wes_somatic_pipeline

CONTRIBUTING.md

@@ -0,0 +1 @@
+This code is written under supervision of Dr. Pierre Khoueiry

README.md

@@ -0,0 +1,21 @@
+WES Somatic scatter-gather pipeline
+
+This pipeline runs by just invoking run.sh <projectDirectory> in command line.
+the <projectDir> should have the following structure:
+
+    1- "fastq" directory which contains FASTQ files. FASTQ files should have the following naming style:
+        sampleName_R1.fastq.gz and sampleName_R2.fastq.gz
+
+    2- "lists" directory which contains two files:
+        - "fastq_list.txt"
+        - "hg_38_intervals.bed"
+
+            "fastq_list.txt" is a tab separated file and should contain all samples required for analysis:
+                sampleName1    sampleName1_R1.fastq.gz    sampleName1_R2.fastq.gz
+                sampleName2    sampleName2_R1.fastq.gz    sampleName2_R2.fastq.gz
+
+            "hg_38_intervals.bed" is an intervals file in BED format.
+
+        Finally, we have to specify the path of both "fastq_list.txt" and "hg_38_intervals.bed" in the JSON file
+
+We can invoke each WDL and shell scripts separately.

bwa_and_gatk_wdl.json

@@ -0,0 +1,57 @@
+{
+    "#splitting_bed_file":"splitting using gatk tools SplitIntervals",
+    "splitting.gatk":"/home/pk4/software/gatk-4.0.11.0/gatk-package-4.0.11.0-local.jar",
+    "splitting.bed":"/home/pk4/project/test_new_1/lists/intervals_lifted_hg19_to_hg38.bed",
+    "splitting.scatter_count":10,
+    "splitting.refFasta":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa",
+    "splitting.refIndex":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.fai",
+    "splitting.refDict":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.dict",
+    "splitting.refAMB":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.amb",
+    "splitting.refANN":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.ann",
+    "splitting.refBWT":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.bwt",
+    "splitting.refPAC":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.pac",
+    "splitting.refSA":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.sa",
+    "#-----------------------":"-------------------------------------------------------------",
+    "#data_processing":"Quality Check, adapter trimming, alignment, metrics, mark dup and baserecalibration",
+    "data_processing.SCATTER_CALLING_INTERVALS_LIST":"/home/pk4/project/test_new_1/lists/intervals.txt",
+    "data_processing.FASTQ_LIST":"/home/pk4/project/test_new_1/lists/fastq_list.txt",
+    "data_processing.fastqc":"/usr/bin/fastqc",
+    "data_processing.cutadapt":"/usr/local/bin/cutadapt",
+    "data_processing.bwa":"/home/pk4/software/bwa-0.7.16a/bwa",
+    "data_processing.samtools":"/home/pk4/software/samtools-1.4.1/samtools",
+    "data_processing.gatk":"/home/pk4/software/gatk-4.0.11.0/gatk-package-4.0.11.0-local.jar",
+    "data_processing.refFasta":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa",
+    "data_processing.refIndex":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.fai",
+    "data_processing.refDict":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.dict",
+    "data_processing.refAMB":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.amb",
+    "data_processing.refANN":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.ann",
+    "data_processing.refBWT":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.bwt",
+    "data_processing.refPAC":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.pac",
+    "data_processing.refSA":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.sa",
+    "data_processing.dbsnp38":"/home/pk4/resources/hg38bundle/Homo_sapiens_assembly38.dbsnp138.vcf.gz",
+    "data_processing.dbsnp38_index":"/home/pk4/resources/hg38bundle/Homo_sapiens_assembly38.dbsnp138.vcf.gz.tbi",
+    "data_processing.phase1snps":"/home/pk4/resources/hg38bundle/1000G_phase1.snps.high_confidence.hg38.vcf.gz",
+    "data_processing.phase1snps_index":"/home/pk4/resources/hg38bundle/1000G_phase1.snps.high_confidence.hg38.vcf.gz.tbi",
+    "data_processing.mills":"/home/pk4/resources/hg38bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
+    "data_processing.mills_index":"/home/pk4/resources/hg38bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi",
+    "#--------------------":"----------------------------------------------------------------",
+    "#Mutect2_variant_calling":"Mutect2 - gatk",
+    "mutect_variant_calling.BAM_LIST":"/home/pk4/project/test_new_1/lists/bam_list.txt",
+    "mutect_variant_calling.SCATTER_CALLING_INTERVALS_LIST":"/home/pk4/project/test_new_1/lists/intervals.txt",
+    "mutect_variant_calling.refFasta":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa",
+    "mutect_variant_calling.refIndex":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.fai",
+    "mutect_variant_calling.refDict":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.dict",
+    "mutect_variant_calling.samtools":"/home/pk4/software/samtools-1.4.1/samtools",
+    "mutect_variant_calling.gatk":"/home/pk4/software/gatk-4.0.11.0/gatk-package-4.0.11.0-local.jar",
+    "#--------VCFs------------------":"-------------------------------------------",
+    "mergevcfs.VCF_samples_lists":"/home/pk4/project/test_new_1/lists/vcfs_samples_lists.txt",
+    "#-------_VCFs_------------------":"-------------------------------------------",
+    "mergevcfs.gatk":"/home/pk4/software/gatk-4.0.11.0/gatk-package-4.0.11.0-local.jar",
+    "mergevcfs.tabix":"/home/pk4/software/tabix/tabix",
+    "mergevcfs.samtools":"/home/pk4/software/samtools-1.4.1/samtools",
+    "mergevcfs.refFasta":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa",
+    "mergevcfs.refIndex":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.fa.fai",
+    "mergevcfs.refDict":"/home/pk4/genome/H.sapiens/hg38/indexes/bwa/hg38.dict",
+    "##-------------------":"----------------------------------------------------------------"
+
+}