Merge pull request #1611 from nvnieuwk/split-hap.py-into-two-modules

Split hap.py into two parts

modules/happy/happy/main.nf

@@ -1,7 +1,6 @@
-def VERSION_HAP = '0.3.14'
-def VERSION_PRE = '0.3.14'
+def VERSION = '0.3.14'
 
-process HAPPY {
+process HAPPY_HAPPY {
     tag "$meta.id"
     label 'process_medium'
 
@@ -23,22 +22,13 @@ process HAPPY {
 
     script:
     def args = task.ext.args ?: ''
-    def args2 = task.ext.args2 ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
 
     """
-    pre.py \\
-        $args \\
-        -R $bed \\
-        --reference $fasta \\
-        --threads $task.cpus \\
-        $query_vcf \\
-        ${prefix}_preprocessed.vcf.gz
-
     hap.py \\
         $truth_vcf \\
-        ${prefix}_preprocessed.vcf.gz \\
-        $args2 \\
+        $query_vcf \\
+        $args \\
         --reference $fasta \\
         --threads $task.cpus \\
         -R $bed \\
@@ -46,8 +36,7 @@ process HAPPY {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        hap.py: $VERSION_HAP
-        pre.py: $VERSION_PRE
+        hap.py: $VERSION
     END_VERSIONS
     """
 }

modules/happy/happy/meta.yml

@@ -1,4 +1,4 @@
-name: "happy"
+name: "happy_happy"
 description: Hap.py is a tool to compare diploid genotypes at haplotype level. Rather than comparing VCF records row by row, hap.py will generate and match alternate sequences in a superlocus. A superlocus is a small region of the genome (sized between 1 and around 1000 bp) that contains one or more variants.
 keywords:
   - happy
@@ -35,6 +35,10 @@ input:
       type: file
       description: FASTA file of the reference genome
       pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: The index of the reference FASTA
+      pattern: "*.fai"
 
 output:
   - meta:

modules/happy/prepy/main.nf

@@ -0,0 +1,41 @@
+def VERSION = '0.3.14'
+
+process HAPPY_PREPY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::hap.py=0.3.14" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hap.py:0.3.14--py27h5c5a3ab_0':
+        'quay.io/biocontainers/hap.py:0.3.14--py27h5c5a3ab_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(bed)
+    tuple path(fasta), path(fasta_fai)
+
+    output:
+    tuple val(meta), path('*.vcf.gz')  , emit: preprocessed_vcf
+    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}"
+
+    """
+    pre.py \\
+        $args \\
+        -R $bed \\
+        --reference $fasta \\
+        --threads $task.cpus \\
+        $vcf \\
+        ${prefix}.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pre.py: $VERSION
+    END_VERSIONS
+    """
+}

modules/happy/prepy/meta.yml

@@ -0,0 +1,55 @@
+name: "happy_prepy"
+description: Pre.py is a preprocessing tool made to preprocess VCF files for Hap.py
+keywords:
+  - happy
+  - benchmark
+  - haplotype
+tools:
+  - "happy":
+      description: "Haplotype VCF comparison tools"
+      homepage: "https://www.illumina.com/products/by-type/informatics-products/basespace-sequence-hub/apps/hap-py-benchmarking.html"
+      documentation: "https://github.com/Illumina/hap.py"
+      tool_dev_url: "https://github.com/Illumina/hap.py"
+      doi: ""
+      licence: "['BSD-2-clause']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: VCF file to preprocess
+      pattern: "*.{vcf,vcf.gz}"
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - fasta:
+      type: file
+      description: FASTA file of the reference genome
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: The index of the reference FASTA
+      pattern: "*.fai"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: A preprocessed VCF file
+      pattern: "*.vcf.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nvnieuwk"

tests/config/pytest_modules.yml

@@ -891,9 +891,13 @@ hamronization/summarize:
   - modules/hamronization/summarize/**
   - tests/modules/hamronization/summarize/**
 
