sink for circulating phages in the body.
              During phage therapy, high doses of phages are directly
              administered to a patient in order to treat a bacterial
              infection, thereby facilitating broad interactions between phages
              and mammalian cells. Understanding these interactions will have
              important implications on innate immune responses, phage
              pharmacokinetics, and the efficacy of phage therapy.",
  journal  = "iScience",
  volume   =  24,
  number   =  4,
  pages    = "102287",
  month    =  apr,
  year     =  2021,
  keywords = "Immunology; Microbiology; Virology",
  language = "en"
}

@ARTICLE{Sato2021-zh,
  title    = "Novel bile acid biosynthetic pathways are enriched in the
              microbiome of centenarians",
  author   = "Sato, Yuko and Atarashi, Koji and Plichta, Damian R and Arai,
              Yasumichi and Sasajima, Satoshi and Kearney, Sean M and Suda,
              Wataru and Takeshita, Kozue and Sasaki, Takahiro and Okamoto,
              Shoki and Skelly, Ashwin N and Okamura, Yuki and Vlamakis, Hera
              and Li, Youxian and Tanoue, Takeshi and Takei, Hajime and
              Nittono, Hiroshi and Narushima, Seiko and Irie, Junichiro and
              Itoh, Hiroshi and Moriya, Kyoji and Sugiura, Yuki and Suematsu,
              Makoto and Moritoki, Nobuko and Shibata, Shinsuke and Littman,
              Dan R and Fischbach, Michael A and Uwamino, Yoshifumi and Inoue,
              Takashi and Honda, Akira and Hattori, Masahira and Murai,
              Tsuyoshi and Xavier, Ramnik J and Hirose, Nobuyoshi and Honda,
              Kenya",
  abstract = "Centenarians have a decreased susceptibility to ageing-associated
              illnesses, chronic inflammation and infectious diseases1-3. Here
              we show that centenarians have a distinct gut microbiome that is
              enriched in microorganisms that are capable of generating unique
              secondary bile acids, including various isoforms of lithocholic
              acid (LCA): iso-, 3-oxo-, allo-, 3-oxoallo- and
              isoallolithocholic acid. Among these bile acids, the biosynthetic
              pathway for isoalloLCA had not been described previously. By
              screening 68 bacterial isolates from the faecal microbiota of a
              centenarian, we identified Odoribacteraceae strains as effective
              producers of isoalloLCA both in vitro and in vivo. Furthermore,
              we found that the enzymes 5$\alpha$-reductase (5AR) and
              3$\beta$-hydroxysteroid dehydrogenase (3$\beta$-HSDH) were
              responsible for the production of isoalloLCA. IsoalloLCA exerted
              potent antimicrobial effects against Gram-positive (but not
              Gram-negative) multidrug-resistant pathogens, including
              Clostridioides difficile and Enterococcus faecium. These findings
              suggest that the metabolism of specific bile acids may be
              involved in reducing the risk of infection with pathobionts,
              thereby potentially contributing to the maintenance of intestinal
              homeostasis.",
  journal  = "Nature",
  volume   =  599,
  number   =  7885,
  pages    = "458--464",
  month    =  nov,
  year     =  2021,
  language = "en"
}

@ARTICLE{Rousset2022-sn,
  title    = "Phages and their satellites encode hotspots of antiviral systems",
  author   = "Rousset, Fran{\c c}ois and Depardieu, Florence and Miele, Solange
              and Dowding, Julien and Laval, Anne-Laure and Lieberman, Erica
              and Garry, Daniel and Rocha, Eduardo P C and Bernheim, Aude and
              Bikard, David",
  abstract = "Bacteria carry diverse genetic systems to defend against viral
              infection, some of which are found within prophages where they
              inhibit competing viruses. Phage satellites pose additional
              pressures on phages by hijacking key viral elements to their own
              benefit. Here, we show that E. coli P2-like phages and their
              parasitic P4-like satellites carry hotspots of genetic variation
              containing reservoirs of anti-phage systems. We validate the
              activity of diverse systems and describe PARIS, an abortive
              infection system triggered by a phage-encoded anti-restriction
              protein. Antiviral hotspots participate in inter-viral
              competition and shape dynamics between the bacterial host,
              P2-like phages, and P4-like satellites. Notably, the anti-phage
              activity of satellites can benefit the helper phage during
              competition with virulent phages, turning a parasitic
              relationship into a mutualistic one. Anti-phage hotspots are
              present across distant species and constitute a substantial
              source of systems that participate in the competition between
              mobile genetic elements.",
  journal  = "Cell Host Microbe",
  volume   =  30,
  number   =  5,
  pages    = "740--753.e5",
  month    =  may,
  year     =  2022,
  keywords = "abortive infection; bacterial immunity; genetic diversity;
              inter-viral competition; mobile genetic elements; phage defense;
              phage satellite",
  language = "en"
}

@ARTICLE{Venter2004-ce,
  title    = "Environmental genome shotgun sequencing of the Sargasso Sea",
  author   = "Venter, J Craig and Remington, Karin and Heidelberg, John F and
              Halpern, Aaron L and Rusch, Doug and Eisen, Jonathan A and Wu,
              Dongying and Paulsen, Ian and Nelson, Karen E and Nelson, William
              and Fouts, Derrick E and Levy, Samuel and Knap, Anthony H and
              Lomas, Michael W and Nealson, Ken and White, Owen and Peterson,
              Jeremy and Hoffman, Jeff and Parsons, Rachel and Baden-Tillson,
              Holly and Pfannkoch, Cynthia and Rogers, Yu-Hui and Smith,
              Hamilton O",
  abstract = "We have applied ``whole-genome shotgun sequencing'' to microbial
              populations collected en masse on tangential flow and impact
              filters from seawater samples collected from the Sargasso Sea
              near Bermuda. A total of 1.045 billion base pairs of nonredundant
              sequence was generated, annotated, and analyzed to elucidate the
              gene content, diversity, and relative abundance of the organisms
              within these environmental samples. These data are estimated to
              derive from at least 1800 genomic species based on sequence
              relatedness, including 148 previously unknown bacterial
              phylotypes. We have identified over 1.2 million previously
              unknown genes represented in these samples, including more than
              782 new rhodopsin-like photoreceptors. Variation in species
              present and stoichiometry suggests substantial oceanic microbial
              diversity.",
  journal  = "Science",
  volume   =  304,
  number   =  5667,
  pages    = "66--74",
  month    =  apr,
  year     =  2004,
  language = "en"
}

