updating readme, fixing genotypes, adding annovar

README.md

@@ -1,43 +1,73 @@
-# somatic_point_mutations
-call somatic point mutations from tumor/normal pairs
+# Somatic Point Mutations
 
-## nextflow 
-```
-nextflow run digenoma-lab/somatic_point_mutations -r v1.0 --tn test.csv -params-file strelka-params.yml -profile kutral
-```
+This repository provides a Nextflow pipeline for calling somatic point mutations from tumor/normal pairs using Whole Genome Sequencing (WGS) or Exome data.
+
+## Getting Started
 
-### Tumor/Normal file
+### Running the Pipeline
 
-CSV file indicating the paths to CRAM or BAM files, including index and alternative manta_indel VCFs files.
+To run the pipeline, use the following command:
+
+```sh
+nextflow run digenoma-lab/somatic_point_mutations -r v1.1 --tn test.csv -params-file strelka-params.yml -profile kutral
 ```
+
+### Input File: Tumor/Normal Pairs
+
+Prepare a CSV file indicating the paths to CRAM or BAM files, including index and optional manta_indel VCF files. The CSV file should follow this format:
+
+```csv
 sampleId,normal,normal_index,tumor,tumor_index,manta_indel,manta_indel_index
 A,A.cram,A.cram.crai,AT.cram,AT.cram.crai,,
 B,B.cram,B.cram.crai,BT.cram,BT.cram.crai,,
 C,C.cram,C.cram.crai,CT.cram,CT.cram.crai,,
 D,D.cram,D.cram.crai,DT.cram,DT.cram.crai,DT.manta.vcf.gz,DT.manta.vcf.gz.tbi
 ```
 
