Merge branch 'master' into busco

modules/cnvpytor/callcnvs/main.nf

@@ -20,7 +20,6 @@ process CNVPYTOR_CALLCNVS {
 
     script:
     def bins = bin_sizes ?: '1000'
-    def prefix = task.ext.prefix ?: "${meta.id}"
     """
     cnvpytor \\
         -root $pytor \\

modules/cnvpytor/view/main.nf

@@ -8,7 +8,7 @@ process CNVPYTOR_VIEW {
         'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
 
     input:
-    tuple val(meta), path(pytor)
+    tuple val(meta), path(pytor_files)
     val bin_sizes
     val output_format
 
@@ -23,17 +23,18 @@ process CNVPYTOR_VIEW {
 
     script:
     def output_suffix = output_format ?: 'vcf'
-    def bins = bin_sizes ?: '1000'
+    def bins   = bin_sizes ?: '1000'
+    def input  = pytor_files.join(" ")
+    def prefix = task.ext.prefix ?: "${meta.id}"
     """
 
     python3 <<CODE
     import cnvpytor,os
-    from pathlib import Path
-    pytor_file = Path("$pytor")
     binsizes = "${bins}".split(" ")
     for binsize in binsizes:
-        app = cnvpytor.Viewer(["$pytor"], params={} )
+        file_list = "${input}".split(" ")
-        outputfile = "{}_{}.{}".format(pytor_file.stem,binsize.strip(),"${output_suffix}")
+        app = cnvpytor.Viewer(file_list, params={} )
+        outputfile = "{}_{}.{}".format("${prefix}",binsize.strip(),"${output_suffix}")
         app.print_filename = outputfile
         app.bin_size = int(binsize)
         app.print_calls_file()
@@ -47,8 +48,9 @@ process CNVPYTOR_VIEW {
 
     stub:
     def output_suffix = output_format ?: 'vcf'
+    def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch ${pytor.baseName}.${output_suffix}
+    touch ${prefix}.${output_suffix}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/cnvpytor/view/meta.yml

@@ -17,9 +17,9 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test' ]
-  - pytor:
+  - pytor_files:
       type: file
-      description: pytor file containing read depth data
+      description: pytor file containing cnv calls. To merge calls from multiple samples use a list of files.
       pattern: "*.{pytor}"
   - bin_sizes:
       type: string

modules/md5sum/main.nf

@@ -0,0 +1,35 @@
+process MD5SUM {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::coreutils=9.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
+        'ubuntu:20.04' }"
+
+    input:
+    tuple val(meta), path(file)
+
+    output:
+    tuple val(meta), path("*.md5"), emit: checksum
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    md5sum \\
+        $args \\
+        ${file} \\
+        > ${file}.md5
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        md5sum: \$(echo \$(md5sum --version 2>&1 | head -n 1| sed 's/^.*) //;' ))
+    END_VERSIONS
+    """
+}

modules/md5sum/meta.yml

@@ -0,0 +1,39 @@
+name: "md5sum"
+description: Create an MD5 (128-bit) checksum
+keywords:
+  - checksum
+tools:
+  - "md5sum":
+      description: Create an MD5 (128-bit) checksum
+      homepage: "https://www.gnu.org"
+      documentation: "https://man7.org/linux/man-pages/man1/md5sum.1.html"
+      licence: GPLv3+
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - file:
+      type: file
+      description: Any file
+      pattern: "*.*"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - checksum:
+      type: file
+      description: File containing checksum
+      pattern: "*.md5"
+
+authors:
+  - "@matthdsm"

modules/shasum/main.nf

@@ -0,0 +1,35 @@
+process SHASUM {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::coreutils=9.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
+        'ubuntu:20.04' }"
+
+    input:
+    tuple val(meta), path(file)
+
+    output:
+    tuple val(meta), path("*.sha256"), emit: checksum
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    sha256sum \\
+        $args \\
+        ${file} \\
+        > ${file}.sha256
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sha256sum: \$(echo \$(sha256sum --version 2>&1 | head -n 1| sed 's/^.*) //;' ))
+    END_VERSIONS
+    """
+}

modules/shasum/meta.yml

@@ -0,0 +1,40 @@
+name: "shasum"
+description: Print SHA256 (256-bit) checksums.
+keywords:
+  - checksum
+  - sha256
+tools:
+  - "md5sum":
+      description: Create an SHA256 (256-bit) checksum.
+      homepage: "https://www.gnu.org"
+      documentation: "https://linux.die.net/man/1/shasum"
+      licence: GPLv3+
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - file:
+      type: file
+      description: Any file
+      pattern: "*.*"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - checksum:
+      type: file
+      description: File containing checksum
+      pattern: "*.sha256"
+
+authors:
+  - "@matthdsm"