@ARTICLE{Obringer1988-yd,
  title    = "The functions of the phage {T4} immunity and spackle genes in
              genetic exclusion",
  author   = "Obringer, J W",
  journal  = "Genet. Res.",
  volume   =  52,
  number   =  2,
  pages    = "81--90",
  month    =  oct,
  year     =  1988,
  language = "en"
}

@ARTICLE{Shkoporov2019-mk,
  title    = "The Human Gut Virome Is Highly Diverse, Stable, and Individual
              Specific",
  author   = "Shkoporov, Andrey N and Clooney, Adam G and Sutton, Thomas D S
              and Ryan, Feargal J and Daly, Karen M and Nolan, James A and
              McDonnell, Siobhan A and Khokhlova, Ekaterina V and Draper,
              Lorraine A and Forde, Amanda and Guerin, Emma and Velayudhan,
              Vimalkumar and Ross, R Paul and Hill, Colin",
  abstract = "The human gut contains a vast array of viruses, mostly
              bacteriophages. The majority remain uncharacterized, and their
              roles in shaping the gut microbiome and in impacting on human
              health remain poorly understood. We performed longitudinal
              metagenomic analysis of fecal viruses in healthy adults that
              reveal high temporal stability, individual specificity, and
              correlation with the bacterial microbiome. Using a
              database-independent approach that uses most of the sequencing
              data, we uncovered the existence of a stable, numerically
              predominant individual-specific persistent personal virome.
              Clustering of viral genomes and de novo taxonomic annotation
              identified several groups of crAss-like and Microviridae
              bacteriophages as the most stable colonizers of the human gut.
              CRISPR-based host prediction highlighted connections between
              these stable viral communities and highly predominant gut
              bacterial taxa such as Bacteroides, Prevotella, and
              Faecalibacterium. This study provides insights into the structure
              of the human gut virome and serves as an important baseline for
              hypothesis-driven research.",
  journal  = "Cell Host Microbe",
  volume   =  26,
  number   =  4,
  pages    = "527--541.e5",
  month    =  oct,
  year     =  2019,
  keywords = "CRISPR; Microviridae; bacteriophages; crAss-like phages;
              crAssphage; human microbiome; longitudinal study; persistent
              personal virome; phageome;
              virome;phamb;phamb;1st\_regular\_assessment",
  language = "en"
}

@ARTICLE{Kieft2021-gl,
  title    = "Virus-associated organosulfur metabolism in human and
              environmental systems",
  author   = "Kieft, Kristopher and Breister, Adam M and Huss, Phil and Linz,
              Alexandra M and Zanetakos, Elizabeth and Zhou, Zhichao and
              Rahlff, Janina and Esser, Sarah P and Probst, Alexander J and
              Raman, Srivatsan and Roux, Simon and Anantharaman, Karthik",
  abstract = "Viruses influence the fate of nutrients and human health by
              killing microorganisms and altering metabolic processes.
              Organosulfur metabolism and biologically derived hydrogen sulfide
              play dynamic roles in manifestation of diseases, infrastructure
              degradation, and essential biological processes. Although
              microbial organosulfur metabolism is well studied, the role of
              viruses in organosulfur metabolism is unknown. Here, we report
              the discovery of 39 gene families involved in organosulfur
              metabolism encoded by 3,749 viruses from diverse ecosystems,
              including human microbiomes. The viruses infect organisms from
              all three domains of life. Six gene families encode for enzymes
              that degrade organosulfur compounds into sulfide, whereas others
              manipulate organosulfur compounds and may influence sulfide
              production. We show that viral metabolic genes encode key
              enzymatic domains, are translated into protein, and are
              maintained after recombination, and sulfide provides a fitness
              advantage to viruses. Our results reveal viruses as drivers of
              organosulfur metabolism with important implications for human and
              environmental health.",
  journal  = "Cell Rep.",
  volume   =  36,
  number   =  5,
  pages    = "109471",
  month    =  aug,
  year     =  2021,
  keywords = "auxiliary metabolism; bacteriophages; cysteine; human microbiome;
              organic sulfur; sulfide; viruses",
  language = "en"
}

@ARTICLE{Liang2020-lr,
  title    = "The stepwise assembly of the neonatal virome is modulated by
              breastfeeding",
  author   = "Liang, Guanxiang and Zhao, Chunyu and Zhang, Huanjia and Mattei,
              Lisa and Sherrill-Mix, Scott and Bittinger, Kyle and Kessler,
              Lyanna R and Wu, Gary D and Baldassano, Robert N and DeRusso,
              Patricia and Ford, Eileen and Elovitz, Michal A and Kelly,
              Matthew S and Patel, Mohamed Z and Mazhani, Tiny and Gerber,
              Jeffrey S and Kelly, Andrea and Zemel, Babette S and Bushman,
              Frederic D",
  abstract = "The gut of healthy human neonates is usually devoid of viruses at
              birth, but quickly becomes colonized, which-in some cases-leads
              to gastrointestinal disorders1-4. Here we show that the assembly
              of the viral community in neonates takes place in distinct steps.
              Fluorescent staining of virus-like particles purified from infant
              meconium or early stool samples shows few or no particles, but by
              one month of life particle numbers increase to 109 per gram, and
              these numbers seem to persist throughout life5-7. We investigated
              the origin of these viral populations using shotgun metagenomic
              sequencing of virus-enriched preparations and whole microbial
              communities, followed by targeted microbiological analyses.
              Results indicate that, early after birth, pioneer bacteria
              colonize the infant gut and by one month prophages induced from
              these bacteria provide the predominant population of virus-like
              particles. By four months of life, identifiable viruses that
              replicate in human cells become more prominent. Multiple human
              viruses were more abundant in stool samples from babies who were
              exclusively fed on formula milk compared with those fed partially
              or fully on breast milk, paralleling reports that breast milk can
              be protective against viral infections8-10. Bacteriophage
              populations also differed depending on whether or not the infant
              was breastfed. We show that the colonization of the infant gut is
              stepwise, first mainly by temperate bacteriophages induced from
              pioneer bacteria, and later by viruses that replicate in human
              cells; this second phase is modulated by breastfeeding.",
  journal  = "Nature",
  volume   =  581,
  number   =  7809,
  pages    = "470--474",
  month    =  may,
  year     =  2020,
  keywords = "phamb;phamb",
  language = "en"
}

