Adding plasflow module

modules/nf-core/plasflow/main.nf

@@ -0,0 +1,76 @@
+process PLASFLOW {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "bioconda::plasflow=1.1.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/plasflow:1.1.0--py35_0':
+        'biocontainers/plasflow:1.1.0--py35_0' }"
+
+    input:
+    tuple val(meta), path(assembly)
+
+    output:
+    tuple val(meta), path("*.tsv")                  , emit: tsv
+    tuple val(meta), path("*_chromosomes.fasta.gz") , emit: chromosomes
+    tuple val(meta), path("*_plasmids.fasta.gz")    , emit: plasmids
+    tuple val(meta), path("*_unclassified.fasta.gz"), emit: unclassified
+    path "versions.yml"                             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '1.1' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    if [[ "$assembly" == *.gz ]]; then
+        gunzip -c $assembly > ${prefix}.fasta
+        PlasFlow.py \\
+            $args \\
+            --input ${prefix}.fasta \\
+            --output ${prefix}.tsv
+    else
+        PlasFlow.py \\
+            $args \\
+            --input $assembly \\
+            --output ${prefix}.tsv
+    fi
+
+    if [ -f ${prefix}.tsv_chromosomes.fasta ]; then
+        mv ${prefix}.tsv_chromosomes.fasta ${prefix}_chromosomes.fasta
+        gzip -n ${prefix}_chromosomes.fasta
+    fi
+
+    if [ -f ${prefix}.tsv_plasmids.fasta ]; then
+        mv ${prefix}.tsv_plasmids.fasta ${prefix}_plasmids.fasta
+        gzip -n ${prefix}_plasmids.fasta
+    fi
+
+    if [ -f ${prefix}.tsv_unclassified.fasta ]; then
+        mv ${prefix}.tsv_unclassified.fasta ${prefix}_unclassified.fasta
+        gzip -n ${prefix}_unclassified.fasta
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        PlasFlow: $VERSION
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.tsv
+    touch ${prefix}_chromosomes.fasta.gz
+    touch ${prefix}_plasmids.fasta.gz
+    touch ${prefix}_unclassified.fasta.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        PlasFlow: $VERSION
+    END_VERSIONS
+    """
+}

modules/nf-core/plasflow/meta.yml

@@ -0,0 +1,59 @@
+name: "plasflow"
+description: Uses PlasFlow for prediction of plasmid sequences in metagenomic contigs.
+keywords:
+  - plasmid
+  - chromosomes
+  - metagenomes
+  - contigs
+tools:
+  - "PlasFlow":
+      description: |
+        PlasFlow is a set of scripts used for prediction of plasmid sequences in metagenomic contigs. 
+        It relies on the neural network models trained on full genome and plasmid sequences and is able 
+        to differentiate between plasmids and chromosomes with accuracy reaching 96%. It outperforms 
+        other available solutions for plasmids recovery from metagenomes and incorporates the thresholding 
+        which allows for exclusion of incertain predictions.
+      homepage: https://github.com/smaegol/PlasFlow
+      documentation: https://github.com/smaegol/PlasFlow
+      tool_dev_url: https://github.com/smaegol/PlasFlow
+      doi: 10.1093/nar/gkx1321
+      licence: ["GPL v3"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+  - assembly:
+      type: file
+      description: fasta file
+      pattern: "*.{gz,fasta,fa,fna}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+  - tsv:
+      type: file
+      description: file containing classified sequences
+      pattern: "*.tsv"
+  - chromosomes:
+      type: file
+      description: Fasta file containing chromosome sequences
+      pattern: "*_chromosomes.fasta.gz"
+  - plasmids:
+      type: file
+      description: Fasta file containing plasmid sequences
+      pattern: "*_plasmids.fasta.gz"
+  - unclassified:
+      type: file
+      description: Fasta file containing unclassified sequences
+      pattern: "*_unclassified.fasta.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@limrp"

modules/nf-core/samtools/cramsize/main.nf

@@ -0,0 +1,46 @@
+process SAMTOOLS_CRAMSIZE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "bioconda::samtools=1.17"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0':
+        'biocontainers/samtools:1.17--h00cdaf9_0' }"
+
+    input:
+    tuple val(meta), path(cram)
+
+    output:
+    tuple val(meta), path("*.size"), emit: size
+    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"
+    """
+    samtools \\
+        cram-size \\
+        $args \\
+        -o ${prefix}.size \\
+        $cram
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "$meta.id"
+    """
+    touch ${prefix}.size
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """ 
+}

