Add busco

CHANGELOG.md

@@ -5,6 +5,7 @@
 ## NEW FEATURES
 
 * `arriba`: Detect gene fusions from RNA-seq data (PR #1).
+* `busco`: Assess genome assembly and annotation completeness with single copy orthologs (PR #6).
 
 * `fastp`: An ultra-fast all-in-one FASTQ preprocessor (PR #3).
 

src/busco/config.vsh.yaml

@@ -0,0 +1,210 @@
+functionality:
+  name: busco
+  description: Assessment of genome assembly and annotation completeness with single copy orthologs
+  info:
+    keywords: [Genome assembly, quality control]
+    homepage: https://busco.ezlab.org/
+    documentation: https://busco.ezlab.org/busco_userguide.html
+    repository: https://gitlab.com/ezlab/busco
+    reference: "10.1007/978-1-4939-9173-0_14"
+    licence: MIT
+  argument_groups:
+    - name: Inputs
+      arguments:
+        - name: --input
+          alternatives: ["-i"]
+          type: file
+          description: |
+            Input fasta file or directory containing input fasta files to analyse. Fasta files can either be a nucleotide or protein fasta file, depending on the BUSCO mode.
+          required: true
+          example: file.fasta
+        - name: --mode
+          alternatives: ["-m"]
+          type: string
+          choices: ["protein", "genome", "transcriptome"]
+          required: true
+          description: |
+            Busco assesment mode
+          example: protein
+        - name: --lineage_dataset
+          alternatives: ["-l"]
+          type: string
+          required: false
+          description: |
+            Specify a BUSCO lineage dataset that is most closely related to the assembly or gene set being assessed. 
+            The full list of available datasets can be viewed using "busco --list-datasets".
+            When unsure, the "--auto-lineage" flag can be set to automatically find the optimal lineage path.
+            Requested datasets will automatically be downloaded if not already present in the download folder.
+          example: stramenopiles_odb10
+
+    - name: Outputs
+      arguments:
+        - name: --output_dir
+          alternatives: ["-o"]
+          required: true
+          direction: output
+          type: file
+          description: |
+            Path to output directory for publishing BUSCO results
+          example: output
+        - name: --output_prefix
+          type: string
+          required: false
+          description: |
+            Name of the analysis run, output folders and files will be labeled with this name. if not specified the output will be the input file name."
+          example: busco_protein
+
+    - name: Resource and Run Settings
+      arguments:
+        - name: --force
+          type: boolean_true
+          description: |
+            Force rewriting of existing files. Must be used when output files with the provided name already exist.
+        - name: --offline
+          type: boolean_true
+          description: |
+            In offline mode BUSCO will not attempt to download files. Ensure all required dataset files are already downloaded and available.
+        - name: --opt_out_run_stats
+          type: boolean_true
+          description: |
+            Opt out of data collection (from v5.6.0). Collected data is used to improve BUSCO.
+            All collected data is anonymised and includes the pipelines used, the datasets selected, options used and runtime statistics.
+        - name: --quiet
+          alternatives: ["-q"]
+          type: boolean_true
+          description: |
+            Disable the info logs, displays only errors.
+        - name: --restart
+          alternatives: ["-r"]
+          type: boolean_true
+          description: |
+            Continue a run that had already partially completed. Restarting skips calls to tools that have completed but performs all pre- and post-processing steps.
+        - name: --tar
+          type: boolean_true
+          description: |
+            Compress some subdirectories with many files to save space.
+
+    - name: Download Settings
+      arguments:
+        - name: --download
+          type: string
+          required: false
+          description: |
+            Download dataset. Possible values are a specific dataset name, "all", "prokaryota", "eukaryota", or "virus".
+        - name: --download_base_url
+          type: string
+          description: |
+            Set the url to the remote BUSCO dataset location.
+        - name: --download_path
+          type: string
+          description: |