@ARTICLE{Dion2020-hj,
  title    = "Phage diversity, genomics and phylogeny",
  author   = "Dion, Mo{\"\i}ra B and Oechslin, Frank and Moineau, Sylvain",
  abstract = "Recent advances in viral metagenomics have enabled the rapid
              discovery of an unprecedented catalogue of phages in numerous
              environments, from the human gut to the deep ocean. Although
              these advances have expanded our understanding of phage genomic
              diversity, they also revealed that we have only scratched the
              surface in the discovery of novel viruses. Yet, despite the
              remarkable diversity of phages at the nucleotide sequence level,
              the structural proteins that form viral particles show strong
              similarities and conservation. Phages are uniquely interconnected
              from an evolutionary perspective and undergo multiple events of
              genetic exchange in response to the selective pressure of their
              hosts, which drives their diversity. In this Review, we explore
              phage diversity at the structural, genomic and community levels
              as well as the complex evolutionary relationships between phages,
              moulded by the mosaicity of their genomes.",
  journal  = "Nat. Rev. Microbiol.",
  volume   =  18,
  number   =  3,
  pages    = "125--138",
  month    =  mar,
  year     =  2020,
  language = "en"
}

@ARTICLE{Shamash2021-nk,
  title    = "Phages in the infant gut: a framework for virome development
              during early life",
  author   = "Shamash, Michael and Maurice, Corinne F",
  journal  = "ISME J.",
  month    =  aug,
  year     =  2021,
  language = "en"
}

@ARTICLE{Plaza_Onate2019-sh,
  title    = "{MSPminer}: abundance-based reconstitution of microbial
              pan-genomes from shotgun metagenomic data",
  author   = "Plaza O{\~n}ate, Florian and Le Chatelier, Emmanuelle and
              Almeida, Mathieu and Cervino, Alessandra C L and Gauthier, Franck
              and Magoul{\`e}s, Fr{\'e}d{\'e}ric and Ehrlich, S Dusko and
              Pichaud, Matthieu",
  abstract = "MOTIVATION: Analysis toolkits for shotgun metagenomic data
              achieve strain-level characterization of complex microbial
              communities by capturing intra-species gene content variation.
              Yet, these tools are hampered by the extent of reference genomes
              that are far from covering all microbial variability, as many
              species are still not sequenced or have only few strains
              available. Binning co-abundant genes obtained from de novo
              assembly is a powerful reference-free technique to discover and
              reconstitute gene repertoire of microbial species. While current
              methods accurately identify species core parts, they miss many
              accessory genes or split them into small gene groups that remain
              unassociated to core clusters. RESULTS: We introduce MSPminer, a
              computationally efficient software tool that reconstitutes
              Metagenomic Species Pan-genomes (MSPs) by binning co-abundant
              genes across metagenomic samples. MSPminer relies on a new robust
              measure of proportionality coupled with an empirical classifier
              to group and distinguish not only species core genes but
              accessory genes also. Applied to a large scale metagenomic
              dataset, MSPminer successfully delineates in a few hours the gene
              repertoires of 1661 microbial species with similar specificity
              and higher sensitivity than existing tools. The taxonomic
              annotation of MSPs reveals microorganisms hitherto unknown and
              brings coherence in the nomenclature of the species of the human
              gut microbiota. The provided MSPs can be readily used for
              taxonomic profiling and biomarkers discovery in human gut
              metagenomic samples. In addition, MSPminer can be applied on gene
              count tables from other ecosystems to perform similar analyses.
              AVAILABILITY AND IMPLEMENTATION: The binary is freely available
              for non-commercial users at www.enterome.com/downloads.
              SUPPLEMENTARY INFORMATION: Supplementary data are available at
              Bioinformatics online.",
  journal  = "Bioinformatics",
  volume   =  35,
  number   =  9,
  pages    = "1544--1552",
  month    =  may,
  year     =  2019,
  language = "en"
}

@ARTICLE{Almeida2019-fk,
  title    = "A new genomic blueprint of the human gut microbiota",
  author   = "Almeida, Alexandre and Mitchell, Alex L and Boland, Miguel and
              Forster, Samuel C and Gloor, Gregory B and Tarkowska, Aleksandra
              and Lawley, Trevor D and Finn, Robert D",
  abstract = "The composition of the human gut microbiota is linked to health
              and disease, but knowledge of individual microbial species is
              needed to decipher their biological roles. Despite extensive
              culturing and sequencing efforts, the complete bacterial
              repertoire of the human gut microbiota remains undefined. Here we
              identify 1,952 uncultured candidate bacterial species by
              reconstructing 92,143 metagenome-assembled genomes from 11,850
              human gut microbiomes. These uncultured genomes substantially
              expand the known species repertoire of the collective human gut
              microbiota, with a 281\% increase in phylogenetic diversity.
              Although the newly identified species are less prevalent in
              well-studied populations compared to reference isolate genomes,
              they improve classification of understudied African and South
              American samples by more than 200\%. These candidate species
              encode hundreds of newly identified biosynthetic gene clusters
              and possess a distinctive functional capacity that might explain
              their elusive nature. Our work expands the known diversity of
              uncultured gut bacteria, which provides unprecedented resolution
              for taxonomic and functional characterization of the intestinal
              microbiota.",
  journal  = "Nature",
  volume   =  568,
  number   =  7753,
  pages    = "499--504",
  month    =  apr,
  year     =  2019
}

@ARTICLE{Ghosh2022-vc,
  title    = "The gut microbiome as a modulator of healthy ageing",
  author   = "Ghosh, Tarini Shankar and Shanahan, Fergus and O'Toole, Paul W",
  abstract = "The gut microbiome is a contributory factor in ageing-related
              health loss and in several non-communicable diseases in all age
              groups. Some age-linked and disease-linked compositional and
              functional changes overlap, while others are distinct. In this
              Review, we explore targeted studies of the gut microbiome of
              older individuals and general cohort studies across
              geographically distinct populations. We also address the promise
              of the targeted restoration of microorganisms associated with
              healthier ageing.",
  journal  = "Nat. Rev. Gastroenterol. Hepatol.",
  volume   =  19,
  number   =  9,
  pages    = "565--584",
  month    =  sep,
  year     =  2022,
  language = "en"
}

@ARTICLE{Doersch2016-bo,
  title         = "Tutorial on Variational Autoencoders",
  author        = "Doersch, Carl",
  abstract      = "In just three years, Variational Autoencoders (VAEs) have
                   emerged as one of the most popular approaches to
                   unsupervised learning of complicated distributions. VAEs are
                   appealing because they are built on top of standard function
                   approximators (neural networks), and can be trained with
                   stochastic gradient descent. VAEs have already shown promise
                   in generating many kinds of complicated data, including
                   handwritten digits, faces, house numbers, CIFAR images,
                   physical models of scenes, segmentation, and predicting the
                   future from static images. This tutorial introduces the
                   intuitions behind VAEs, explains the mathematics behind
                   them, and describes some empirical behavior. No prior
                   knowledge of variational Bayesian methods is assumed.",
  month         =  jun,
  year          =  2016,
  archivePrefix = "arXiv",
  primaryClass  = "stat.ML",
  eprint        = "1606.05908"
}

