WES-pipeline-SNP-calling.sh

addGrp:
        java -Xmx${heap}m -Djava.io.tmpdir\=${temp_folder}/${patient}  \
         -jar ${picard}/AddOrReplaceReadGroups.jar \
          RGLB\=${sample}.fastq \
          RGPL\=Illumina \
          RGPU\=${sample} \
          RGSM\=${sample} \
          I\=${SCRATCH}/${sample}/${sample}.rmdup.bam \
          O\=${SCRATCH}/${sample}/${sample}.rmdup.grp.bam \
          SORT_ORDER\=coordinate \
          CREATE_INDEX\=true \
          VALIDATION_STRINGENCY\=SILENT

# the sort_order argument may not be necessary if the input is already sorted

	mv -f ${SCRATCH}/${sample}/${sample}.rmdup.grp.bam    ${SCRATCH}/${sample}/${sample}.rmdup.bam
        mv -f ${SCRATCH}/${sample}/${sample}.rmdup.grp.bai     ${SCRATCH}/${sample}/${sample}.rmdup.bai
        
        
BQSR:

    java -jar GenomeAnalysisTK.jar \ 
      -T BaseRecalibrator \ 
      -R ${refSequence} \ 
      -I ${SCRATCH}/${sample}/${sample}.rmdup.bam \ 
      -L 20 \ 
      -knownSites ${dbsnp} \ 
      -knownSites ${goldIndels} \ 
      -o ${SCRATCH}/${sample}/${sample}.recal_data.table 
    
    java -jar GenomeAnalysisTK.jar \ 
      -T BaseRecalibrator \ 
      -R ${refSequence} \ 
     -I ${SCRATCH}/${sample}/${sample}.rmdup.bam \ 
     -L 20 \ 
     -knownSites ${dbsnp} \ 
     -knownSites ${goldIndels} \ 
     -BQSR ${SCRATCH}/${sample}/${sample}.recal_data.table  \ 
     -o ${SCRATCH}/${sample}/${sample}.post_recal_data.table
     
   java -jar GenomeAnalysisTK.jar \ 
     -T AnalyzeCovariates \ 
     -R ${refSequence} \ 
     -L 20 \ 
     -before ${SCRATCH}/${sample}/${sample}.recal_data.table \
     -after ${SCRATCH}/${sample}/${sample}.post_recal_data.table \
     -plots ${SCRATCH}/${sample}/${sample}.recalibration_plots.pdf
    
    
  java -jar GenomeAnalysisTK.jar \ 
    -T PrintReads \ 
    -R ${refSequence} \ 
    -I ${SCRATCH}/${sample}/${sample}.rmdup.bam \ 
    -L 20 \ 
    -BQSR ${SCRATCH}/${sample}/${sample}.recal_data.table \ 
    -o ${SCRATCH}/${sample}/${sample}.recalibrated.bam 
    
    
variantDiscovery:

  java -jar GenomeAnalysisTK.jar \ 
    -T HaplotypeCaller \ 
    -R ${refSequence} \ 
    -I ${SCRATCH}/${sample}/${sample}.recalibrated.bam \  
    -L 20 \ 
    --genotyping_mode DISCOVERY \ 
    -stand_emit_conf 10 \ 
    -stand_call_conf 30 \ 
    -o ${SCRATCH}/${sample}/${sample}.raw_variants.vcf 
    
java -jar GenomeAnalysisTK.jar \ 
    -T SelectVariants \ 
    -R ${refSequence} \ 
    -V ${SCRATCH}/${sample}/${sample}.raw_variants.vcf \ 
    -selectType SNP \ 
    -o ${SCRATCH}/${sample}/${sample}.raw_snps.vcf 
    
java -jar GenomeAnalysisTK.jar \ 
    -T VariantFiltration \ 
    -R ${refSequence} \ 
    -V ${SCRATCH}/${sample}/${sample}.raw_snps.vcf \ 
    --filterExpression "QD < 2.0 || FS > 60.0 || MQ < 40.0 || MQRankSum < -12.5 || ReadPosRankSum < -8.0" \ 
    --filterName "my_snp_filter" \ 
    -o ${SCRATCH}/${sample}/${sample}.filtered_snps.vcf 
   
java -jar GenomeAnalysisTK.jar \ 
    -T VariantFiltration \ 
    -R ${refSequence} \ 
    -V ${SCRATCH}/${sample}/${sample}.filtered_snps.vcf \ 
    --filterExpression "AC == 1 && DP > 20 && AF >= 0.40 && AF <= 0.60" \ 
    --filterName "heterozygous_filter" \ 
    -o ${SCRATCH}/${sample}/${sample}.filtered_snps.heterozygous.vcf