+            Specify filepath for storing BUSCO dataset downloads. The default is a busco_downloads subdirectory in the current working directory.
+
+    - name: Lineage Dataset Settings
+      arguments:
+        - name: --auto_lineage
+          type: boolean_true
+          description: |
+            Run auto-lineage pipelilne to automatically determine BUSCO lineage dataset that is most closely related to the assembly or gene set being assessed.
+        - name: --auto_lineage_euk
+          type: boolean_true
+          description: |
+            Run auto-placement just on eukaryota tree to find optimal lineage path.
+        - name: --auto_lineage_prok
+          type: boolean_true
+          description: |
+            Run auto_lineage just on prokaryota trees to find optimum lineage path.
+        - name: --datasets_version
+          type: string
+          required: false
+          description: |
+            Specify the version of BUSCO datasets
+          example: odb10
+
+    - name: Augustus Settings
+      arguments:
+        - name: --augustus
+          type: boolean_true
+          description: |
+            Use augustus gene predictor for eukaryote runs.
+        - name: --augustus_parameters
+          type: string
+          required: false
+          description: |
+            Additional parameters to be passed to Augustus (see Augustus documentation: https://github.com/Gaius-Augustus/Augustus/blob/master/docs/RUNNING-AUGUSTUS.md).
+            Parameters should be contained within a single string, without whitespace and seperated by commas.
+          example: "--PARAM1=VALUE1,--PARAM2=VALUE2"
+        - name: --augustus_species
+          type: string
+          required: false
+          description: |
+            Specify the augustus species
+        - name: --long
+          type: boolean_true
+          description: |
+            Optimize Augustus self-training mode. This adds considerably to the run time, but can improve results for some non-model organisms.
+
+    - name: BBTools Settings
+      arguments:
+        - name: --contig_break
+          type: integer
+          default: 10
+          description: |
+            Number of contiguous Ns to signify a break between contigs in BBTools analysis.
+        - name: --limit
+          type: integer
+          default: 3
+          description: |
+            Number of candidate regions (contig or transcript) from the BLAST output to consider per BUSCO.
+            This option is only effective in pipelines using BLAST, i.e. the genome pipeline (see --augustus) or the prokaryota transcriptome pipeline.
+        - name: --scaffold_composition
+          type: boolean_true
+          description: |
+            Writes ACGTN content per scaffold to a file scaffold_composition.txt.
+
+    - name: BLAST Settings
+      arguments:
+        - name: --e_value
+          type: double
+          default: 0.001
+          description: |
+            E-value cutoff for BLAST searches.
+
+    - name: Protein Gene Prediction settings
+      arguments:
+        - name: --miniprot
+          type: boolean_true
+          description: |
+            Use Miniprot gene predictor.
+
+    - name: MetaEuk Settings
+      arguments:
+        - name: --metaeuk_parameters
+          type: string
+          description: |
+            Pass additional arguments to Metaeuk for the first run (see Metaeuk documentation https://github.com/soedinglab/metaeuk).
+            All parameters should be contained within a single string with no white space, with each parameter separated by a comma.
+          example: "--max-overlap=15,--min-exon-aa=15"
+        - name: --metaeuk_rerun_parameters
+          type: string
+          description: |
+            Pass additional arguments to Metaeuk for the second run (see Metaeuk documentation https://github.com/soedinglab/metaeuk).
+            All parameters should be contained within a single string with no white space, with each parameter separated by a comma.
+          example: "--max-overlap=15,--min-exon-aa=15"
+
+  resources:
+    - type: bash_script
+      path: script.sh
+  test_resources:
+    - type: bash_script
+      path: test.sh
+    - type: file
+      path: test_data
+platforms:
+  - type: docker
+    image: quay.io/biocontainers/busco:5.6.1--pyhdfd78af_0
+    setup:
+      - type: docker
+        run: |
+          busco: "$(busco --version 2>&1 | sed -n 's/BUSCO \([0-9.]*\)/\1/p')" > /var/software_versions.txt
+  - type: nextflow