@ARTICLE{Bakir2006-kw,
  title    = "Bacteroides dorei sp. nov., isolated from human faeces",
  author   = "Bakir, Mohammad Abdul and Sakamoto, Mitsuo and Kitahara, Maki and
              Matsumoto, Mitsuharu and Benno, Yoshimi",
  abstract = "Two Gram-negative, anaerobic, non-spore-forming rod-shaped
              organisms were isolated from human faeces. These isolates were
              tentatively identified as Bacteroides based on morphological and
              biochemical criteria and appeared closely related to Bacteroides
              vulgatus ATCC 8482(T). The 16S rRNA gene sequence analysis showed
              that the isolates were highly related to each other (99.5 \%) and
              confirmed their placement in the genus Bacteroides. 16S rRNA gene
              sequence similarity values with close phylogenetic neighbours
              Bacteroides vulgatus ATCC 8482(T) (96 \%) and Bacteroides
              massiliensis CCUG 48901(T) (93 \%) preliminarily demonstrated
              that the organisms represented a novel species. The results of
              phenotypic, chemotaxonomic and 16S rRNA gene sequence analyses,
              and DNA-DNA homology values provided evidence that these two
              unknown isolates represent a single species and should be
              assigned to a novel species of the genus Bacteroides, as
              Bacteroides dorei sp. nov. The type strain is JCM 13471(T) (=DSM
              17855(T)).",
  journal  = "Int. J. Syst. Evol. Microbiol.",
  volume   =  56,
  number   = "Pt 7",
  pages    = "1639--1643",
  month    =  jul,
  year     =  2006,
  language = "en"
}

@ARTICLE{Duerkop2013-zx,
  title    = "Resident viruses and their interactions with the immune system",
  author   = "Duerkop, Breck A and Hooper, Lora V",
  abstract = "The human body is colonized with a diverse resident microflora
              that includes viruses. Recent studies of metagenomes have begun
              to characterize the composition of the human 'virobiota' and its
              associated genes (the 'virome'), and have fostered the emerging
              field of host-virobiota interactions. In this Perspective, we
              explore how resident viruses interact with the immune system. We
              review recent findings that highlight the role of the immune
              system in shaping the composition of the virobiota and consider
              how resident viruses may impact host immunity. Finally, we
              discuss the implications of virobiota-immune system interactions
              for human health.",
  journal  = "Nat. Immunol.",
  volume   =  14,
  number   =  7,
  pages    = "654--659",
  month    =  jul,
  year     =  2013,
  language = "en"
}

@ARTICLE{Bondy-Denomy2016-hy,
  title    = "Prophages mediate defense against phage infection through diverse
              mechanisms",
  author   = "Bondy-Denomy, Joseph and Qian, Jason and Westra, Edze R and
              Buckling, Angus and Guttman, David S and Davidson, Alan R and
              Maxwell, Karen L",
  abstract = "The activity of bacteriophages poses a major threat to bacterial
              survival. Upon infection, a temperate phage can either kill the
              host cell or be maintained as a prophage. In this state, the
              bacteria carrying the prophage is at risk of superinfection,
              where another phage injects its genetic material and competes for
              host cell resources. To avoid this, many phages have evolved
              mechanisms that alter the bacteria and make it resistant to phage
              superinfection. The mechanisms underlying these phentoypic
              conversions and the fitness consequences for the host are poorly
              understood, and systematic studies of superinfection exclusion
              mechanisms are lacking. In this study, we examined a wide range
              of Pseudomonas aeruginosa phages and found that they mediate
              superinfection exclusion through a variety of mechanisms, some of
              which affected the type IV pilus and O-antigen, and others that
              functioned inside the cell. The strongest resistance mechanism
              was a surface modification that we showed is cost-free for the
              bacterial host in a natural soil environment and in a
              Caenorhabditis. elegans infection model. This study represents
              the first systematic approach to address how a population of
              prophages influences phage resistance and bacterial behavior in
              P. aeruginosa.",
  journal  = "ISME J.",
  volume   =  10,
  number   =  12,
  pages    = "2854--2866",
  month    =  dec,
  year     =  2016,
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Gregory2019-xr,
  title    = "Marine {DNA} Viral Macro- and Microdiversity from Pole to Pole",
  author   = "Gregory, Ann C and Zayed, Ahmed A and Concei{\c c}{\~a}o-Neto,
              N{\'a}dia and Temperton, Ben and Bolduc, Ben and Alberti, Adriana
              and Ardyna, Mathieu and Arkhipova, Ksenia and Carmichael, Margaux
              and Cruaud, Corinne and Dimier, C{\'e}line and
              Dom{\'\i}nguez-Huerta, Guillermo and Ferland, Joannie and
              Kandels, Stefanie and Liu, Yunxiao and Marec, Claudie and Pesant,
              St{\'e}phane and Picheral, Marc and Pisarev, Sergey and Poulain,
              Julie and Tremblay, Jean-{\'E}ric and Vik, Dean and {Tara Oceans
              Coordinators} and Babin, Marcel and Bowler, Chris and Culley,
              Alexander I and de Vargas, Colomban and Dutilh, Bas E and
              Iudicone, Daniele and Karp-Boss, Lee and Roux, Simon and
              Sunagawa, Shinichi and Wincker, Patrick and Sullivan, Matthew B",
  abstract = "Microbes drive most ecosystems and are modulated by viruses that
              impact their lifespan, gene flow, and metabolic outputs. However,
              ecosystem-level impacts of viral community diversity remain
              difficult to assess due to classification issues and few
              reference genomes. Here, we establish an ∼12-fold expanded global
              ocean DNA virome dataset of 195,728 viral populations, now
              including the Arctic Ocean, and validate that these populations
              form discrete genotypic clusters. Meta-community analyses
              revealed five ecological zones throughout the global ocean,
              including two distinct Arctic regions. Across the zones, local
              and global patterns and drivers in viral community diversity were
              established for both macrodiversity (inter-population diversity)
              and microdiversity (intra-population genetic variation). These
              patterns sometimes, but not always, paralleled those from
              macro-organisms and revealed temperate and tropical surface
              waters and the Arctic as biodiversity hotspots and mechanistic
              hypotheses to explain them. Such further understanding of ocean
              viruses is critical for broader inclusion in ecosystem models.",
  journal  = "Cell",
  volume   =  177,
  number   =  5,
  pages    = "1109--1123.e14",
  month    =  may,
  year     =  2019,
  keywords = "community ecology; diversity gradients; marine biology;
              metagenomics; population ecology; species;
              viruses;phamb;1st\_regular\_assessment",
  language = "en"
}

