Move long read preprocessing into a subworkflow

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - [#665](https://github.com/nf-core/mag/pull/648) - Add support for supplying pre-made bowtie host reference index (requested by @simone-pignotti, added by @jfy133)
 - [#670](https://github.com/nf-core/mag/pull/670) - Added --gtdbtk_pplacer_useram to run GTDBTk in memory mode rather than write to disk (reported by @harper357, fixed by @jfy133)
+- Added optional use of porechop-abi, instead of porechop, for long read adapter trimming.
 
 ### `Changed`
 
@@ -20,6 +21,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#667](https://github.com/nf-core/mag/pull/667) - Fix pipeline crashing if only CONCOCT selected during binning (reported and fixed by @jfy133)
 - [#670](https://github.com/nf-core/mag/pull/670) - Re-add missing GTDBTk parameters into GTDBTk module (reported by harper357, fixed by @jfy133)
 - [#672](https://github.com/nf-core/mag/pull/673) - Fix GTDB-Tk per-sample TSV files not being published in output directory (reported by @jhayer, fix by @jfy133)
+- Make longread preprocessing a subworkflow
+- Add porechop and filtlong logs to multiqc
+- Change local filtlong module to the official nf-core/filtlong module
 
 ### `Dependencies`
 

CITATIONS.md

@@ -40,6 +40,10 @@
 
   > Parks, D. H., Imelfort, M., Skennerton, C. T., Hugenholtz, P., & Tyson, G. W. (2015). CheckM: assessing the quality of microbial genomes recovered from isolates, single cells, and metagenomes. Genome Research, 25(7), 1043–1055. doi: 10.1101/gr.186072.114
 
+- [Chopper](https://github.com/wdecoster/chopper)
+
+  > De Coster W, Rademakers R. NanoPack2: population-scale evaluation of long-read sequencing data. Bioinformatics. 2023 May 4;39(5):btad311. doi: 10.1093/bioinformatics/btad311. PMID: 37171891; PMCID: PMC10196664.
+
 - [CONCOCT](https://doi.org/10.1038/nmeth.3103)
 
   > Alneberg, J., Bjarnason, B. S., de Bruijn, I., Schirmer, M., Quick, J., Ijaz, U. Z., Lahti, L., Loman, N. J., Andersson, A. F., & Quince, C. (2014). Binning metagenomic contigs by coverage and composition. Nature Methods, 11(11), 1144–1146. doi: 10.1038/nmeth.3103
@@ -116,6 +120,8 @@
 
 - [Porechop](https://github.com/rrwick/Porechop)
 
+- [Porechop-abi](https://github.com/bonsai-team/Porechop_ABI)
+
 - [Prodigal](https://pubmed.ncbi.nlm.nih.gov/20211023/)
 
   > Hyatt D, Chen GL, Locascio PF, Land ML, Larimer FW, Hauser LJ. Prodigal: prokaryotic gene recognition and translation initiation site identification. BMC Bioinformatics. 2010 Mar 8;11:119. doi: 10.1186/1471-2105-11-119. PMID: 20211023; PMCID: PMC2848648.

README.md

@@ -90,6 +90,7 @@ Other code contributors include:
 - [Jim Downie](https://github.com/prototaxites)
 - [Phil Palmer](https://github.com/PhilPalmer)
 - [@willros](https://github.com/willros)
+- [Adam Rosenbaum](https://github.com/muabnezor)
 
 Long read processing was inspired by [caspargross/HybridAssembly](https://github.com/caspargross/HybridAssembly) written by Caspar Gross [@caspargross](https://github.com/caspargross)
 

assets/multiqc_config.yml

@@ -25,6 +25,8 @@ run_modules:
   - quast
   - kraken
   - prokka
+  - porechop
+  - filtlong
 
 ## Module order
 top_modules:
@@ -35,6 +37,7 @@ top_modules:
   - "fastp"
   - "adapterRemoval"
   - "porechop"
+  - "filtlong"
   - "fastqc":
       name: "FastQC: after preprocessing"
       info: "After trimming and, if requested, contamination removal."
@@ -109,6 +112,9 @@ sp:
     fn_re: ".*[kraken2|centrifuge].*report.txt"
   quast:
     fn_re: "report.*.tsv"
+  filtlong:
+    num_lines: 20
+    fn_re: ".*_filtlong.log"
 
 ## File name cleaning
 extra_fn_clean_exts:

conf/modules.config

@@ -171,20 +171,36 @@ process {
         publishDir = [
             path: { "${params.outdir}/QC_longreads/porechop" },
             mode: params.publish_dir_mode,
-            pattern: "*_trimmed.fastq",
+            pattern: "*_porechop_trimmed.fastq",
             enabled: params.save_porechop_reads
         ]
-        ext.prefix = { "${meta.id}_run${meta.run}_trimmed" }
+        ext.prefix = { "${meta.id}_run${meta.run}_porechop_trimmed" }
+    }
+
+    withName: PORECHOP_ABI {
+        publishDir = [
+                path: { "${params.outdir}/QC_longreads/porechop" },
+                mode: params.publish_dir_mode,
+                pattern: "*_porechop-abi_trimmed.fastq",
+                enabled: params.save_porechop_reads
+            ]
+        ext.prefix = { "${meta.id}_run${meta.run}_porechop-abi_trimmed" }
     }
 
     withName: FILTLONG {
+        ext.args = [
+            "--min_length ${params.longreads_min_length}",
+            "--keep_percent ${params.longreads_keep_percent}",
+            "--trim",
+            "--length_weight ${params.longreads_length_weight}"
+        ].join(' ').trim()
         publishDir = [
-            path: { "${params.outdir}/QC_longreads/Filtlong" },
-            mode: params.publish_dir_mode,
-            pattern: "*_lr_filtlong.fastq.gz",
-            enabled: params.save_filtlong_reads
-        ]
-        ext.prefix = { "${meta.id}_run${meta.run}_lengthfiltered" }
+                path: { "${params.outdir}/QC_longreads/Filtlong" },
+                mode: params.publish_dir_mode,
+                pattern: "*_lr_filtlong.fastq.gz",
+                enabled: params.save_filtlong_reads
+            ]
+        ext.prefix = { "${meta.id}_run${meta.run}_lr_filtlong" }
     }
 
     withName: NANOLYSE {

modules.json

@@ -62,6 +62,11 @@
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
                         "installed_by": ["modules"]
                     },
+                    "chopper": {
+                        "branch": "master",
+                        "git_sha": "06c8865e36741e05ad32ef70ab3fac127486af48",
+                        "installed_by": ["modules"]
+                    },
                     "concoct/concoct": {
                         "branch": "master",
                         "git_sha": "baa30accc6c50ea8a98662417d4f42ed18966353",
@@ -107,6 +112,11 @@
                         "git_sha": "285a50500f9e02578d90b3ce6382ea3c30216acd",
                         "installed_by": ["modules"]
                     },
+                    "filtlong": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "freebayes": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
@@ -202,6 +212,11 @@
                         "git_sha": "3135090b46f308a260fc9d5991d7d2f9c0785309",
                         "installed_by": ["modules"]
                     },
+                    "porechop/abi": {
+                        "branch": "master",
+                        "git_sha": "06c8865e36741e05ad32ef70ab3fac127486af48",
+                        "installed_by": ["modules"]
+                    },
                     "porechop/porechop": {
                         "branch": "master",
                         "git_sha": "1d68c7f248d1a480c5959548a9234602b771199e",