modules/svdb/merge/main.nf

@@ -2,10 +2,10 @@ process SVDB_MERGE {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::svdb=2.6.0" : null)
+    conda (params.enable_conda ? "bioconda::svdb=2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/svdb:2.6.0--py39h5371cbf_0':
+        'https://depot.galaxyproject.org/singularity/svdb:2.6.1--py39h5371cbf_0':
-        'quay.io/biocontainers/svdb:2.6.0--py39h5371cbf_0' }"
+        'quay.io/biocontainers/svdb:2.6.1--py39h5371cbf_0' }"
 
     input:
     tuple val(meta), path(vcfs)

modules/svdb/query/main.nf

@@ -2,10 +2,10 @@ process SVDB_QUERY {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::svdb=2.6.0" : null)
+    conda (params.enable_conda ? "bioconda::svdb=2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/svdb:2.6.0--py39h5371cbf_0':
+        'https://depot.galaxyproject.org/singularity/svdb:2.6.1--py39h5371cbf_0':
-        'quay.io/biocontainers/svdb:2.6.0--py39h5371cbf_0' }"
+        'quay.io/biocontainers/svdb:2.6.1--py39h5371cbf_0' }"
 
     input:
     tuple val(meta), path(vcf)

tests/config/pytest_modules.yml

@@ -1062,10 +1062,6 @@ krona/kronadb:
   - modules/krona/kronadb/**
   - tests/modules/krona/kronadb/**
 
-krona/ktupdatetaxonomy:
-  - modules/krona/ktupdatetaxonomy/**
-  - tests/modules/krona/ktupdatetaxonomy/**
-
 krona/ktimporttaxonomy:
   - modules/krona/ktimporttaxonomy/**
   - tests/modules/krona/ktimporttaxonomy/**
@@ -1074,6 +1070,10 @@ krona/ktimporttext:
   - modules/krona/ktimporttext/**
   - tests/modules/krona/ktimporttext/**
 
+krona/ktupdatetaxonomy:
+  - modules/krona/ktupdatetaxonomy/**
+  - tests/modules/krona/ktupdatetaxonomy/**
+
 last/dotplot:
   - modules/last/dotplot/**
   - tests/modules/last/dotplot/**
@@ -1194,6 +1194,10 @@ maxbin2:
   - modules/maxbin2/**
   - tests/modules/maxbin2/**
 
+md5sum:
+  - modules/md5sum/**
+  - tests/modules/md5sum/**
+
 medaka:
   - modules/medaka/**
   - tests/modules/medaka/**
@@ -1739,6 +1743,10 @@ seqwish/induce:
   - modules/seqwish/induce/**
   - tests/modules/seqwish/induce/**
 
+shasum:
+  - modules/shasum/**
+  - tests/modules/shasum/**
+
 shigatyper:
   - modules/shigatyper/**
   - tests/modules/shigatyper/**

tests/modules/cnvpytor/view/main.nf

@@ -8,7 +8,7 @@ workflow test_cnvpytor_view {
 
     input = [
         [ id:'test'], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)
+        [file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)]
     ]
 
     bin_sizes = "10000 100000"
@@ -20,7 +20,7 @@ workflow test_cnvpytor_view_tsvout {
 
     input = [
         [ id:'test'], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)
+        [file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)]
     ]
 
     output_suffix = "tsv"
@@ -32,7 +32,7 @@ workflow test_cnvpytor_view_stub {
 
     input = [
         [ id:'test'], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)
+        [file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)]
     ]
 
     bin_sizes = []

tests/modules/md5sum/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MD5SUM } from '../../../modules/md5sum/main.nf'
+
+workflow test_md5sum {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    MD5SUM ( input )
+}

tests/modules/md5sum/nextflow.config

@@ -0,0 +1,3 @@
+process {
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+}

tests/modules/md5sum/test.yml

@@ -0,0 +1,8 @@
+- name: md5sum test_md5sum
+  command: nextflow run tests/modules/md5sum -entry test_md5sum -c tests/config/nextflow.config
+  tags:
+    - md5sum
+  files:
+    - path: output/md5sum/test.paired_end.bam.md5
+      md5sum: 1163095be8fdfb2acb3cc6c027389c4b
+    - path: output/md5sum/versions.yml

tests/modules/shasum/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SHASUM } from '../../../modules/shasum/main.nf'
+
+workflow test_shasum {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    SHASUM ( input )
+}

tests/modules/shasum/nextflow.config

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

tests/modules/shasum/test.yml

@@ -0,0 +1,8 @@
+- name: shasum test_shasum
+  command: nextflow run tests/modules/shasum -entry test_shasum -c tests/config/nextflow.config
+  tags:
+    - shasum
+  files:
+    - path: output/shasum/test.paired_end.bam.sha256
+      md5sum: 138a19e100f09fc975ea1b717da9b6dd
+    - path: output/shasum/versions.yml