@ARTICLE{Parras-Molto2018-wy,
  title    = "Evaluation of bias induced by viral enrichment and random
              amplification protocols in metagenomic surveys of saliva {DNA}
              viruses",
  author   = "Parras-Molt{\'o}, Marcos and Rodr{\'\i}guez-Galet, Ana and
              Su{\'a}rez-Rodr{\'\i}guez, Patricia and L{\'o}pez-Bueno, Alberto",
  abstract = "BACKGROUND: Viruses are key players regulating microbial
              ecosystems. Exploration of viral assemblages is now possible
              thanks to the development of metagenomics, the most powerful tool
              available for studying viral ecology and discovering new viruses.
              Unfortunately, several sources of bias lead to the
              misrepresentation of certain viruses within metagenomics
              workflows, hindering the shift from merely descriptive studies
              towards quantitative comparisons of communities. Therefore,
              benchmark studies on virus enrichment and random amplification
              protocols are required to better understand the sources of bias.
              RESULTS: We assessed the bias introduced by viral enrichment on
              mock assemblages composed of seven DNA viruses, and the bias from
              random amplification methods on human saliva DNA viromes, using
              qPCR and deep sequencing, respectively. While iodixanol cushions
              and 0.45 $\mu$m filtration preserved the original composition of
              nuclease-protected viral genomes, low-force centrifugation and
              0.22 $\mu$m filtration removed large viruses. Comparison of
              unamplified and randomly amplified saliva viromes revealed that
              multiple displacement amplification (MDA) induced stochastic bias
              from picograms of DNA template. However, the type of bias shifted
              to systematic using 1 ng, with only a marginal influence by
              amplification time. Systematic bias consisted of
              over-amplification of small circular genomes, and
              under-amplification of those with extreme GC content, a negative
              bias that was shared with the PCR-based sequence-independent,
              single-primer amplification (SISPA) method. MDA based on random
              priming provided by a DNA primase activity slightly outperformed
              those based on random hexamers and SISPA, which may reflect
              differences in ability to handle sequences with extreme GC
              content. SISPA viromes showed uneven coverage profiles, with high
              coverage peaks in regions with low linguistic sequence
              complexity. Despite misrepresentation of certain viruses after
              random amplification, ordination plots based on dissimilarities
              among contig profiles showed perfect overlapping of related
              amplified and unamplified saliva viromes and strong separation
              from unrelated saliva viromes. This result suggests that random
              amplification bias has a minor impact on beta diversity studies.
              CONCLUSIONS: Benchmark analyses of mock and natural communities
              of viruses improve understanding and mitigate bias in
              metagenomics surveys. Bias induced by random amplification
              methods has only a minor impact on beta diversity studies of
              human saliva viromes.",
  journal  = "Microbiome",
  volume   =  6,
  number   =  1,
  pages    = "119",
  month    =  jun,
  year     =  2018,
  language = "en"
}

@MISC{Shah_undated-vc,
  title  = "Manual resolution of virome dark matter uncovers hundreds of viral
            families in the infant gut",
  author = "Shah, Shiraz A and Deng, Ling and Thorsen, Jonathan and Pedersen,
            Anders Gorm and Dion, Mo{\"\i}ra B and Castro Mejia, Josue and
            Silins, Ronalds and Romme, Fie O and Sausset, Romain and Ndela,
            Eric O and Hjems{\o}, Mathis H and Rasmussen, Morten Arendt A and
            Redgwell, Tamsin and Vestergaard, Gisle A and Zhang, Yichang and
            Enault, Francois and S{\o}rensen, S{\o}ren Johannes and Bisgaard,
            Hans and Stokholm, Jakob and Moineau, Sylvain and Petit,
            Marie-Agnes and Nielsen, Dennis Sandris"
}

@ARTICLE{Zuo2021-ll,
  title    = "Depicting {SARS-CoV-2} faecal viral activity in association with
              gut microbiota composition in patients with {COVID-19}",
  author   = "Zuo, Tao and Liu, Qin and Zhang, Fen and Lui, Grace Chung-Yan and
              Tso, Eugene Yk and Yeoh, Yun Kit and Chen, Zigui and Boon, Siaw
              Shi and Chan, Francis Kl and Chan, Paul Ks and Ng, Siew C",
  abstract = "OBJECTIVE: Although severe acute respiratory syndrome coronavirus
              2 (SARS-CoV-2) RNA was detected in faeces of patients with
              COVID-19, the activity and infectivity of the virus in the GI
              tract during disease course is largely unknown. We investigated
              temporal transcriptional activity of SARS-CoV-2 and its
              association with longitudinal faecal microbiome alterations in
              patients with COVID-19. DESIGN: We performed RNA shotgun
              metagenomics sequencing on serial faecal viral extractions from
              15 hospitalised patients with COVID-19. Sequencing coverage of
              the SARS-CoV-2 genome was quantified. We assessed faecal
              microbiome composition and microbiome functionality in
              association with signatures of faecal SARS-CoV-2 infectivity.
              RESULTS: Seven (46.7\%) of 15 patients with COVID-19 had stool
              positivity for SARS-CoV-2 by viral RNA metagenomic sequencing.
              Even in the absence of GI manifestations, all seven patients
              showed strikingly higher coverage (p=0.0261) and density
              (p=0.0094) of the 3' vs 5' end of SARS-CoV-2 genome in their
              faecal viral metagenome profile. Faecal viral metagenome of three
              patients continued to display active viral infection signature
              (higher 3' vs 5' end coverage) up to 6 days after clearance of
              SARS-CoV-2 from respiratory samples. Faecal samples with
              signature of high SARS-CoV-2 infectivity had higher abundances of
              bacterial species Collinsella aerofaciens, Collinsella tanakaei,
              Streptococcus infantis, Morganella morganii, and higher
              functional capacity for nucleotide de novo biosynthesis, amino
              acid biosynthesis and glycolysis, whereas faecal samples with
              signature of low-to-none SARS-CoV-2 infectivity had higher
              abundances of short-chain fatty acid producing bacteria,
              Parabacteroides merdae, Bacteroides stercoris, Alistipes
              onderdonkii and Lachnospiraceae bacterium 1\_1\_57FAA.
              CONCLUSION: This pilot study provides evidence for active and
              prolonged 'quiescent' GI infection even in the absence of GI
              manifestations and after recovery from respiratory infection of
              SARS-CoV-2. Gut microbiota of patients with active SARS-CoV-2 GI
              infection was characterised by enrichment of opportunistic
              pathogens, loss of salutary bacteria and increased functional
              capacity for nucleotide and amino acid biosynthesis and
              carbohydrate metabolism.",
  journal  = "Gut",
  volume   =  70,
  number   =  2,
  pages    = "276--284",
  month    =  feb,
  year     =  2021,
  keywords = "diagnostic virology; gut inflammation; infectious disease",
  language = "en"
}

