updates somatic indel detection

hxrts · Apr 21, 2015 · 86553dd · 86553dd
1 parent 05efa39
commit 86553dd
Show file tree

Hide file tree

Showing 6 changed files with 54 additions and 26 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,6 +1,7 @@
 *.bam
 *.bai
-*.DS_Store
+.DS_Store
+scripts/.DS_Store
 docs/
 refs/
 tools/

diff --git a/README.md b/README.md
@@ -5,9 +5,21 @@ When cloning this repo for the first time you must install the necessary tools.
 2. Place a copy of annovar, samtools, etc.
 
 ### Executing the script
-`python master.py -s sample_info.txt -p path_file.txt -d test`
+production run: `python call-mutations-indels.py -s sample_info.txt -p path_file.txt -d test -b test`
 
-This pipeline is currently installed on the hopp-cli server and must be executed from /home/sam/HOPP-Informatics/projects/sequencing_pipeline.
+debug run: `python -i call-mutations-indels.py -s sample_info.txt -p path_file.txt -d test -b test`
+
+This pipeline is currently installed on the hopp-cli server and must be executed from /home/sam/HOPP-Informatics/projects/sequencingPipeline.
+
+### Build reference index (if adding new assembly)
+Generate the BWA index
+`bwa index -a bwtsw reference.fa`
+
+Generate the fasta file index
+`samtools faidx reference.fa`
+
+Generate the sequence dictionary
+`java -jar picard.jar /home/sam/tools/picard-tools-1.130/CreateSequenceDictionary REFERENCE=reference.fa OUTPUT=reference.dict`
 
 ### Warning
-This pipeline is still in development and produces known errors. This page will be updated upon reaching a functional alpha.
+This pipeline is still in development and produces known errors use at your own risk.
diff --git a/call-mutations-indels.py b/call-mutations-indels.py
@@ -1,5 +1,5 @@
 # --------------------------------------------------------------------------------------------------------#
-# This master script that parses the sample information provided by the user and calls mutations + indels
+# This primary script that parses the sample information provided by the user and calls mutations + indels
 # If there is a need to realign and recalibrate, it runs GATK realignment/recalibration scripts
 # --------------------------------------------------------------------------------------------------------#
 
@@ -17,7 +17,6 @@
 import csv
 import os
 import argparse
-import recurse
 
 #------------------------------------------------------------------#
 # Parser Info
@@ -116,7 +115,7 @@
 
 GATK_PATH = exdir + '/scripts/pipelineGATK.sh'																				# GATK pipeline path
 GATK_INTERVAL_PATH = exdir + '/scripts/pipelineIntervalGATK.sh'																# GATK interval script path
-SAM_INDEX_PATH = exdir + '/home/sam/HOPP-Informatics/projects/sequencing_pipeline/tools/samtools-0.1.19/samtools index'		# samtools path	
+SAM_INDEX_PATH = exdir + '/home/sam/tools/samtools-1.1/samtools index'		# samtools path	
 SOMATIC_SNIPER_PATH = exdir + '/scripts/call-somatic-sniper.sh'																# somatic sniper path
 SOMATIC_INDEL_PATH = exdir + '/scripts/call-indels.sh'																		# somatic indel_detector path
 SOMATIC_INDEL_INTERVAL_PATH = exdir + '/scripts/call-indels-with-intervals.sh'												# somatic indel path with intervals
@@ -345,7 +344,6 @@
 			print "Calling somatic mutations using Somatic Sniper"
 			sys.stdout.flush()
 			os_call = SOMATIC_SNIPER_PATH+" "+tumor_recalibrated_directory+" "+normal_recalibrated_directory+" "+somatic_sniper_directory+" "+sample_name[i]
-			print os_call+"!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
 			os.system(os_call)
 		if (somatic_indel_flag == 1):
 			if (bedfile_flag == 1):

diff --git a/path_file.sh b/path_file.sh
@@ -2,7 +2,8 @@
 # GLOBAL
 #--------#
 
-REF=/home/sam/HOPP-Informatics/projects/sequencingPipeline/refs/Homo_sapiens_assembly19.fasta
+#REF=/home/sam/HOPP-Informatics/projects/sequencingPipeline/refs/Homo_sapiens_assembly19.fasta
+REF=/home/sam/HOPP-Informatics/projects/sequencingPipeline/refs/GRCh37-lite.fa
 
 #---------#
 # ANNOVAR
@@ -18,9 +19,14 @@ ANNOVAR_DB=/hopp-storage/HOPP-TOOLS/ANNOTATIONS/annovar-may-2013/annovar/humandb
 # GATK
 #------#
 