src/busco/help.txt

@@ -0,0 +1,60 @@
+```bash
+busco -h
+```
+
+Welcome to BUSCO 5.6.1: the Benchmarking Universal Single-Copy Ortholog assessment tool.
+For more detailed usage information, please review the README file provided with this distribution and the BUSCO user guide. Visit this page https://gitlab.com/ezlab/busco#how-to-cite-busco to see how to cite BUSCO
+
+optional arguments:
+  -i SEQUENCE_FILE, --in SEQUENCE_FILE
+                        Input sequence file in FASTA format. Can be an assembled genome or transcriptome (DNA), or protein sequences from an annotated gene set. Also possible to use a path to a directory containing multiple input files.
+  -o OUTPUT, --out OUTPUT
+                        Give your analysis run a recognisable short name. Output folders and files will be labelled with this name. The path to the output folder is set with --out_path.
+  -m MODE, --mode MODE  Specify which BUSCO analysis mode to run.
+                        There are three valid modes:
+                        - geno or genome, for genome assemblies (DNA)
+                        - tran or transcriptome, for transcriptome assemblies (DNA)
+                        - prot or proteins, for annotated gene sets (protein)
+  -l LINEAGE, --lineage_dataset LINEAGE
+                        Specify the name of the BUSCO lineage to be used.
+  --augustus            Use augustus gene predictor for eukaryote runs
+  --augustus_parameters --PARAM1=VALUE1,--PARAM2=VALUE2
+                        Pass additional arguments to Augustus. All arguments should be contained within a single string with no white space, with each argument separated by a comma.
+  --augustus_species AUGUSTUS_SPECIES
+                        Specify a species for Augustus training.
+  --auto-lineage        Run auto-lineage to find optimum lineage path
+  --auto-lineage-euk    Run auto-placement just on eukaryote tree to find optimum lineage path
+  --auto-lineage-prok   Run auto-lineage just on non-eukaryote trees to find optimum lineage path
+  -c N, --cpu N         Specify the number (N=integer) of threads/cores to use.
+  --config CONFIG_FILE  Provide a config file
+  --contig_break n      Number of contiguous Ns to signify a break between contigs. Default is n=10.
+  --datasets_version DATASETS_VERSION
+                        Specify the version of BUSCO datasets, e.g. odb10
+  --download [dataset [dataset ...]]
+                        Download dataset. Possible values are a specific dataset name, "all", "prokaryota", "eukaryota", or "virus". If used together with other command line arguments, make sure to place this last.
+  --download_base_url DOWNLOAD_BASE_URL
+                        Set the url to the remote BUSCO dataset location
+  --download_path DOWNLOAD_PATH
+                        Specify local filepath for storing BUSCO dataset downloads
+  -e N, --evalue N      E-value cutoff for BLAST searches. Allowed formats, 0.001 or 1e-03 (Default: 1e-03)
+  -f, --force           Force rewriting of existing files. Must be used when output files with the provided name already exist.
+  -h, --help            Show this help message and exit
+  --limit N             How many candidate regions (contig or transcript) to consider per BUSCO (default: 3)
+  --list-datasets       Print the list of available BUSCO datasets
+  --long                Optimization Augustus self-training mode (Default: Off); adds considerably to the run time, but can improve results for some non-model organisms
+  --metaeuk_parameters "--PARAM1=VALUE1,--PARAM2=VALUE2"
+                        Pass additional arguments to Metaeuk for the first run. All arguments should be contained within a single string with no white space, with each argument separated by a comma.
+  --metaeuk_rerun_parameters "--PARAM1=VALUE1,--PARAM2=VALUE2"
+                        Pass additional arguments to Metaeuk for the second run. All arguments should be contained within a single string with no white space, with each argument separated by a comma.
+  --miniprot            Use miniprot gene predictor
+  --skip_bbtools        Skip BBTools for assembly statistics
+  --offline             To indicate that BUSCO cannot attempt to download files
+  --opt-out-run-stats   Opt out of data collection. Information on the data collected is available in the user guide.
+  --out_path OUTPUT_PATH
+                        Optional location for results folder, excluding results folder name. Default is current working directory.
+  -q, --quiet           Disable the info logs, displays only errors
+  -r, --restart         Continue a run that had already partially completed.
+  --scaffold_composition
+                        Writes ACGTN content per scaffold to a file scaffold_composition.txt
+  --tar                 Compress some subdirectories with many files to save space
+  -v, --version         Show this version and exit

