TOPAS/GenConS

modules/nf-core/topas/gencons/main.nf

@@ -0,0 +1,57 @@
+process TOPAS_GENCONS {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "bioconda::topas=1.0.1"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/topas:1.0.1--hdfd78af_1':
+        'biocontainers/topas:1.0.1--hdfd78af_1' }"
+
+    input:
+    tuple val(meta), path(vcf)
+    tuple val(meta2), path(vcf_indels)
+    tuple val(meta3), path(reference)
+    tuple val(meta4), path(fai)
+    val(vcf_output)
+
+    output:
+    tuple val(meta), path("*.fasta.gz"), emit: fasta
+    tuple val(meta), path("*.vcf.gz")  , emit: vcf     , optional: true
+    tuple val(meta), path("*.ccf")     , emit: ccf
+    tuple val(meta), path("*.log")     , emit: log
+    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 optionalvcfindels = vcf_indels ? "-indels ${vcf_indels}" : ''
+    def optionalfai = fai ? "-fai ${fai}" : ''
+    def vcfoutput = vcf_output ? "-vcf_out ${prefix}.vcf" : ""
+    def VERSION = '1.0.1' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+
+    """
+
+    topas \\
+        GenConS \\
+        $args \\
+        -o ${prefix}.fasta \\
+        -snps $vcf \\
+        $optionalvcfindels \\
+        $vcfoutput \\
+        -ref $reference
+
+    gzip -n ${prefix}.fasta
+
+    if [[ -f ${prefix}.vcf ]];then
+        gzip -n ${prefix}.vcf
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        topas: $VERSION
+    END_VERSIONS
+    """
+}

modules/nf-core/topas/gencons/meta.yml

@@ -0,0 +1,80 @@
+name: "topas_gencons"
+description: Create fasta consensus with TOPAS toolkit with options to penalize substitutions for typical DNA damage present in ancient DNA
+keywords:
+  - consensus
+  - fasta
+  - ancient DNA
+tools:
+  - "topas":
+      description: "This toolkit allows the efficient manipulation of sequence data in various ways. It is organized into modules: The FASTA processing modules, the FASTQ processing modules, the GFF processing modules and the VCF processing modules."
+      homepage: "https://github.com/subwaystation/TOPAS"
+      documentation: "https://github.com/subwaystation/TOPAS/wiki/Overview-Modules"
+      tool_dev_url: "https://github.com/subwaystation/TOPAS"
+      doi: "10.1038/s41598-017-17723-1"
+      licence: "['CC-BY']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - vcf:
+      type: file
+      description: Gzipped compressed vcf file generated with GATK UnifiedGenotyper containing the called snps
+      pattern: "*.vcf.gz"
+
+  - vcf_indels:
+      type: file
+      description: Optional gzipped compressed vcf file generated with GATK UnifiedGenotyper containing the called indels
+      pattern: "*.vcf.gz"
+
+  - reference:
+      type: file
+      description: Fasta file of reference genome
+      pattern: "*.fasta"
+
+  - fai:
+      type: file
+      description: Optional index for the fasta file of reference genome
+      pattern: "*.fai"
+
+  - vcf_output:
+      type: boolean
+      description: Boolean value to indicate if a compressed vcf file with the consensus calls included as SNPs should be produced
+
+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"
+
+  - fasta:
+      type: file
+      description: Gzipped consensus fasta file with bases under threshold replaced with Ns
+      pattern: "*.fasta.gz"
+
+  - vcf:
+      type: file
+      description: Gzipped vcf file with updated calls for the SNPs used in the consensus generation and for bases under threshold replaced with Ns
+      pattern: "*.vcf.gz"
+
+  - ccf:
+      type: file
+      description: Statistics file containing information about the consensus calls in the fasta file
+      pattern: "*.ccf"
+
+  - log:
+      type: file
+      description: Log file
+      pattern: "*.log"
+
+authors:
+  - "@aidaanva"

tests/config/pytest_modules.yml

@@ -3988,6 +3988,10 @@ tiddit/sv:
   - modules/nf-core/tiddit/sv/**
   - tests/modules/nf-core/tiddit/sv/**
 
+topas/gencons:
+  - modules/nf-core/topas/gencons/**
+  - tests/modules/nf-core/topas/gencons/**
+
 transdecoder/longorf:
   - modules/nf-core/transdecoder/longorf/**
   - tests/modules/nf-core/transdecoder/longorf/**