-### Available Options
+## Pipeline Options
 
+The `somatic_point_mutations` pipeline has several required and optional arguments.
+
+### Required Arguments
+
+- `--tn`: CSV file with tumor/normal pairs.
+- `--fasta`: Reference genome file in FASTA format.
+- `--fai`: Reference genome index file in FAI format.
+
+### Optional Arguments
+
+- `--outdir`: Directory for Nextflow results. Default: `./results`.
+- `--exome`: Set if the data is Exome rather than WGS. Default: `false`.
+- `--target_bed`: Target regions for Strelka in BED format for hg38. Default: `/somatic_point_mutations/auxfiles/hg38.bed.gz`.
+- `--target_bed_index`: Index for target BED regions. Default: `/somatic_point_mutations/auxfiles/hg38.bed.gz.tbi`.
+
+### Annovar Options
+
+- `--annovar_bin`: Path to `annovar_table.pl` executable. Default: `/annovar/annovar/table_annovar.pl`.
+- `--annovar_bd`: Path to Annovar database for hg38. Default: `/databases/annovar/hg38`.
+- `--annovar_protocol`: Databases included in Annovar analysis. Default: `ensGene,clinvar_20220320,revel,dbnsfp42c,gnomad30_genome,avsnp150,icgc28`.
+- `--annovar_operation`: Operations according to Annovar selected databases. Default: `g,f,f,f,f,f,f`.
+
+## Example Usage
+
+```sh
+nextflow run digenoma-lab/somatic_point_mutations -r v1.1 \
+  --tn test.csv \
+  --fasta /path/to/reference.fasta \
+  --fai /path/to/reference.fasta.fai \
+  --outdir ./results \
+  --exome true \
+  --target_bed /path/to/target.bed.gz \
+  --target_bed_index /path/to/target.bed.gz.tbi \
+  --annovar_bin /path/to/annovar/table_annovar.pl \
+  --annovar_bd /path/to/annovar/hg38 \
+  --annovar_protocol ensGene,clinvar_20220320,revel,dbnsfp42c,gnomad30_genome,avsnp150,icgc28 \
+  --annovar_operation g,f,f,f,f,f,f
+   -profile kutral
 ```
-somatic_point_mutations.nf: somatic point mutation caller pipeline.
-Required arguments:
-  --tn  tumor normal pairs
-                [default: false]
-  --fasta  reference file in fasta format
-                [default: false]
-  --fai  reference index file in fai format
-                [default: false]
-
-Optional arguments:
-  --outdir       The NextFlow result directory.
-                [default: ./results]
-  --exome       Data is Exome rather than WGS.
-                [default: false]
-  --target_bed  target region for strelka in bed format hg38
-                [default: /somatic_point_mutations/auxfiles/hg38.bed.gz]
-  --target_bed_index  bed index for target regions
-                [default: /somatic_point_mutations/auxfiles/hg38.bed.gz.tbi]
-```
+
+## Support
+
+If you encounter any issues or have questions, please open an issue on the [GitHub repository](https://github.com/digenoma-lab/somatic_point_mutations).
 
 

auxfiles/fixGT.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+for vcf in "$@"
+do
+
+out=${vcf/vcf.gz/vcf}
+
+first_format_num=$(zgrep -n -m 1 '##FORMAT' "$vcf" | cut -d : -f 1)
+zcat "$vcf" | sed "$first_format_num"'i##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">' > "$out"
+sed -ri 's|(DP:)|GT:\1|' "$out"
+sed -ri 's|(:TU\t)|\10/0:|g' "$out"
+sed -ri 's|(:TU\t[^\t]*\t)|\10/1:|g' "$out"
+sed -ri 's|(:BCN50\t)|\10/0:|g' "$out"
+sed -ri 's|(:BCN50\t[^\t]*\t)|\10/1:|g' "$out"
+gzip -f $out
+
+done

main.nf

@@ -30,7 +30,7 @@ def help_function() {
              | --annovar_protocol databases included in annovar analysis
              |              [default: ${params.annovar_protocol}]
              | --annovar_operation operation according to annovar selected databases
-             |              [default: ${params.annovar_operations}]
+             |              [default: ${params.annovar_operation}]
              |                """.stripMargin()
     // Print the help with the stripped margin and exit
     println(help)
@@ -94,6 +94,8 @@ process STRELKA_SOMATIC {
     mv strelka/results/variants/somatic.indels.vcf.gz.tbi ${prefix}.somatic_indels.vcf.gz.tbi
     mv strelka/results/variants/somatic.snvs.vcf.gz       ${prefix}.somatic_snvs.vcf.gz
     mv strelka/results/variants/somatic.snvs.vcf.gz.tbi   ${prefix}.somatic_snvs.vcf.gz.tbi
+    # we add the genotype information to strelka files
+    sh ${baseDir}/auxfiles/fixGT.sh *.vcf.gz 
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -143,15 +145,15 @@ process ANNOVAR{
 
   script:
    """
-    ${params.annovar_bin}/table_annovar.pl ${variants} \\
-    ${params.annovar_bd}/hg38 -out ${meta}_annovar  --thread  $task.cpus \\
+    ${params.annovar_bin} ${variants} \\
+    ${params.annovar_bd} -out ${meta}_annovar  --thread  $task.cpus \\
     -nastring . -vcfinput --buildver hg38  --codingarg -includesnp --remove --onetranscript \\
     -protocol ${params.annovar_protocol} -operation ${params.annovar_operation} 
     """
   stub:
     """
-   echo ${params.annovar_bin}/table_annovar.pl ${variants} \\
-        ${params.annovar_bd}/hg38 -out ${meta}_annovar --thread  $task.cpus \\
+   echo ${params.annovar_bin} ${variants} \\
+        ${params.annovar_bd} -out ${meta}_annovar --thread  $task.cpus \\
     -nastring . -vcfinput --buildver hg38  --codingarg -includesnp --remove --onetranscript \\
     -protocol ${params.annovar_protocol} -operation ${params.annovar_operation} 
     touch ${meta}_annovar_multianno.vcf ${meta}_annovar_multianno.txt

nextflow.config

@@ -53,6 +53,7 @@ shell = ['/bin/bash', '-euo', 'pipefail']
 // default run resource parameters 
 process {
 
+errorStrategy="retry"
 withName: 'STRELKA_SOMATIC' {
 	cpus    = 8
 	memory  = 20.GB