v102

Author: Cao

README.md

@@ -1,32 +1,15 @@
 
-# Somaticwrapper version 1.6.1, compute1 #
+# Somaticwrapper version 2.1, compute1 #
 
 Detect somatic variants from tumor and normal WGS/WXS data (HG38 reference). SomaticWrapper pipeline is a fully automated and modular software package designed for detection of somatic variants from tumor and normal exome data. It works on LSF job scheduler and can run multiple jobs in parallel. Multiple standard variant calling tools are included in the pipeline such as varscan2, strelka2, mutect1 and pindel. The final called variant can be found from dnp.annotated.maf file. 
 
 SNV calls are intersecting results from 2 over 3 callers (Strelka2, Mutect1, and VarScan2).
 
 Indel calls are called by 2 over 3 callers (Strelka2, Varscan2 and pindel). 
 
-Improvements compared to version 1.6:
+Improvements compared to version 1.6.1:
 
-1. Requires smg input in the pipeline run
-
-2. Adding step 14 for cleaning unnecessary intermediate files  
-
-## Install the third-party software ##
-
-Mutect-1.1.7: https://software.broadinstitute.org/gatk/download/archive
-
-Strelka-2.9.2: https://github.com/Illumina/strelka/releases
-
-Varscan 2.2.8: https://sourceforge.net/projects/varscan/files/
-
-Pindel version 0.2.5b9: 1: http://gmt.genome.wustl.edu/packages/pindel/install.html
-		   	2: conda install -c bioconda pindel
-	
-bam-readcount 0.7.4: https://github.com/genome/bam-readcount 
-
-java jre1.8.0_121: https://www.oracle.com/java/technologies/javase/javase8-archive-downloads.html
+Use ensembl V102 for annotation 
 
 ## Usage ##
 

somaticwrapper.pl

@@ -230,8 +230,12 @@
 my $samtools="/storage1/fs1/songcao/Active/Software/samtools/1.2/bin";
 my $varscan="/storage1/fs1/songcao/Active/Software/varscan/2.3.8.ndown";
 my $bamreadcount="/storage1/fs1/songcao/Active/Software/bam-readcount/0.7.4/bam-readcount";
-my $vepannot="/storage1/fs1/songcao/Active/Database/hg38_database/vep/ensembl-tools-release-85/scripts/variant_effect_predictor/variant_effect_predictor.pl";
-my $vepcache="/storage1/fs1/songcao/Active/Database/hg38_database/vep/v85";
+my $vepannot="/storage1/fs1/songcao/Active/Database/hg38_database/vep/ensembl-tools-release-85/scripts/variant_effect_predictor/variant_effect_predictor.v102.pl";
+my $vepannot="/storage1/fs1/songcao/Active/Git/ensembl-vep/vep";
+
+#my $vepcache="/storage1/fs1/songcao/Active/Database/hg38_database/vep/v85";
+
+my $vepcache="/storage1/fs1/songcao/Active/Database/hg38_database/vep/v102";
 
 my $DB_SNP_NO_CHR="/storage1/fs1/songcao/Active/Database/hg38_database/DBSNP/00-All.vcf";
 my $DB_SNP="/storage1/fs1/songcao/Active/Database/hg38_database/DBSNP/00-All.chr.vcf";
@@ -1496,7 +1500,7 @@ sub bsub_vcf_2_maf{
 
 
     my $sh_file=$job_files_dir."/".$current_job_file;
-    $bsub_com = "LSF_DOCKER_ENTRYPOINT=/bin/bash LSF_DOCKER_PRESERVE_ENVIRONMENT=false bsub -g /$compute_username/$group_name -n 1 -R \"select[mem>30000] rusage[mem=30000]\" -M 30000000 -a \'docker(registry.gsc.wustl.edu/genome/genome_perl_environment)\' -o $lsf_out -e $lsf_err bash $sh_file\n";
+    $bsub_com = "LSF_DOCKER_ENTRYPOINT=/bin/bash LSF_DOCKER_PRESERVE_ENVIRONMENT=false bsub -g /$compute_username/$group_name -n 1 -R \"select[mem>30000] rusage[mem=30000]\" -M 30000000 -a \'docker(ensemblorg/ensembl-vep:release_102.0)\' -o $lsf_out -e $lsf_err bash $sh_file\n";
     print $bsub_com;
     system ($bsub_com);
 

work_log_run_mild_v102

@@ -0,0 +1,6 @@
+perl somaticwrapper.pl --rdir /scratch1/fs1/dinglab/scao/sw/mildvep102 --log /scratch1/fs1/dinglab/scao/sw/mildvep102.log --ref  /storage1/fs1/songcao/Active/Database/hg38_database/GRCh38.d1.vd1/GRCh38.d1.vd1.fa --q general --smg  /storage1/fs1/songcao/Active/Database/smg_database/smg.lung.tsv --users songcao --groupname SomaticWXS --step 11 --sre 1
+
+perl somaticwrapper.pl --rdir /scratch1/fs1/dinglab/scao/sw/mildvep102 --log /scratch1/fs1/dinglab/scao/sw/mildvep102.log --ref  /storage1/fs1/songcao/Active/Database/hg38_database/GRCh38.d1.vd1/GRCh38.d1.vd1.fa --q general --smg  /storage1/fs1/songcao/Active/Database/smg_database/smg.lung.tsv --users songcao --groupname SomaticWXS --step 12 --sre 1
+
+perl somaticwrapper.pl --rdir /scratch1/fs1/dinglab/scao/sw/mildvep102 --log /scratch1/fs1/dinglab/scao/sw/mildvep102.log --ref  /storage1/fs1/songcao/Active/Database/hg38_database/GRCh38.d1.vd1/GRCh38.d1.vd1.fa --q general --smg  /storage1/fs1/songcao/Active/Database/smg_database/smg.lung.tsv --users songcao --groupname SomaticWXS --sre 1 --step 13 --sre 1
+