Created fcs subworkflow

.github/workflows/pytest-workflow.yml

@@ -146,6 +146,8 @@ jobs:
             tags: subworkflows/vcf_annotate_ensemblvep_snpeff
           - profile: "conda"
             tags: subworkflows/vcf_annotate_ensemblvep
+          - profile: "conda"
+            tags: subworkflows/fasta_clean_fcs
           - profile: "conda"
             tags: islandpath
     env:

modules/nf-core/fcs/fcsadaptor/main.nf

@@ -5,7 +5,7 @@ process FCS_FCSADAPTOR {
     // WARN: Version information not provided by tool on CLI. Please update version string below when bumping container versions.
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/releases/0.2.3/fcs-adaptor.0.2.3.sif':
-        'ncbi/fcs-adaptor:0.2.3' }"
+        'docker.io/ncbi/fcs-adaptor:0.2.3' }"
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {

subworkflows/nf-core/fasta_clean_fcs/main.nf

@@ -0,0 +1,29 @@
+include { FCS_FCSADAPTOR  } from '../../../modules/nf-core/fcs/fcsadaptor/main'
+include { FCS_FCSGX       } from '../../../modules/nf-core/fcs/fcsgx/main'
+
+workflow FASTA_CLEAN_FCS {
+
+    take:
+    ch_fasta // channel: [ val(meta), [ fasta ] ]
+    database // value: the db to use
+
+    main:
+    ch_versions = Channel.empty()
+
+    FCS_FCSADAPTOR ( ch_fasta )
+    ch_versions = ch_versions.mix(FCS_FCSADAPTOR.out.versions)
+
+    FCS_FCSGX ( FCS_FCSADAPTOR.out.cleaned_assembly, database )
+    ch_versions = ch_versions.mix(FCS_FCSGX.out.versions)
+
+    emit:
+    fcsadaptor_cleaned_assembly = FCS_FCSADAPTOR.out.cleaned_assembly       // channel: [ val(meta), [ cleaned_assembly ] ]
+    fcsadaptor_report           = FCS_FCSADAPTOR.out.adaptor_report         // channel: [ val(meta), [ adaptor_report ] ]
+    fcsadaptor_log              = FCS_FCSADAPTOR.out.log                    // channel: [ val(meta), [ log ] ]
+    fcsadaptor_pipeline_args    = FCS_FCSADAPTOR.out.pipeline_args          // channel: [ val(meta), [ pipeline_args ] ]
+    fcsadaptor_skipped_trims    = FCS_FCSADAPTOR.out.skipped_trims          // channel: [ val(meta), [ skipped_trims ] ]
+    fcsgx_report                = FCS_FCSGX.out.fcs_gx_report               // channel: [ val(meta), [ fcs_gx_report ] ]
+    fcsgx_taxonomy_report       = FCS_FCSGX.out.taxonomy_report             // channel: [ val(meta), [ taxonomy_report ] ]
+    versions                    = ch_versions                               // channel: [ versions.yml ]
+}
+

subworkflows/nf-core/fasta_clean_fcs/meta.yml

@@ -0,0 +1,61 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json
+name: "fasta_clean_fcs"
+description: Foreign Contamination Screen (FCS) is a tool suite for identifying and removing contaminant sequences in genome assemblies
+keywords:
+  - contamination screening
+  - cleaning
+  - assemblies
+  - fasta
+modules:
+  - fcs/fcsadaptor
+  - fcs/fcsgx
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - assembly:
+      type: file
+      description: assembly fasta file
+      pattern: "*.{fasta,fa}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - fcsadaptor_cleaned_assembly:
+      type: file
+      description: Cleaned assembly in fasta format
+      pattern: "*.{cleaned_sequences.fa.gz}"
+  - fcsadaptor_report:
+      type: file
+      description: Report of identified adaptors
+      pattern: "*.{fcs_adaptor_report.txt}"
+  - fcsadaptor_log:
+      type: file
+      description: Log file
+      pattern: "*.{fcs_adaptor.log}"
+  - fcsadaptor_pipeline_args:
+      type: file
+      description: Run arguments
+      pattern: "*.{pipeline_args.yaml}"
+  - fcsadaptor_skipped_trims:
+      type: file
+      description: Skipped trim information
+      pattern: "*.{skipped_trims.jsonl}"
+  - fcs_gx_report:
+      type: file
+      description: Report containing the contig identifier and recommended action (EXCLUDE, TRIM, FIX, REVIEW)
+      pattern: "*.fcs_gx_report.txt"
+  - fcsgx_taxonomy_report:
+      type: file
+      description: Report containing the contig identifier and mapped contaminant species
+      pattern: "*.taxonomy.rpt"
+authors:
+  - "@scorreard"

tests/config/pytest_modules.yml

@@ -3508,6 +3508,10 @@ subworkflows/fasta_binning_concoct:
   - subworkflows/nf-core/fasta_binning_concoct/**
   - tests/subworkflows/nf-core/fasta_binning_concoct/**
 
+subworkflows/fasta_clean_fcs:
+  - subworkflows/nf-core/fasta_clean_fcs/**
+  - tests/subworkflows/nf-core/fasta_clean_fcs/**
+
 subworkflows/fasta_index_dna:
   - subworkflows/nf-core/fasta_index_dna/**
   - tests/subworkflows/nf-core/fasta_index_dna/**

tests/subworkflows/nf-core/fasta_clean_fcs/main.nf

@@ -0,0 +1,23 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FASTA_CLEAN_FCS } from '../../../../subworkflows/nf-core/fasta_clean_fcs/main.nf'
+
+workflow test_fasta_clean_fcs {
+
+    input = [
+        [ id:'test', single_end:false, taxid:'9606' ], // meta map
+        file(params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true)
+    ]
+
+    database = [
+        file("https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.gxi"),
+        file("https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.gxs"),
+        file("https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.taxa.tsv"),
+        file("https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.meta.jsonl"),
+        file("https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.blast_div.tsv.gz")
+    ]
+
+    FASTA_CLEAN_FCS ( input, database )
+}

tests/subworkflows/nf-core/fasta_clean_fcs/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/subworkflows/nf-core/fasta_clean_fcs/test.yml

@@ -0,0 +1,26 @@
+- name: fasta_clean_fcs test_fasta_clean_fcs
+  command: nextflow run ./tests/subworkflows/nf-core/fasta_clean_fcs -entry test_fasta_clean_fcs -c ./tests/config/nextflow.config
+  tags:
+    - fcs
+    - fcs/fcsadaptor
+    - fcs/fcsgx
+    - subworkflows
+    - subworkflows/fasta_clean_fcs
+  files:
+    - path: output/fcs/out/test.cleaned_sequences.fa.9606.fcs_gx_report.txt
+      contains:
+        - '##[["FCS genome report", 2, 1]'
+    - path: output/fcs/out/test.cleaned_sequences.fa.9606.taxonomy.rpt
+      contains:
+        - '##[["GX taxonomy analysis report", 3, 1]'
+    - path: output/fcs/test.cleaned_sequences.fa.gz
+      md5sum: 2f331e59b352418420a35236091bf93c
+    - path: output/fcs/test.fcs_adaptor.log
+      contains:
+        - "INFO:cwltool:[workflow ] start"
+    - path: output/fcs/test.fcs_adaptor_report.txt
+      md5sum: 27375be4671e01d2d2674ddd1d44414a
+    - path: output/fcs/test.pipeline_args.yaml
+      md5sum: 80effed2a75550a6a861c47f4c30449d
+    - path: output/fcs/test.skipped_trims.jsonl
+      md5sum: d41d8cd98f00b204e9800998ecf8427e