@ARTICLE{Russel2020-wz,
  title    = "{CRISPRCasTyper}: Automated Identification, Annotation, and
              Classification of {CRISPR-Cas} Loci",
  author   = "Russel, Jakob and Pinilla-Redondo, Rafael and Mayo-Mu{\~n}oz,
              David and Shah, Shiraz A and S{\o}rensen, S{\o}ren J",
  abstract = "Automated classification of CRISPR-Cas systems has been
              challenged by their dynamic nature and expanding classification.
              Here, we developed CRISPRCasTyper, an automated tool with
              improved capabilities for identifying and typing CRISPR arrays
              and cas loci based on the latest nomenclature (44
              subtypes/variants). As a novel feature, CRISPRCasTyper uses a
              machine learning approach to subtype CRISPR arrays based on the
              sequences of the repeats, which allows the typing of orphan and
              distant arrays. CRISPRCasTyper provides a graphical output, where
              CRISPRs and cas operons are visualized as gene maps, thus aiding
              annotation of partial and novel systems through synteny.
              CRISPRCasTyper was benchmarked against a manually curated set of
              31 subtypes with a median accuracy of 98.6\% and used to explore
              CRISPR-Cas diversity across >3,000 metagenomes. Altogether, we
              present an up-to-date software for improved automated prediction
              of CRISPR-Cas loci. CRISPRCasTyper is available through conda and
              as a web server (cctyper.crispr.dk).",
  journal  = "CRISPR J",
  volume   =  3,
  number   =  6,
  pages    = "462--469",
  month    =  dec,
  year     =  2020,
  language = "en"
}

@ARTICLE{Pasolli2019-ik,
  title    = "Extensive Unexplored Human Microbiome Diversity Revealed by Over
              150,000 Genomes from Metagenomes Spanning Age, Geography, and
              Lifestyle",
  author   = "Pasolli, Edoardo and Asnicar, Francesco and Manara, Serena and
              Zolfo, Moreno and Karcher, Nicolai and Armanini, Federica and
              Beghini, Francesco and Manghi, Paolo and Tett, Adrian and Ghensi,
              Paolo and Collado, Maria Carmen and Rice, Benjamin L and DuLong,
              Casey and Morgan, Xochitl C and Golden, Christopher D and Quince,
              Christopher and Huttenhower, Curtis and Segata, Nicola",
  abstract = "The body-wide human microbiome plays a role in health, but its
              full diversity remains uncharacterized, particularly outside of
              the gut and in international populations. We leveraged 9,428
              metagenomes to reconstruct 154,723 microbial genomes (45\% of
              high quality) spanning body sites, ages, countries, and
              lifestyles. We recapitulated 4,930 species-level genome bins
              (SGBs), 77\% without genomes in public repositories (unknown SGBs
              [uSGBs]). uSGBs are prevalent (in 93\% of well-assembled
              samples), expand underrepresented phyla, and are enriched in
              non-Westernized populations (40\% of the total SGBs). We
              annotated 2.85 M genes in SGBs, many associated with conditions
              including infant development (94,000) or Westernization
              (106,000). SGBs and uSGBs permit deeper microbiome analyses and
              increase the average mappability of metagenomic reads from
              67.76\% to 87.51\% in the gut (median 94.26\%) and 65.14\% to
              82.34\% in the mouth. We thus identify thousands of microbial
              genomes from yet-to-be-named species, expand the pangenomes of
              human-associated microbes, and allow better exploitation of
              metagenomic technologies.",
  journal  = "Cell",
  volume   =  176,
  number   =  3,
  pages    = "649--662.e20",
  month    =  jan,
  year     =  2019,
  keywords = "human microbiome; metagenomic assembly; metagenomic mappability;
              metagenomic meta-analysis; metagenomics; non-Westernized
              microbiomes; unexplored microbial diversity",
  language = "en"
}

@ARTICLE{Ma2019-mp,
  title    = "Integrate multi-omics data with biological interaction networks
              using Multi-view Factorization {AutoEncoder} ({MAE})",
  author   = "Ma, Tianle and Zhang, Aidong",
  abstract = "BACKGROUND: Comprehensive molecular profiling of various cancers
              and other diseases has generated vast amounts of multi-omics
              data. Each type of -omics data corresponds to one feature space,
              such as gene expression, miRNA expression, DNA methylation, etc.
              Integrating multi-omics data can link different layers of
              molecular feature spaces and is crucial to elucidate molecular
              pathways underlying various diseases. Machine learning approaches
              to mining multi-omics data hold great promises in uncovering
              intricate relationships among molecular features. However, due to
              the ``big p, small n'' problem (i.e., small sample sizes with
              high-dimensional features), training a large-scale generalizable
              deep learning model with multi-omics data alone is very
              challenging. RESULTS: We developed a method called Multi-view
              Factorization AutoEncoder (MAE) with network constraints that can
              seamlessly integrate multi-omics data and domain knowledge such
              as molecular interaction networks. Our method learns feature and
              patient embeddings simultaneously with deep representation
              learning. Both feature representations and patient
              representations are subject to certain constraints specified as
              regularization terms in the training objective. By incorporating
              domain knowledge into the training objective, we implicitly
              introduced a good inductive bias into the machine learning model,
              which helps improve model generalizability. We performed
              extensive experiments on the TCGA datasets and demonstrated the
              power of integrating multi-omics data and biological interaction
              networks using our proposed method for predicting target clinical
              variables. CONCLUSIONS: To alleviate the overfitting problem in
              deep learning on multi-omics data with the ``big p, small n''
              problem, it is helpful to incorporate biological domain knowledge
              into the model as inductive biases. It is very promising to
              design machine learning models that facilitate the seamless
              integration of large-scale multi-omics data and biomedical domain
              knowledge for uncovering intricate relationships among molecular
              features and clinical features.",
  journal  = "BMC Genomics",
  volume   =  20,
  number   = "Suppl 11",
  pages    = "944",
  month    =  dec,
  year     =  2019,
  keywords = "Autoencoder; Biological interaction networks; Data integration;
              Deep learning; Graph regularization; Multi-omics data; Multi-view
              learning",
  language = "en"
}