tests/modules/nf-core/topas/gencons/main.nf

@@ -0,0 +1,102 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK_UNIFIEDGENOTYPER as GATK_UNIFIEDGENOTYPERSNPS } from '../../../../modules/nf-core/gatk/unifiedgenotyper/main.nf'
+include { GATK_UNIFIEDGENOTYPER as GATK_UNIFIEDGENOTYPERINDELS } from '../../../../modules/nf-core/gatk/unifiedgenotyper/main.nf'
+include { TOPAS_GENCONS         } from '../../../../../modules/nf-core/topas/gencons/main.nf'
+
+workflow test_topas_gencons {
+
+    input_gatk = [ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                ]
+    fasta = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    fai = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ]
+    dict = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+    ]
+
+    GATK_UNIFIEDGENOTYPERSNPS ( input_gatk, fasta, fai, dict, [[],[]], [[],[]], [[],[]], [[],[]])
+
+    gencons_vcf = GATK_UNIFIEDGENOTYPERSNPS.out.vcf
+    gencons_vcf_indels = [[],[]]
+    gencons_fasta =[ [ id:'test' ], // meta map
+                     file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                    ]
+    gencons_vcf_output = false
+
+    TOPAS_GENCONS ( gencons_vcf, gencons_vcf_indels, gencons_fasta, [[],[]], gencons_vcf_output)
+}
+
+workflow test_topas_gencons_fai {
+
+    input_gatk = [ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                ]
+    fasta = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    fai = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ]
+    dict = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+    ]
+
+    GATK_UNIFIEDGENOTYPERSNPS ( input_gatk, fasta, fai, dict, [[],[]], [[],[]], [[],[]], [[],[]])
+
+    gencons_vcf = GATK_UNIFIEDGENOTYPERSNPS.out.vcf
+    gencons_vcf_indels = [[],[]]
+    gencons_fasta =[ [ id:'test' ], // meta map
+                     file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                    ]
+    gencons_vcf_output = false
+
+    TOPAS_GENCONS ( gencons_vcf, gencons_vcf_indels, gencons_fasta, fai, gencons_vcf_output)
+}
+
+workflow test_topas_gencons_indels {
+
+    input_gatk = [ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                ]
+    fasta = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    fai = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ]
+    dict = [
+        [id: 'test'],
+        file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+    ]
+
+    GATK_UNIFIEDGENOTYPERSNPS ( input_gatk, fasta, fai, dict, [[],[]], [[],[]], [[],[]], [[],[]])
+    GATK_UNIFIEDGENOTYPERINDELS ( input_gatk, fasta, fai, dict, [[],[]], [[],[]], [[],[]], [[],[]])
+
+
+    gencons_vcf = GATK_UNIFIEDGENOTYPERSNPS.out.vcf
+    gencons_vcf_indels = GATK_UNIFIEDGENOTYPERINDELS.out.vcf
+    gencons_fasta =[ [ id:'test' ], // meta map
+                     file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                    ]
+    gencons_vcf_output = true
+
+    TOPAS_GENCONS ( gencons_vcf, gencons_vcf_indels, gencons_fasta, [[],[]], gencons_vcf_output)
+}

tests/modules/nf-core/topas/gencons/nextflow.config

@@ -0,0 +1,15 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: GATK_UNIFIEDGENOTYPERSNPS {
+        ext.args = "--genotype_likelihoods_model SNP -stand_call_conf 30 --sample_ploidy 2 -dcov 250 --output_mode EMIT_ALL_SITES"
+        ext.prefix = { "${meta.id}_snps" }
+    }
+
+    withName: GATK_UNIFIEDGENOTYPERINDELS {
+        ext.args = "--genotype_likelihoods_model INDEL -stand_call_conf 30 --sample_ploidy 2 -dcov 250 --output_mode EMIT_ALL_SITES"
+        ext.prefix = { "${meta.id}_indels" }
+    }
+
+}

tests/modules/nf-core/topas/gencons/test.yml

@@ -0,0 +1,54 @@
+- name: topas gencons test_topas_gencons
+  command: nextflow run ./tests/modules/nf-core/topas/gencons -entry test_topas_gencons -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/topas/gencons/nextflow.config
+  tags:
+    - topas/gencons
+    - topas
+  files:
+    - path: output/gatk/test_snps.vcf.gz
+    - path: output/gatk/versions.yml
+    - path: output/topas/test.fasta.ccf
+      md5sum: 794d4231ee35302a9816df2c1f595041
+    - path: output/topas/test.fasta.gz
+      md5sum: 1f219a39d28eed85be8a48cb167d5879
+    - path: output/topas/test.fasta.log
+      contains:
+        - "Parameters chosen: "
+    - path: output/topas/versions.yml
+
+- name: topas gencons test_topas_gencons_fai
+  command: nextflow run ./tests/modules/nf-core/topas/gencons -entry test_topas_gencons_fai -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/topas/gencons/nextflow.config
+  tags:
+    - topas/gencons
+    - topas
+  files:
+    - path: output/gatk/test_snps.vcf.gz
+    - path: output/gatk/versions.yml
+    - path: output/topas/test.fasta.ccf
+      md5sum: 794d4231ee35302a9816df2c1f595041
+    - path: output/topas/test.fasta.gz
+      md5sum: 1f219a39d28eed85be8a48cb167d5879
+    - path: output/topas/test.fasta.log
+      contains:
+        - "Parameters chosen: "
+    - path: output/topas/versions.yml
+
+- name: topas gencons test_topas_gencons_indels
+  command: nextflow run ./tests/modules/nf-core/topas/gencons -entry test_topas_gencons_indels -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/topas/gencons/nextflow.config
+  tags:
+    - topas/gencons
+    - topas
+  files:
+    - path: output/gatk/test_indels.vcf.gz
+    - path: output/gatk/test_snps.vcf.gz
+    - path: output/gatk/versions.yml
+    - path: output/topas/test.fasta.ccf
+      md5sum: f7337d6e701ab7c5b3c8654742e5116a
+    - path: output/topas/test.fasta.gz
+      md5sum: 1f219a39d28eed85be8a48cb167d5879
+    - path: output/topas/test.fasta.log
+      contains:
+        - "Parameters chosen: "
+    - path: output/topas/test.vcf.gz
+      contains:
+        - "##FILTER="
+    - path: output/topas/versions.yml