-happy:
-  - modules/happy/**
-  - tests/modules/happy/**
+happy/happy:
+  - modules/happy/happy/**
+  - tests/modules/happy/happy/**
+
+happy/prepy:
+  - modules/happy/prepy/**
+  - tests/modules/happy/prepy/**
 
 hicap:
   - modules/hicap/**

tests/modules/happy/happy/main.nf

@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { HAPPY } from '../../../modules/happy/main.nf'
+include { HAPPY_HAPPY } from '../../../../modules/happy/happy/main.nf'
 
 workflow test_happy_vcf {
     
@@ -18,7 +18,7 @@ workflow test_happy_vcf {
         file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
     ])
 
-    HAPPY ( input, fasta )
+    HAPPY_HAPPY ( input, fasta )
 }
 
 workflow test_happy_gvcf {
@@ -35,5 +35,5 @@ workflow test_happy_gvcf {
         file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
     ])
 
-    HAPPY ( input, fasta )
+    HAPPY_HAPPY ( input, fasta )
 }

tests/modules/happy/happy/test.yml

@@ -1,7 +1,8 @@
-- name: happy test_happy_vcf
-  command: nextflow run tests/modules/happy -entry test_happy_vcf -c tests/config/nextflow.config
+- name: happy happy test_happy_vcf
+  command: nextflow run tests/modules/happy/happy -entry test_happy_vcf -c tests/config/nextflow.config
   tags:
     - happy
+    - happy/happy
   files:
     - path: output/happy/test.extended.csv
       md5sum: ef79c7c789ef4f146ca2e50dafaf22b3
@@ -9,12 +10,13 @@
     - path: output/happy/test.summary.csv
       md5sum: f8aa5d36d3c48dede2f607fd565894ad
     - path: output/happy/versions.yml
-      md5sum: 2c2b8249f9f52194da7f09076dbb5019
+      md5sum: 82243bf6dbdc71aa63211ee2a89f47f2
 
-- name: happy test_happy_gvcf
-  command: nextflow run tests/modules/happy -entry test_happy_gvcf -c tests/config/nextflow.config
+- name: happy happy test_happy_gvcf
+  command: nextflow run tests/modules/happy/happy -entry test_happy_gvcf -c tests/config/nextflow.config
   tags:
     - happy
+    - happy/happy
   files:
     - path: output/happy/test.extended.csv
       md5sum: 3d5c21b67a259a3f6dcb088d55b86cd3
@@ -22,4 +24,4 @@
     - path: output/happy/test.summary.csv
       md5sum: 03044e9bb5a0c6f0947b7e910fc8a558
     - path: output/happy/versions.yml
-      md5sum: 75331161af9ec046d045ffcba83abddf
+      md5sum: 551fa216952d6f5de78e6e453b92aaab

tests/modules/happy/prepy/main.nf

@@ -0,0 +1,37 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HAPPY_PREPY } from '../../../../modules/happy/prepy/main.nf'
+
+workflow test_happy_prepy_vcf {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_genome21_indels_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)        
+    ]
+
+    fasta = Channel.value([
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ])
+
+    HAPPY_PREPY ( input, fasta )
+}
+
+workflow test_happy_prepy_gvcf {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)        
+    ]
+
+    fasta = Channel.value([
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ])
+
+    HAPPY_PREPY ( input, fasta )
+}

tests/modules/happy/prepy/nextflow.config

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

tests/modules/happy/prepy/test.yml

@@ -0,0 +1,19 @@
+- name: happy prepy test_happy_prepy_vcf
+  command: nextflow run tests/modules/happy/prepy -entry test_happy_prepy_vcf -c tests/config/nextflow.config
+  tags:
+    - happy/prepy
+    - happy
+  files:
+    - path: output/happy/test.vcf.gz
+    - path: output/happy/versions.yml
+      md5sum: 814d20f1f29f23a3d21012748a5d6393
+
+- name: happy prepy test_happy_prepy_gvcf
+  command: nextflow run tests/modules/happy/prepy -entry test_happy_prepy_gvcf -c tests/config/nextflow.config
+  tags:
+    - happy/prepy
+    - happy
+  files:
+    - path: output/happy/test.vcf.gz
+    - path: output/happy/versions.yml
+      md5sum: 970a54de46e68ef6d5228a26eaa4c8e7