Merge pull request #108 from CarsonJM/add-cobra

Added cobra-meta and changed workflow figure

bin/extract_viral_assemblies.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python
+
+import argparse
+import pandas as pd
+from Bio import SeqIO
+import sys
+import gzip
+
+
+def parse_args(args=None):
+    Description = "Extract genomes identified as contained via mash screen, and append to the sample's FASTA assembly."
+    Epilog = "Example usage: python append_screen_hits.py <FILES_IN> <FILE_OUT>"
+
+    parser = argparse.ArgumentParser(description=Description, epilog=Epilog)
+    parser.add_argument(
+        "-v",
+        "--virus_fasta",
+        help="Path to virus FASTA file (gzipped) containing virus sequences.",
+    )
+    parser.add_argument(
+        "-o",
+        "--output",
+        help="Output TSV file containing the names of all viral assemblies.",
+    )
+    return parser.parse_args(args)
+
+
+def extract_viral_assemblies(virus_fasta, output):
+
+    viral_assemblies = []
+    with gzip.open(virus_fasta, "rt") as reference_fasta_gunzip:
+        for record in SeqIO.parse(reference_fasta_gunzip, "fasta"):
+            viral_assemblies.append(record.id)
+
+    out = open(output, "w")
+    for sequence in viral_assemblies:
+        out.write(sequence + "\n")
+
+
+def main(args=None):
+    args = parse_args(args)
+    extract_viral_assemblies(args.virus_fasta, args.output)
+
+
+if __name__ == "__main__":
+    sys.exit(main())

modules.json

@@ -22,7 +22,7 @@
                     },
                     "bowtie2/align": {
                         "branch": "master",
-                        "git_sha": "3c77ca9aac783e76c3614a06db3bfe4fef619bde",
+                        "git_sha": "0fe30831abbc2ed115e46e92330edf38f56edc3d",
                         "installed_by": ["fastq_align_bowtie2"]
                     },
                     "bowtie2/build": {
@@ -46,6 +46,12 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/checkv/endtoend/checkv-endtoend.diff"
                     },
+                    "cobrameta": {
+                        "branch": "master",
+                        "git_sha": "647fb8e703ef352161eac8791ac0468e4727c4f7",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/cobrameta/cobrameta.diff"
+                    },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c",
@@ -158,7 +164,7 @@
                     },
                     "fastq_align_bowtie2": {
                         "branch": "master",
-                        "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa",
+                        "git_sha": "55e7bb6d5279ec21f254bbab0943117cb3d2fc35",
                         "installed_by": ["subworkflows"]
                     },
                     "initialise": {

modules/local/extractviralassemblies/environment.yml

@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - conda-forge::biopython=1.78
+  - conda-forge::pandas=1.3.5

modules/local/extractviralassemblies/main.nf

@@ -0,0 +1,49 @@
+process EXTRACTVIRALASSEMBLIES {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-80c23cbcd32e2891421c54d1899665046feb07ef:77a31e289d22068839533bf21f8c4248ad274b60-0' :
+        'biocontainers/mulled-v2-80c23cbcd32e2891421c54d1899665046feb07ef:77a31e289d22068839533bf21f8c4248ad274b60-0' }"
+
+    input:
+    tuple val(meta), path(virus_fasta_gz)
+
+    output:
+    tuple val(meta), path("${prefix}_viral_assemblies.tsv") , emit: viral_assemblies
+    path "versions.yml"                                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    extract_viral_assemblies.py \\
+        --virus_fasta ${virus_fasta_gz} \\
+        --output ${prefix}_viral_assemblies.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$( python --version | sed 's/Python //' )
+        biopython: \$(echo \$(biopython_version.py 2>&1))
+        pandas: \$(echo \$(pandas_version.py 2>&1))
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_viral_assemblies.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$( python --version | sed 's/Python //' )
+        biopython: \$(echo \$(biopython_version.py 2>&1))
+        pandas: \$(echo \$(pandas_version.py 2>&1))
+    END_VERSIONS
+    """
+}

modules/local/extractviralassemblies/nextflow.config

@@ -0,0 +1,7 @@
+process {
+    withName: EXTRACTVIRALASSEMBLIES {
+        publishDir = [
+            enabled: false
+        ]
+    }
+}

modules/local/extractviralassemblies/tests/main.nf.test

@@ -0,0 +1,61 @@
+nextflow_process {
+
+    name "Test process: EXTRACTVIRALASSEMBLIES"
+    script "../main.nf"
+    process "EXTRACTVIRALASSEMBLIES"
+
+    tag "modules"
+    tag "modules_local"
+    tag "extractviralassemblies"
+
+
+    test("fasta.gz") {
+
+        when {
+            params {
+                outdir   = "$outputDir"
+            }
+            process {
+                """
+                input[0] = [
+                    [ id: 'test' ],
+                        file(params.modules_testdata_base_path + "genomics/prokaryotes/bacteroides_fragilis/illumina/fasta/test1.contigs.fa.gz", checkifExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("fasta.gz - stub") {
+
+        options "-stub"
+
+        when {
+            params {
+                outdir   = "$outputDir"
+            }
+            process {
+                """
+                input[0] = [
+                    [ id: 'test' ],
+                        file(params.modules_testdata_base_path + "genomics/prokaryotes/bacteroides_fragilis/illumina/fasta/test1.contigs.fa.gz", checkifExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}