modules/nf-core/samtools/cramsize/meta.yml

@@ -0,0 +1,42 @@
+name: samtools_cramsize
+description: List CRAM Content-ID and Data-Series sizes
+keywords:
+  - cram-size
+  - cram
+  - size
+tools:
+  - samtools:
+      description: |
+        SAMtools is a set of utilities for interacting with and post-processing
+        short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+        These files are generated as output by short read aligners like BWA.
+      homepage: http://www.htslib.org/
+      documentation: http://www.htslib.org/doc/samtools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cram:
+      type: file
+      description: CRAM file
+      pattern: "*.cram"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - size:
+      type: file
+      description: Size information file
+      pattern: "*.size"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@limrp"

tests/config/pytest_modules.yml

@@ -2799,6 +2799,10 @@ pirate:
   - modules/nf-core/pirate/**
   - tests/modules/nf-core/pirate/**
 
+plasflow:
+  - modules/nf-core/plasflow/**
+  - tests/modules/nf-core/plasflow/**
+
 plasmidfinder:
   - modules/nf-core/plasmidfinder/**
   - tests/modules/nf-core/plasmidfinder/**
@@ -3119,6 +3123,10 @@ samtools/coverage:
   - modules/nf-core/samtools/coverage/**
   - tests/modules/nf-core/samtools/coverage/**
 
+samtools/cramsize:
+  - modules/nf-core/samtools/cramsize/**
+  - tests/modules/nf-core/samtools/cramsize/**
+
 samtools/depth:
   - modules/nf-core/samtools/depth/**
   - tests/modules/nf-core/samtools/depth/**
@@ -3868,6 +3876,10 @@ trinity:
   - modules/nf-core/trinity/**
   - tests/modules/nf-core/trinity/**
 
+ublast:
+  - modules/nf-core/ublast/**
+  - tests/modules/nf-core/ublast/**
+
 ucsc/bedclip:
   - modules/nf-core/ucsc/bedclip/**
   - tests/modules/nf-core/ucsc/bedclip/**

tests/modules/nf-core/plasflow/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PLASFLOW } from '../../../../modules/nf-core/plasflow/main.nf'
+
+workflow test_plasflow {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['bacteroides_fragilis']['illumina']['test1_contigs_fa_gz'], checkIfExists: true)
+    ]
+
+    PLASFLOW ( input )
+}

tests/modules/nf-core/plasflow/nextflow.config

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

tests/modules/nf-core/plasflow/test.yml

@@ -0,0 +1,19 @@
+- name: test_plasflow
+  command: nextflow run ./tests/modules/nf-core/plasflow -entry test_plasflow -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/plasflow/nextflow.config
+  tags:
+    - metagenome
+    - chromosome
+    - plasmid
+  files:
+    - path: output/plasflow/test.tsv
+      md5sum: a7c0ee75bca40f7ae5000a120d3f2099
+    - path: output/plasflow/test_chromosomes.fasta.gz
+      contains:
+        - Fasta file containing chromosome sequences
+    - path: output/plasflow/test_plasmids.fasta.gz
+      contains:
+        - Fasta file containing plasmid sequences
+    - path: output/plasflow/test_unclassified.fasta.gz
+      contains:
+        - Fasta file containing unclassified sequences
+    - path: output/plasflow/versions.yml

tests/modules/nf-core/samtools/cramsize/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_CRAMSIZE } from '../../../../../modules/nf-core/samtools/cramsize/main.nf'
+
+workflow test_samtools_cramsize {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true)
+    ]
+
+    SAMTOOLS_CRAMSIZE ( input )
+}

tests/modules/nf-core/samtools/cramsize/nextflow.config

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

tests/modules/nf-core/samtools/cramsize/test.yml

@@ -0,0 +1,8 @@
+- name: samtools cramsize test_samtools_cramsize
+  command: nextflow run ./tests/modules/nf-core/samtools/cramsize -entry test_samtools_cramsize -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/samtools/cramsize/nextflow.config
+  tags:
+    - samtools/cramsize
+  files:
+    - path: output/samtools/test.size
+      md5sum: aff113286a3368bcb9c5b708bdf5f777
+    - path: output/samtools/versions.yml