@ARTICLE{Gogokhia2019-li,
  title    = "Expansion of Bacteriophages Is Linked to Aggravated Intestinal
              Inflammation and Colitis",
  author   = "Gogokhia, Lasha and Buhrke, Kate and Bell, Rickesha and Hoffman,
              Brenden and Brown, D Garrett and Hanke-Gogokhia, Christin and
              Ajami, Nadim J and Wong, Matthew C and Ghazaryan, Arevik and
              Valentine, John F and Porter, Nathan and Martens, Eric and
              O'Connell, Ryan and Jacob, Vinita and Scherl, Ellen and Crawford,
              Carl and Stephens, W Zac and Casjens, Sherwood R and Longman,
              Randy S and Round, June L",
  abstract = "Bacteriophages are the most abundant members of the microbiota
              and have the potential to shape gut bacterial communities.
              Changes to bacteriophage composition are associated with disease,
              but how phages impact mammalian health remains unclear. We noted
              an induction of host immunity when experimentally treating
              bacterially driven cancer, leading us to test whether
              bacteriophages alter immune responses. Treating germ-free mice
              with bacteriophages leads to immune cell expansion in the gut.
              Lactobacillus, Escherichia, and Bacteroides bacteriophages and
              phage DNA stimulated IFN-$\gamma$ via the nucleotide-sensing
              receptor TLR9. The resultant immune responses were both phage and
              bacteria specific. Additionally, increasing bacteriophage levels
              exacerbated colitis via TLR9 and IFN-$\gamma$. Similarly,
              ulcerative colitis (UC) patients responsive to fecal microbiota
              transplantation (FMT) have reduced phages compared to
              non-responders, and mucosal IFN-$\gamma$ positively correlates
              with bacteriophage levels. Bacteriophages from active UC patients
              induced more IFN-$\gamma$ compared to healthy individuals.
              Collectively, these results indicate that bacteriophages can
              alter mucosal immunity to impact mammalian health.",
  journal  = "Cell Host Microbe",
  volume   =  25,
  number   =  2,
  pages    = "285--299.e8",
  month    =  feb,
  year     =  2019,
  keywords = "FMT; IFN-y; T cells; TLR9; Th1; bacteriophages; colitis;
              dendritic cells",
  language = "en"
}

@INCOLLECTION{Ehrlich2011-el,
  title     = "{MetaHIT}: The European Union Project on Metagenomics of the
               Human Intestinal Tract",
  booktitle = "Metagenomics of the Human Body",
  author    = "Ehrlich, S Dusko",
  editor    = "Nelson, Karen E",
  abstract  = "MetaHIT (http://www.metahit.eu) has as a first objective the
               creation of a catalog of the microbial genes from our intestinal
               tract, thus laying foundations for characterization of the gut
               microbial communities. Next, it aims to explore associations
               between microbial genes and human phenotypes. For that, it
               develops, on the one hand, molecular tools for profiling of the
               intestinal microbial genes that are harbored by any individual,
               and on the other, a bio-informatics resource to organize and
               interpret heterogeneous information, including sequencing data
               and clinical metadata. Moreover, MetaHIT develops approaches to
               detect and analyze functional interactions of microbes and the
               human host, focusing on the role of target genes in the
               microbial cell and the effect of gene products on the human
               host. MetaHIT targets two pathologies, obesity and inflammatory
               bowel diseases (Crohn's disease and ulcerative colitis). The
               studies involve (i) cross-sectional comparisons of healthy and
               sick individuals; (ii) longitudinal follow-up of patients in
               clinical remission; (iii) nutritional intervention related to
               the stability of gut microbial community; and (iv) comparison of
               patients responding or not to a drug treatment.",
  publisher = "Springer New York",
  pages     = "307--316",
  year      =  2011,
  address   = "New York, NY"
}

@ARTICLE{Paez-Espino2016-bb,
  title    = "Uncovering Earth's virome",
  author   = "Paez-Espino, David and Eloe-Fadrosh, Emiley A and Pavlopoulos,
              Georgios A and Thomas, Alex D and Huntemann, Marcel and
              Mikhailova, Natalia and Rubin, Edward and Ivanova, Natalia N and
              Kyrpides, Nikos C",
  abstract = "Viruses are the most abundant biological entities on Earth, but
              challenges in detecting, isolating, and classifying unknown
              viruses have prevented exhaustive surveys of the global virome.
              Here we analysed over 5 Tb of metagenomic sequence data from
              3,042 geographically diverse samples to assess the global
              distribution, phylogenetic diversity, and host specificity of
              viruses. We discovered over 125,000 partial DNA viral genomes,
              including the largest phage yet identified, and increased the
              number of known viral genes by 16-fold. Half of the predicted
              partial viral genomes were clustered into genetically distinct
              groups, most of which included genes unrelated to those in known
              viruses. Using CRISPR spacers and transfer RNA matches to link
              viral groups to microbial host(s), we doubled the number of
              microbial phyla known to be infected by viruses, and identified
              viruses that can infect organisms from different phyla. Analysis
              of viral distribution across diverse ecosystems revealed strong
              habitat-type specificity for the vast majority of viruses, but
              also identified some cosmopolitan groups. Our results highlight
              an extensive global viral diversity and provide detailed insight
              into viral habitat distribution and host--virus interactions.",
  journal  = "Nature",
  volume   =  536,
  number   =  7617,
  pages    = "425--430",
  month    =  aug,
  year     =  2016,
  language = "en"
}

