Merge pull request #8 from IARCbioinfo/dev

Dev

.circleci/config.yml

@@ -18,14 +18,17 @@ jobs:
 #                - run: cd ~ ; VERSION=3.6.0; wget https://github.com/sylabs/singularity/releases/download/v${VERSION}/singularity-${VERSION}.tar.gz; tar -xzf singularity-${VERSION}.tar.gz; cd singularity; ./mconfig; make -C builddir; sudo make -C builddir install                         
 #                - run: cd ~ ; singularity pull ...
                 - run: cd ~ && git clone https://github.com/iarcbioinfo/data_test.git
-                - run: cd ; nextflow run ~/project/ --help
-                - run: cd ; nextflow run ~/project/ -with-docker iarcbioinfo/strelka2-nf --input_folder ~/data_test/BAM/ --mode germline --output_folder strelka2-germline-results --ref ~/data_test/REF/17.fasta --cpu 2 --mem 4
-                - run: cd ; nextflow run ~/project/ -with-docker iarcbioinfo/strelka2-nf --input_folder ~/data_test/BAM/ --mode germline --output_folder strelka2-germline-exome-results --ref ~/data_test/REF/17.fasta --exome --cpu 2 --mem 4
-                - run: cd ; nextflow run ~/project/ -with-docker iarcbioinfo/strelka2-nf --input_folder ~/data_test/BAM/ --mode germline --output_folder strelka2-germline-rna-results --ref ~/data_test/REF/17.fasta --rna --cpu 2 --mem 4
-                - run: cd ; echo -e 'tumor\tnormal\ndata_test/BAM/test/NA06984_T.bam\tdata_test/BAM/test/NA06984_N.bam' > input.tsv ; nextflow run ~/project/ -with-docker iarcbioinfo/strelka2-nf --tn_pairs input.tsv --mode somatic --output_folder strelka2-somatic-results --ref ~/data_test/REF/17.fasta --cpu 2 --mem 4
-                - run: cd ; nextflow run ~/project/ -with-docker iarcbioinfo/strelka2-nf --tn_pairs input.tsv --mode somatic  --output_folder strelka2-somatic-callable-exome-results --ref ~/data_test/REF/17.fasta --AF --exome --outputCallableRegions --cpu 2 --mem 4 -with-dag dag.html
-                - run: cd ; nextflow run ~/project/ -with-docker iarcbioinfo/strelka2-nf --tn_pairs input.tsv --mode somatic  --output_folder strelka2-somatic-callable-exome-results --ref ~/data_test/REF/17.fasta --AF --exome --outputCallableRegions --cpu 2 --mem 4 -with-dag dag.png -resume
-                - run: cd ; cp ~/dag.* ~/project/.
+                - run: cd ; nextflow run project/ --help
+                - run: cd ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_folder data_test/BAM/ --mode germline --output_folder strelka2-germline-results --ref data_test/REF/17.fasta --cpu 2 --mem 4
+                - run: cd ; echo -e 'sample\tbam\nNA06984\tdata_test/BAM/test/NA06984_N.bam' > input_germline.tsv ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_file input_germline.tsv --mode germline --output_folder strelka2-germline-results-input-file --ref data_test/REF/17.fasta --cpu 2 --mem 4
+                - run: cd ; echo -e 'sample\tbam\tvcf\nNA06984\tdata_test/BAM/test/NA06984_N.bam\tstrelka2-germline-results/VCFs/filtered/NA06984_N.germline_PASS.vcf.gz' > input_germline_GT.tsv ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_file input_germline_GT.tsv --mode germline --output_folder strelka2-germline-results-input-file-GT --ref data_test/REF/17.fasta --cpu 2 --mem 4
+                - run: cd ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_folder data_test/BAM/ --mode germline --output_folder strelka2-germline-exome-results --ref data_test/REF/17.fasta --exome --cpu 2 --mem 4
+                - run: cd ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_folder data_test/BAM/ --mode germline --output_folder strelka2-germline-rna-results --ref data_test/REF/17.fasta --rna --cpu 2 --mem 4
+                - run: cd ; echo -e 'tumor\tnormal\ndata_test/BAM/test/NA06984_T.bam\tdata_test/BAM/test/NA06984_N.bam' > input.tsv ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_file input.tsv --mode somatic --output_folder strelka2-somatic-results --ref data_test/REF/17.fasta --cpu 2 --mem 4
+                - run: cd ; echo -e 'tumor\tnormal\tvcf\ndata_test/BAM/test/NA06984_T.bam\tdata_test/BAM/test/NA06984_N.bam\tstrelka2-somatic-results/VCFs/filtered/NA06984_T.somatic_PASS.vcf.gz' > input_GT.tsv ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_file input_GT.tsv --mode somatic --output_folder strelka2-somatic-results-GT --ref data_test/REF/17.fasta --cpu 2 --mem 4
+                - run: cd ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_file input.tsv --mode somatic  --output_folder strelka2-somatic-callable-exome-results --ref data_test/REF/17.fasta --AF --exome --outputCallableRegions --cpu 2 --mem 4 -with-dag dag.html
+                - run: cd ; nextflow run project/ -with-docker iarcbioinfo/strelka2-nf --input_file input.tsv --mode somatic  --output_folder strelka2-somatic-callable-exome-results --ref data_test/REF/17.fasta --AF --exome --outputCallableRegions --cpu 2 --mem 4 -with-dag dag.png -resume
+                - run: cd ; cp ~/dag.* project/.
                 - add_ssh_keys:
                                 fingerprints:
                                         - "ee:96:12:b3:06:55:ca:68:07:20:cc:77:75:62:04:f1"

