#This very complete configuration will start from a set of single end FASTQ files and generates a cleaned VCF while removing intermediate data $order 1=fastqc 2=cutadapt 3=bwaAln 4=bwaSamse 5=picardToolsSortSam 6=samtoolsflagstat 7=samtoolsview 8=samToolsIndex 9=gatkRealignerTargetCreator 10=gatkIndelRealigner 11=picardToolsMarkDuplicates 1000=gatkHaplotypeCaller 1001=gatkVariantFiltration 1002=gatkSelectVariants $cleaner 3 4 9 #PUT YOUR OWN SCHEDULER CONFIGURATION HERE #Example for SGE #$sge #-q YOURQUEUE.q #-b Y $cutadapt -O=10 -m=35 -q=20 --overlap=7 # Adaptator1 is removed in the forward (-b) read (5' and 3' position) -b ADAPTATOR1REVERSE # Same traitement is done for the forward adaptator sequence -b ADAPTATOR1FORWARD $bwa aln -n=5 $bwa samse $picardToolsSortSam SORT_ORDER=coordinate VALIDATION_STRINGENCY=SILENT CREATE_INDEX=TRUE $samToolsView -h -b -F=4 $gatkRealignerTargetCreator -T=RealignerTargetCreator $gatkIndelRealigner -T=IndelRealigner $picardToolsMarkDuplicates VALIDATION_STRINGENCY=SILENT CREATE_INDEX=TRUE REMOVE_DUPLICATES=TRUE $gatkHaplotypeCaller -T=HaplotypeCaller -rf BadCigar $gatkVariantFiltration -T=VariantFiltration --filterName 'FILTER-DP' --filterExpression 'DP<10 || DP>600' --filterName 'LowQual' --filterExpression 'QUAL<30' $gatkSelectVariants -T=SelectVariants -selectType=SNP