SRR2986953 130216_SN733_0370_AC1N3BACXX_5_ID04 ARBRMR.A06526-2_1AMP-3 1 NIL bwa 0.6.2 bwa aln $aln_params -t $t $index_base read.txt > read.sai (repeated for the pair) 2 1 bwa 0.6.2 bwa sampe $sampe_params $index_base read1.sai read2.sai 3 2 picard 1.88 java -jar FixMateInformation.jar I=merge.bam O=fix.bam 4 3 picard 1.88 java –jar MarkDuplicates.jar I=fix.bam METRICS_FILE=metrics.txt O=dedup.bam 5 4 picard 1.88 java -jar AddOrReplaceReadGroups.jar $rg I=/dev/stdin O=input-$i.bam VALIDATION_STRINGENCY=SILENT 6 5 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T RealignerTargetCreator -I dedup.bam -R ref.fa -nt $nt $known_indels --downsampling_type NONE -o target.intervals 7 6 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T IndelRealigner -I dedup.bam -R ref.fa -targetIntervals target.intervals -o realigned.bam $known_indels --downsampling_type NONE 8 7 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T BaseRecalibrator -I realigned.bam -R ref.fa -nct $nt $dbsnps $indels --downsampling_type NONE -cov ReadGroupCovariate -cov QualityScoreCovariate -cov CycleCovariate -cov ContextCovariate -o recal_data.grp 9 8 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T PrintReads -BQSR recal_data.grp -R ref.fa -I realigned.bam -nct $nt --downsampling_type NONE --emit_original_quals -o recaled.bam 10 9 picard 1.88 java -jar MergeSamFiles.jar I=barcode_recal.realigned-1.bam I=barcode_recal.realigned-2.bam I(x)=barcode_recal.realigned-x.bam O=sample.merged.bam 11 10 picard 1.88 java -jar MarkDuplicates.jar I=sample.merged.bam METRICS_FILE=metric_file.picard O=sample.dups.bam 12 11 samtools 0.1.7(r510) samtools index sample.dups.bam 13 12 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T RealignerTargetCreator -I sample.dups.bam -R reference.fasta -nt 8 --downsampling_type NONE -known 1000G_phase1.indels.b37.vcf.gz -known Mills_and_1000G_gold_standard.indels.b37.vcf.gz -o sample.intervals 14 13 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T IndelRealigner -I sample.dups.bam -R reference.fasta -targetIntervals sample.intervals --downsampling_type NONE --consensusDeterminationModel USE_READS -known 1000G_phase1.indels.b37.vcf.gz -known Mills_and_1000G_gold_standard.indels.b37.vcf.gz -o sample_realigned.bam 15 14 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T BaseRecalibrator I=sample_realigned.bam -R reference.fasta -o sample.GATKrecal_data.grp --downsampling_type NONE -knownSites dbsnp_137.b37.vcf.gz -knownSites 1000G_phase1.indels.b37.vcf.gz -knownSites Mills_and_1000G_gold_standard.indels.b37.vcf.gz -cov ReadGroupCovariate -cov QualityScoreCovariate -cov CycleCovariate -cov ContextCovariate-dP illumina -knownSites:dbSNP,VCF sites.vcf.gz -cov ReadGroupCovariate -cov QualityScoreCovariate -cov CycleCovariate -cov DinucCovariate -recalFile sample.csv 16 15 GATk 2.5-2-gf57256b java -jar GenomeAnalysisTK.jar -T PrintReads -I sample_realigned.bam -R reference.fasta -BQSR sample.GATKrecal_data.grp --emit_original_quals --downsampling_type NONE -o sample_recal.realigned.bam