Merge pull request #36 from ghga-de/35-raw-vcf-is-not-sorted

35 raw vcf is not sorted
ghga-de · Jun 24, 2024 · 1d9554b · 1d9554b
2 parents a4e5bad + d456009
commit 1d9554b
Show file tree

Hide file tree

Showing 20 changed files with 59 additions and 549 deletions.
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -41,7 +41,4 @@ jobs:
           if [[ $NXF_VER = '' ]]; then sleep 1200; fi
       - name: BASIC Run the basic pipeline  with docker
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker
-      - name: BASIC Run the basic pipeline when --runcontig set to "ALT_HLA" (contigs does not exist in bam)
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --runcontigs "ALT_HLA"
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker
diff --git a/.gitignore b/.gitignore
@@ -11,6 +11,7 @@ __pycache__
 output/
 results/
 result/
+results2/
 results37/
 test.xml
 test_output/
@@ -19,3 +20,4 @@ work/
 testdata_hg37/
 .github/CODEOWNERS-tmp
 bin/vcfparser.pyc
+singularity/
diff --git a/assets/samplesheet_hg38_WGS.csv b/assets/samplesheet_hg38_WGS.csv
@@ -1,3 +1,2 @@
 sample,tumor,tumor_index,control,control_index
-SEQC2_LL1,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/tumor01_SEQC2_LL1_merged.mdup.bam,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/tumor01_SEQC2_LL1_merged.mdup.bam.bai,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/control01_SEQC2_LL1_merged.mdup.bam,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/control01_SEQC2_LL1_merged.mdup.bam.bai
-SEQC2_LL2,/omics/odcf/project/public_data/seqc2/sequencing/whole_genome_sequencing/view-by-pid/SEQC2_IL2/tumor01/paired/merged-alignment/tumor01_SEQC2_IL2_merged.mdup.bam,/omics/odcf/project/public_data/seqc2/sequencing/whole_genome_sequencing/view-by-pid/SEQC2_IL2/tumor01/paired/merged-alignment/tumor01_SEQC2_IL2_merged.mdup.bam.bai,/omics/odcf/project/public_data/seqc2/sequencing/whole_genome_sequencing/view-by-pid/SEQC2_IL2/control01/paired/merged-alignment/control01_SEQC2_IL2_merged.mdup.bam,/omics/odcf/project/public_data/seqc2/sequencing/whole_genome_sequencing/view-by-pid/SEQC2_IL2/control01/paired/merged-alignment/control01_SEQC2_IL2_merged.mdup.bam.bai
+SEQC2_LL1,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/tumor01_SEQC2_LL1_merged.mdup.bam,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/tumor01_SEQC2_LL1_merged.mdup.bam.bai,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/control01_SEQC2_LL1_merged.mdup.bam,/omics/odcf/analysis/OE0526_projects/public_data_analyses/seqc2/sequencing/whole_genome_sequencing/results_per_pid/SEQC2_LL1/alignment/control01_SEQC2_LL1_merged.mdup.bam.bai
diff --git a/conf/modules.config b/conf/modules.config
@@ -64,7 +64,7 @@ process {
             mode: params.publish_dir_mode
         ]
     }
-    withName: FILE_CONCATENATOR {
+    withName: SORT_NONSTANDARD_VCF {
         publishDir = [
             path: {"${params.outdir}/${meta.id}"},
             pattern: "*{.vcf.gz,vcf.gz.tbi}",
@@ -175,12 +175,6 @@ process {
             ]
         ]
     }
-        withName: 'CONVERT_TO_VCF' {
-        publishDir = [
-            path: { "${params.outdir}/test" },
-            enabled: false
-        ]
-    }  
     withName: 'BCFTOOLS_SORT' {
         publishDir = [
             path: { "${params.outdir}/${meta.id}/standard_vcf/" },
@@ -199,7 +193,7 @@ process {
 // Don't publish results for these processes
 //
 process {    
-    withName: 'GREP_SAMPLENAME|ANNOVAR|MUTATION_DISTANCE|CONTEXT_FREQUENCIES|ANNOTATE_VCF|FILTER_BY_CRIT|SNV_RELIABILITY_PIPE|DBSNP_COUNTER|FLAG_BIAS|CONFIDENCE_ANNOTATION' {
+    withName: 'GREP_SAMPLENAME|ANNOVAR|MUTATION_DISTANCE|CONTEXT_FREQUENCIES|ANNOTATE_VCF|FILTER_BY_CRIT|SNV_RELIABILITY_PIPE|DBSNP_COUNTER|FLAG_BIAS|CONFIDENCE_ANNOTATION|CONVERT_TO_VCF|FILE_CONCATENATOR' {
         publishDir = [
             path: { "${params.outdir}/test" },
             enabled: false

diff --git a/modules/local/file_concatenator.nf b/modules/local/file_concatenator.nf
@@ -21,9 +21,9 @@ process FILE_CONCATENATOR {
     def prefix = task.ext.prefix ?: "${meta.id}"
 
