Merge pull request nf-core#20 from LouisLeNezet/auto_chr_rename

Add auto detection of chr prefix and auto fixing

CHANGELOG.md

@@ -17,6 +17,7 @@ Initial release of nf-core/phaseimpute, created with the [nf-core](https://nf-co
   - correct meta map propagation
   - Test impute and test sim works
 - [#19](https://github.com/nf-core/phaseimpute/pull/19) - Changed reference panel to accept a csv, update modules and subworkflows (glimpse1/2 and shapeit5)
+- [#20](https://github.com/nf-core/phaseimpute/pull/20) - Added automatic detection of vcf contigs for the reference panel and automatic renaming available
 
 ### `Fixed`
 

conf/modules.config

@@ -56,12 +56,12 @@ process {
         ext.prefix = { "${meta.id}_${meta.region}" }
     }
 
-    withName: BCFTOOLS_ANNOTATE {
+    withName: 'NFCORE_PHASEIMPUTE:PHASEIMPUTE:VCF_CHR_CHECK:VCF_CHR_RENAME:BCFTOOLS_ANNOTATE' {
         ext.args = [
             "-Oz",
             "--no-version"
         ].join(' ')
-        ext.prefix = { "${meta.id}_chrDel_${meta.region}" }
+        ext.prefix = { "${meta.id}_chrrename" }
     }
 
     withName: VIEW_VCF_SNPS {

docs/development.md

@@ -2,7 +2,8 @@
 
 ## Features and tasks
 
-- [] Add automatic detection of chromosome name to create a renaming file for the vcf
+- [x] Add automatic detection of chromosome name to create a renaming file for the vcf files
+- [] Add automatic detection of chromosome name to create a renaming file for the bam files
 - [] Make the different tests workflows work
   - [] Simulation
   - [] Validation

modules.json

@@ -48,6 +48,11 @@
                         "git_sha": "de45447d060b8c8b98575bc637a4a575fd0638e1",
                         "installed_by": ["modules"]
                     },
+                    "gawk": {
+                        "branch": "master",
+                        "git_sha": "dc3527855e7358c6d8400828754c0caa5f11698f",
+                        "installed_by": ["modules"]
+                    },
                     "glimpse/chunk": {
                         "branch": "master",
                         "git_sha": "7e56daae390ff896b292ddc70823447683a79936",

modules/local/vcfchrextract/environment.yml

@@ -0,0 +1,7 @@
+name: vcfchrextract
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::bcftools=1.18

modules/local/vcfchrextract/main.nf

@@ -0,0 +1,49 @@
+process VCFCHREXTRACT {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bcftools:1.18--h8b25389_0':
+        'biocontainers/bcftools:1.18--h8b25389_0' }"
+
+    input:
+    tuple val(meta), path(input)
+
+    output:
+    tuple val(meta), path("*.txt"), emit: chr
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    bcftools \\
+        head \\
+        $input \\
+        \| grep -o -E '^##contig=<ID=([^,>]*)' | cut -d'=' -f3 \\
+        > ${prefix}.txt
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$( bcftools --version |& sed '1!d; s/^.*bcftools //' )
+        grep: \$( grep --help |& grep -o -E '[0-9]+\\.[0-9]+\\.[0-9]+' )
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$( bcftools --version |& sed '1!d; s/^.*bcftools //' )
+        grep: \$( grep --help |& grep -o -E '[0-9]+\\.[0-9]+\\.[0-9]+' )
+    END_VERSIONS
+    """
+}

modules/local/vcfchrextract/meta.yml

@@ -0,0 +1,41 @@
+name: vcfchrextract
+description: Extract all contigs name into txt file
+keywords:
+  - bcftools
+  - vcf
+  - head
+  - contig
+tools:
+  - head:
+      description: Extract header from variant calling file.
+      homepage: http://samtools.github.io/bcftools/bcftools.html
+      documentation: https://samtools.github.io/bcftools/bcftools.html#head
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: Query VCF or BCF file, can be either uncompressed or compressed
+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"
+  - chr:
+      type: file
+      description: List of contigs in the VCF file
+      pattern: "*{txt}"
+authors:
+  - "@louislenezet"
+maintainers:
+  - "@louislenezet"

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

@@ -0,0 +1,32 @@
+nextflow_process {
+
+    name "Test Process VCFCHREXTRACT"
+    script "../main.nf"
+    process "VCFCHREXTRACT"
+
+    tag "modules"
+    tag "modules_local"
+    tag "vcfchrextract"
+
+    test("Extract chr from vcf") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+}

modules/local/vcfchrextract/tests/main.nf.test.snap

@@ -0,0 +1,35 @@
+{
+    "Extract chr from vcf": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.txt:md5,3a9ea6d336e113a74d7fdca5e7b623fc"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,7e6d75a47df5ce3a975172dcd47fd247"
+                ],
+                "chr": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.txt:md5,3a9ea6d336e113a74d7fdca5e7b623fc"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,7e6d75a47df5ce3a975172dcd47fd247"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-03-22T15:09:21.585363234"
+    }
+}

modules/local/vcfchrextract/tests/tags.yml

@@ -0,0 +1,2 @@
+vcfchrextract:
+  - "modules/local/vcfchrextract/**"