-GATK=/hopp-storage/HOPP-TOOLS/PIPELINES/GATKBundle/GenomeAnalysisTK-2.4-9-g532efad/GenomeAnalysisTK.jar
-GAT1=/hopp-storage/HOPP-TOOLS/PIPELINES/GATKBundle/Somatic-Indel-Detector/GATK/dist/GenomeAnalysisTK.jar
-GAT0=/hopp-storage/HOPP-TOOLS/PIPELINES/GATKBundle/Sting/dist/GenomeAnalysisTK.jar								# Use old GATK for identifying target intervals
+GATK=/home/sam/tools/GenomeAnalysisTK-3.3-0/GenomeAnalysisTK.jar
+#GATK_IndelGeno=/home/sam/tools/GenomeAnalysisTK-3.3-0/IndelGenotyper.36.3336-GenomeAnalysisTK.jar
+
+#GAT1=/home/sam/tools/GenomeAnalysisTK-3.3-0/GenomeAnalysisTK.jar
+#GAT0=/home/sam/tools/GenomeAnalysisTK-3.3-0/GenomeAnalysisTK.jar
+#GATK=/hopp-storage/HOPP-TOOLS/PIPELINES/GATKBundle/GenomeAnalysisTK-2.4-9-g532efad/GenomeAnalysisTK.jar
+#GAT1=/hopp-storage/HOPP-TOOLS/PIPELINES/GATKBundle/Somatic-Indel-Detector/GATK/dist/GenomeAnalysisTK.jar
+#GAT0=/hopp-storage/HOPP-TOOLS/PIPELINES/GATKBundle/Sting/dist/GenomeAnalysisTK.jar								# Use old GATK for identifying target intervals
 
 #--------#
 # MUTECT
@@ -61,6 +67,6 @@ SNPEFF=/hopp-storage/HOPP-TOOLS/ANNOTATIONS/snpEff/SnpSift.jar
 # 1000g_ANNO=/hopp-storage/HOPP-TOOLS/PIPELINES/MutPipelines/scripts/annotate-100g-calls.sh <------ missing
 # ESP_ANNO=/hopp-storage/HOPP-TOOLS/PIPELINES/MutPipelines/scripts/annotate-ESP-calls.sh <------ missing
 # dbSNP_ANNO=/hopp-storage/HOPP-TOOLS/PIPELINES/MutPipelines/scripts/annotate-dbSNP-calls.sh <------ missing
-# COSMIC_ANNO=/HOPP-Informatics/projects/sequencing_pipeline/scripts/annotate-cosmic-calls.sh
+# COSMIC_ANNO=/HOPP-Informatics/projects/sequencingPipeline/scripts/annotate-cosmic-calls.sh
 
 
diff --git a/sample_info.txt b/sample_info.txt
@@ -1,3 +1,3 @@
-BAMPath	/home/sam/HOPP-Informatics/projects/sequencing_pipeline/bams
-LOCPath	/home/sam/HOPP-Informatics/projects/sequencing_pipeline/loc
-s_GA_1	s_GA_NL1__1.bam	s_GA_T1__1.bam		
+BAMPath	/home/sam/HOPP-Informatics/projects/sequencingPipeline/bams
+LOCPath	/home/sam/HOPP-Informatics/projects/sequencingPipeline/loc
+AK-3451	TCGA-AK-3451-10A-01D-1251-10_Illumina.bam	TCGA-AK-3451-01A-02D-1251-10_Illumina.bam		
diff --git a/scripts/call-indels-with-intervals.sh b/scripts/call-indels-with-intervals.sh
@@ -3,13 +3,24 @@
 echo "*** calling indels with intervals ***"
 source path_file.sh	# path to the GATK (somatic indel detector) and reference genome
 
-java -Xmx8g -jar "$GAT1" -R "$REF" -T SomaticIndelDetector -mnr 50000  \
-							   -minConsensusFraction 0.7 \
-							   -minCoverage 6 \
-							   -minNormalCoverage 4 \
-							   -o $3/SI-$4.vcf \
-							   -verbose $3/SI-$4.txt \
-							   -I:normal $1/out.recal.quality.bam \
-							   -I:tumor $2/out.recal.quality.bam \
-							   -L $5 \
-							   --validation_strictness SILENT -U
+java -Xmx8g -jar "$GATK" \
+			-R "$REF" \
+			-T UnifiedGenotyper \
+			-I:normal $1/out.recal.quality.bam \
+			-I:tumor $2/out.recal.quality.bam \
+			-o $3/SI-$4.vcf \
+			-stand_call_conf 50.0 \
+			-stand_emit_conf 10.0 \
+			-dcov 200
+
+
+# java -Xmx8g -jar "$GATK_IndelGeno" -R "$REF" -T SomaticIndelDetector -mnr 50000  \
+# 							   -minConsensusFraction 0.7 \
+# 							   -minCoverage 6 \
+# 							   -minNormalCoverage 4 \
+# 							   -o $3/SI-$4.vcf \
+# 							   -verbose $3/SI-$4.txt \
+# 							   -I:normal $1/out.recal.quality.bam \
+# 							   -I:tumor $2/out.recal.quality.bam \
+# 							   -L $5 \
+# 							   --validation_strictness SILENT -U