     """
-    headeredFileConcatenator.pl $vcfs > snvs_${prefix}_raw.vcf
+    headeredFileConcatenator.pl $vcfs > snvs_${prefix}.vcf
 
-    bgzip snvs_${prefix}_raw.vcf && tabix -p vcf snvs_${prefix}_raw.vcf.gz 
+    bgzip snvs_${prefix}.vcf && tabix -p vcf snvs_${prefix}.vcf.gz 
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/modules/local/seq_context_annotator.nf b/modules/local/seq_context_annotator.nf
@@ -26,11 +26,8 @@ process SEQ_CONTEXT_ANNOTATOR {
     """
     seqContext_annotator.pl fastaFromBed $vcf $fasta 10 | \\
         rawSnvFilter.py --outf=${prefix}.${intervals}.bias.vcf.temp $args
-    
-    (head -n 5000 ${prefix}.${intervals}.bias.vcf.temp | \\
-        grep "#" ; cat ${prefix}.${intervals}.bias.vcf.temp | \\
-        grep -v "#" | \\
-        sort -T . -k1,1V -n -k2,2n ) > ${prefix}.${intervals}.bias.vcf
+
+    awk '/^#/ {print; next} {print | "sort -T . -k1,1V -k2,2n"}' ${prefix}.${intervals}.bias.vcf.temp > ${prefix}.${intervals}.bias.vcf
 
     bcftools stats ${prefix}.${intervals}.bias.vcf > ${prefix}.${intervals}.bias.bcftools_stats.txt
 

diff --git a/modules/local/sort_nonstandard_vcf.nf b/modules/local/sort_nonstandard_vcf.nf
@@ -0,0 +1,33 @@
+process SORT_NONSTANDARD_VCF {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda (params.enable_conda ? "" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://kubran/samtools:v1.9':'kubran/samtools:v1.9' }"
+
+    input:
+    tuple val(meta), path(vcf_gz), path(index)
+
+    output:
+    tuple val(meta), path("*_raw.vcf.gz"),path("*_raw.vcf.gz.tbi")  , emit: output
+    path "versions.yml"                                             , emit: versions
+
+    script: 
+    def args       = task.ext.args ?: ''
+    def prefix     = task.ext.prefix ?: "${meta.id}"
+
+    """
+    zcat $vcf_gz | \
+    awk 'BEGIN {header=1} /^#/ {print; next} {header=0; print | "sort -T . -k1,1V -k2,2n"}' | \
+    bgzip > snvs_${prefix}_raw.vcf.gz
+
+    tabix -p vcf snvs_${prefix}_raw.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        tabix: \$(echo \$(tabix -h 2>&1) | sed 's/^.*Version: //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+}
diff --git a/modules/nf-core/modules/bcftools/mpileup/main.nf b/modules/nf-core/modules/bcftools/mpileup/main.nf
@@ -4,8 +4,7 @@ process BCFTOOLS_MPILEUP {
 
     conda (params.enable_conda ? "bioconda::bcftools=1.9" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/bcftools:1.9--h47928c2_2':
-        'quay.io/biocontainers/bcftools:1.9--h47928c2_2' }"
+        'docker://kubran/bcftools:1.9':'kubran/bcftools:1.9' }"
 
     input:
     tuple val(meta), path(tumor), path(tumor_bai), path(control),  path(control_bai), val(tumorname), val(controlname), val(intervals), path(interval_file)

diff --git a/modules/nf-core/modules/bcftools/reheader/environment.yml b/modules/nf-core/modules/bcftools/reheader/environment.yml
diff --git a/modules/nf-core/modules/bcftools/reheader/main.nf b/modules/nf-core/modules/bcftools/reheader/main.nf
diff --git a/modules/nf-core/modules/bcftools/reheader/meta.yml b/modules/nf-core/modules/bcftools/reheader/meta.yml
diff --git a/modules/nf-core/modules/bcftools/reheader/tests/bcf.config b/modules/nf-core/modules/bcftools/reheader/tests/bcf.config