src/busco/script.sh

@@ -0,0 +1,60 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+
+[[ "$par_tar" == "false" ]] && unset par_tar
+[[ "$par_force" == "false" ]] && unset par_force
+[[ "$par_offline" == "false" ]] && unset par_offline
+[[ "$par_opt_out_run_stats" == "false" ]] && unset par_opt_out_run_stats
+[[ "$par_quiet" == "false" ]] && unset par_quiet
+[[ "$par_restart" == "false" ]] && unset par_restart
+[[ "$par_auto_lineage" == "false" ]] && unset par_auto_lineage
+[[ "$par_auto_lineage_euk" == "false" ]] && unset par_auto_lineage_euk
+[[ "$par_auto_lineage_prok" == "false" ]] && unset par_auto_lineage_prok
+[[ "$par_augustus" == "false" ]] && unset par_augustus
+[[ "$par_long" == "false" ]] && unset par_long
+[[ "$par_scaffold_composition" == "false" ]] && unset par_scaffold_composition
+[[ "$par_miniprot" == "false" ]] && unset par_miniprot
+
+if [[ -n "$par_output_prefix" ]]; then 
+    prefix="$par_output_prefix"
+else 
+    prefix="$(basename -- $par_input)"
+fi
+
+busco \
+    --in "$par_input" \
+    --mode "$par_mode" \
+    --out "$prefix" \
+    ${meta_cpus:+--cpu "${meta_cpus}"} \
+    ${par_lineage_dataset:+--lineage_dataset "$par_lineage_dataset"} \
+    ${par_augustus:+--augustus} \
+    ${par_augustus_parameters:+--augustus_parameters "$par_augustus_parameters"} \
+    ${par_augustus_species:+--augustus_species "$par_augustus_species"} \
+    ${par_auto_lineage:+--auto-lineage} \
+    ${par_auto_lineage_euk:+--auto-lineage-euk} \
+    ${par_auto_lineage_prok:+--auto-lineage-prok} \
+    ${par_contig_break:+--contig_break $par_contig_break} \
+    ${par_datasets_version:+--datasets_version "$par_datasets_version"} \
+    ${par_e_value:+--evalue "$par_e_value"} \
+    ${par_force:+--force} \
+    ${par_limit:+--limit "$par_limit"} \
+    ${par_long:+--long} \
+    ${par_metaeuk_parameters:+--metaeuk_parameters "$par_metaeuk_parameters"} \
+    ${par_metaeuk_rerun_parameters:+--metaeuk_rerun_parameters "$par_metaeuk_rerun_parameters"} \
+    ${par_miniprot:+--miniprot} \
+    ${par_offline:+--offline} \
+    ${par_opt_out_run_stats:+--opt-out-run-stats} \
+    ${par_quiet:+--quiet} \
+    ${par_restart:+--restart} \
+    ${par_scaffold_composition:+--scaffold_composition} \
+    ${par_tar:+--tar} \
+    ${par_download_base_url:+--download_base_url "$par_download_base_url"} \
+    ${par_download_path:+--download_path "$par_download_path"} \
+    ${par_download:+--download "$par_download"} 
+
+mkdir $par_output_dir
+mv $prefix/* $par_output_dir
+

src/busco/test.sh

@@ -0,0 +1,29 @@
+test_dir="$meta_resources_dir/test_data"
+
+echo "> Running busco"
+echo "$(busco --version 2>&1 | sed -n 's/BUSCO \([0-9.]*\)/\1/p')"
+
+"$meta_executable" \
+    --input $test_dir/protein.fasta \
+    --mode protein \
+    --lineage_dataset stramenopiles_odb10 \
+    --output_dir output 
+
+echo ">> Checking output"
+[ ! -f "output/short_summary.specific.stramenopiles_odb10.protein.fasta.json" ] && echo "specific_short_summary.json does not exist" && exit 1
+[ ! -f "output/short_summary.specific.stramenopiles_odb10.protein.fasta.txt" ] && echo "specific_short_summary.txt does not exist" && exit 1
+[ ! -f "output/run_stramenopiles_odb10/full_table.tsv" ] && echo "full_table.tsv does not exist" && exit 1
+[ ! -f "output/run_stramenopiles_odb10/missing_busco_list.tsv" ] && echo "missing_busco_list.tsv does not exist" && exit 1
+[ ! -f "output/run_stramenopiles_odb10/short_summary.json" ] && echo "short_summary.json does not exist" && exit 1
+[ ! -f "output/run_stramenopiles_odb10/short_summary.txt" ] && echo "short_summary.txt does not exist" && exit 1
+
+echo ">> Checking if output is empty"
+[ ! -s "output/short_summary.specific.stramenopiles_odb10.protein.fasta.json" ] && echo "specific_short_summary.json is empty" && exit 1
+[ ! -s "output/short_summary.specific.stramenopiles_odb10.protein.fasta.txt" ] && echo "specific_short_summary.txt is empty" && exit 1
+[ ! -s "output/run_stramenopiles_odb10/full_table.tsv" ] && echo "full_table.tsv is empty" && exit 1
+[ ! -s "output/run_stramenopiles_odb10/missing_busco_list.tsv" ] && echo "missing_busco_list.tsv is empty" && exit 1
+[ ! -s "output/run_stramenopiles_odb10/short_summary.json" ] && echo "short_summary.json is empty" && exit 1
+[ ! -s "output/run_stramenopiles_odb10/short_summary.txt" ] && echo "short_summary.txt is empty" && exit 1
+
+
+rm -r output/