@ARTICLE{Hargreaves2014-be,
  title    = "Clostridium difficile phages: still difficult?",
  author   = "Hargreaves, Katherine R and Clokie, Martha R J",
  abstract = "Phages that infect Clostridium difficile were first isolated for
              typing purposes in the 1980s, but their use was short lived.
              However, the rise of C. difficile epidemics over the last decade
              has triggered a resurgence of interest in using phages to combat
              this pathogen. Phage therapy is an attractive treatment option
              for C. difficile infection, however, developing suitable phages
              is challenging. In this review we summarize the difficulties
              faced by researchers in this field, and we discuss the solutions
              and strategies used for the development of C. difficile phages
              for use as novel therapeutics. Epidemiological data has
              highlighted the diversity and distribution of C. difficile, and
              shown that novel strains continue to emerge in clinical settings.
              In parallel with epidemiological studies, advances in molecular
              biology have bolstered our understanding of C. difficile biology,
              and our knowledge of phage-host interactions in other bacterial
              species. These three fields of biology have therefore paved the
              way for future work on C. difficile phages to progress and
              develop. Benefits of using C. difficile phages as therapeutic
              agents include the fact that they have highly specific
              interactions with their bacterial hosts. Studies also show that
              they can reduce bacterial numbers in both in vitro and in vivo
              systems. Genetic analysis has revealed the genomic diversity
              among these phages and provided an insight into their taxonomy
              and evolution. No strictly virulent C. difficile phages have been
              reported and this contributes to the difficulties with their
              therapeutic exploitation. Although treatment approaches using the
              phage-encoded endolysin protein have been explored, the benefits
              of using ``whole-phages'' are such that they remain a major
              research focus. Whilst we don't envisage working with C.
              difficile phages will be problem-free, sufficient study should
              inform future strategies to facilitate their development to
              combat this problematic pathogen.",
  journal  = "Front. Microbiol.",
  volume   =  5,
  pages    = "184",
  month    =  apr,
  year     =  2014,
  keywords = "Clostridium difficile; genomics; gut pathogen; lysogeny;
              nosocomial; phage evolution; phage therapy",
  language = "en"
}

@ARTICLE{Wu2019-wo,
  title    = "A {Cross-Sectional} Study of Compositional and Functional
              Profiles of Gut Microbiota in Sardinian Centenarians",
  author   = "Wu, Lu and Zeng, Tiansheng and Zinellu, Angelo and Rubino,
              Salvatore and Kelvin, David J and Carru, Ciriaco",
  abstract = "Sardinia, Italy, has a high prevalence of residents who live more
              than 100 years. The reasons for longevity in this isolated region
              are currently unknown. Gut microbiota may hold a clue. To explore
              the role gut microbiota may play in healthy aging and longevity,
              we used metagenomic sequencing to determine the compositional and
              functional differences in gut microbiota associated with
              populations of different ages in Sardinia. Our data revealed that
              the gut microbiota of both young and elderly Sardinians shared
              similar taxonomic and functional profiles. A different pattern
              was found in centenarians. Within the centenarian group, the gut
              microbiota was correlated with the functional independence
              measurement of the host. Centenarians had a higher diversity of
              core microbiota species and microbial genes than those in the
              young and elderly. We found that the gut microbiota in Sardinian
              centenarians displayed a rearranged taxonomic pattern compared
              with those of the young and elderly, featured by depletion of
              Faecalibacterium prausnitzii and Eubacterium rectale and enriched
              for Methanobrevibacter smithii and Bifidobacterium adolescentis
              Moreover, functional analysis revealed that the microbiota in
              centenarians had high capacity for central metabolism, especially
              glycolysis and fermentation to short-chain fatty acids (SCFAs),
              although the gut microbiota in centenarians was low in genes
              encoding enzymes involved in degradation of carbohydrates,
              including fibers and galactose.IMPORTANCE The gut microbiota has
              been proposed as a promising determinant for human health.
              Centenarians as a model for extreme aging may help us understand
              the correlation of gut microbiota with healthy aging and
              longevity. Here we confirmed that centenarians had microbiota
              elements usually associated with benefits to health. Our finding
              of a high capacity of glycolysis and related SCFA production
              represented a healthy microbiome and environment that is regarded
              as beneficial for host gut epithelium. The low abundance of genes
              encoding components of pathways involved in carbohydrate
              degradation was also found in the gut microbiota of Sardinian
              centenarians and is often associated with poor gut health.
              Overall, our study here represents an expansion of previous
              research investigating the age-related changes in gut microbiota.
              Furthermore, our study provides a new prospective for potential
              targets for gut microbiota intervention directed at limiting gut
              inflammation and pathology and enhancing a healthy gut barrier.",
  journal  = "mSystems",
  volume   =  4,
  number   =  4,
  month    =  jul,
  year     =  2019,
  keywords = "centenarian; gut microbiota; longevity; metagenomic sequencing",
  language = "en"
}

@ARTICLE{Uritskiy2018-uz,
  title     = "{MetaWRAP---a} flexible pipeline for genome-resolved metagenomic
               data analysis",
  author    = "Uritskiy, Gherman V and DiRuggiero, Jocelyne and Taylor, James",
  abstract  = "The study of microbiomes using whole-metagenome shotgun
               sequencing enables the analysis of uncultivated microbial
               populations that may have important roles in their environments.
               Extracting individual draft genomes (bins) facilitates
               metagenomic analysis at the single genome level. Software and
               pipelines for such analysis have become diverse and
               sophisticated, resulting in a significant burden for biologists
               to access and use them. Furthermore, while bin extraction
               algorithms are rapidly improving, there is still a lack of tools
               for their evaluation and visualization. To address these
               challenges, we present metaWRAP, a modular pipeline software for
               shotgun metagenomic data analysis. MetaWRAP deploys
               state-of-the-art software to handle metagenomic data processing
               starting from raw sequencing reads and ending in metagenomic
               bins and their analysis. MetaWRAP is flexible enough to give
               investigators control over the analysis, while still being
               easy-to-install and easy-to-use. It includes hybrid algorithms
               that leverage the strengths of a variety of software to extract
               and refine high-quality bins from metagenomic data through bin
               consolidation and reassembly. MetaWRAP's hybrid bin extraction
               algorithm outperforms individual binning approaches and other
               bin consolidation programs in both synthetic and real data sets.
               Finally, metaWRAP comes with numerous modules for the analysis
               of metagenomic bins, including taxonomy assignment, abundance
               estimation, functional annotation, and visualization. MetaWRAP
               is an easy-to-use modular pipeline that automates the core tasks
               in metagenomic analysis, while contributing significant
               improvements to the extraction and interpretation of
               high-quality metagenomic bins. The bin refinement and reassembly
               modules of metaWRAP consistently outperform other binning
               approaches. Each module of metaWRAP is also a standalone
               component, making it a flexible and versatile tool for tackling
               metagenomic shotgun sequencing data. MetaWRAP is open-source
               software available at https://github.com/bxlab/metaWRAP .",
  journal   = "Microbiome",
  publisher = "BioMed Central",
  volume    =  6,
  number    =  1,
  pages     = "1--13",
  month     =  sep,
  year      =  2018,
  language  = "en"
}