Dockerfile

@@ -6,7 +6,7 @@ FROM continuumio/miniconda3:4.7.12
 LABEL base_image="continuumio/miniconda3"
 LABEL version="4.7.12"
 LABEL software="strelka2-nf"
-LABEL software.version="1.0"
+LABEL software.version="1.2"
 LABEL about.summary="Container image containing all requirements for strelka2-nf"
 LABEL about.home="http://github.com/IARCbioinfo/strelka2-nf"
 LABEL about.documentation="http://github.com/IARCbioinfo/strelka2-nf/README.md"

README.md

@@ -14,9 +14,9 @@
  | Type      | Description     |
   |-----------|---------------|
   | --input_folder    | folder with bam files |
-  |--tn_pairs | Tab delimited text file with two columns called normal and tumor (for somatic mode only) |
+  |--input_file | Tab delimited text file with either two columns called normal and tumor (somatic mode) or one column called bam (germline mode); optionally, a column called sample containing sample names to be used for naming the files can be provided and for genotyping (see genotyping mode below) a column called vcf has to be provided |
 
-Note: the file provided to --tn_pairs is where you can define pairs of bam to analyse with strelka. It's a tabular file with 2 columns normal and tumor.
+Note: the file provided to --input_file is where you can define pairs of bam to analyse with strelka in somatic mode. It's a tabular file with 2 columns normal and tumor.
 
 | normal | tumor |
 | ----------- | ---------- |
@@ -58,14 +58,17 @@ Flags are special parameters without value.
 
 ## Usage
 
-mode somatic
-`nextflow run iarcbioinfo/strelka2.nf r v1.1 -profile singularity --mode somatic --ref hg38.fa --tn_pairs pairs.txt --input_folder path/to/bam/ --strelka path/to/strelka/`
-
-mode germline
-`nextflow run iarcbioinfo/strelka2.nf r v1.1 -profile singularity --mode germline --ref hg38.fa --input_folder path/to/bam/ --strelka path/to/strelka/`
+### mode somatic
+`nextflow run iarcbioinfo/strelka2.nf r v1.2 -profile singularity --mode somatic --ref hg38.fa --tn_pairs pairs.txt --input_folder path/to/bam/ --strelka path/to/strelka/`
 
 To run the pipeline without singularity just remove "-profile singularity". Alternatively, one can run the pipeline using a docker container (-profile docker) the conda receipe containing all required dependencies (-profile conda).
 
+### mode germline
+`nextflow run iarcbioinfo/strelka2.nf r v1.2 -profile singularity --mode germline --ref hg38.fa --input_folder path/to/bam/ --strelka path/to/strelka/`
+
+### genotyping
+When using the input_file mode, if a vcf column with the path to a VCF file for each sample containing a list of somatic variant is provided, the pipeline will use the --forcedGT option from strelka that genotypes these positions, and compute a bedfile for these positions so only variants from the VCF will be genotyped. Note that genotyping can be performed both in somatic mode (in which case tumor/normal pairs must be provided) and germline mode (in which case a single bam file must be provided).
+
 ## Output
   | Type      | Description     |
   |-----------|---------------|

bin/getAllelicFraction

@@ -22,6 +22,8 @@ dict<-list( "A"=6, "C"=7, "G"=8, "T"=9 )
 snvs<-snvs[snvs$FILTER=="PASS",]
 
 system(paste0("zcat ",infile,"  | sed '/#CHROM/Q' > ",infile,".header"))
+# add info for COV and AF
+system(paste0("echo \"##FORMAT=<ID=COV,Number=1,Type=Integer,Description=\\\"Coverage\\\">\n##FORMAT=<ID=AF,Number=1,Type=Float,Description=\\\"Allelic fraction\\\">\" >> ",infile,".header"))
 if(nrow(snvs)==0){
 	write.table(snvs, file=paste0( substr( infile, 1, nchar(infile)-7), ".vcf.body"), sep="\t", row.names=F, quote=F)
 	system(paste0("cat ",infile,".header ",substr( infile, 1, nchar(infile)-7), ".vcf.body > ",substr( infile, 1, nchar(infile)-7), ".vcf"))

environment.yml

@@ -7,4 +7,5 @@ dependencies:
   - strelka=2.9.10
   - r-data.table =1.12.8
   - r-tidyr=1.1.1
-  - bcftools=1.10.2
+  - bcftools=1.10.2
+  - bedops=2.4.39

nextflow.config

@@ -9,11 +9,11 @@ profiles {
        	  conda.createTimeout = "200 min" }
   docker { 
     docker.enabled = true 
-    process.container = 'iarcbioinfo/strelka2-nf:v1.1'
+    process.container = 'iarcbioinfo/strelka2-nf:v1.2'
   }
   singularity { 
     singularity.enabled = true 
-    process.container = 'shub://IARCbioinfo/strelka2-nf:v1.1'
+    process.container = 'shub://IARCbioinfo/strelka2-nf:v1.2'
     pullTimeout = "200 min"
   }
 }