Merge branch 'master' of git.biohpc.swmed.edu:BICF/Astrocyte/process_scripts

alignment/bamqc.sh

@@ -48,10 +48,10 @@ if [[ $nuctype == 'dna' ]]; then
     samtools flagstat ${pair_id}.ontarget.bam > ${pair_id}.ontarget.flagstat.txt
     samtools view -b -q 1 ${pair_id}.ontarget.bam | bedtools coverage -sorted -hist -g ${index_path}/genomefile.txt -b stdin -a ${bed}  >  ${pair_id}.mapqualcov.txt
     samtools view -b -F 1024 ${pair_id}.ontarget.bam | bedtools coverage -sorted -g  ${index_path}/genomefile.txt -a ${bed} -b stdin -hist | grep ^all > ${pair_id}.dedupcov.txt 
-    java -Xmx32g -jar $PICARD/picard.jar CollectAlignmentSummaryMetrics R=${reffa} I=${pair_id}.ontarget.bam OUTPUT=${pair_id}.alignmentsummarymetrics.txt
+    java -Xmx32g -jar $PICARD/picard.jar CollectAlignmentSummaryMetrics R=${index_path}/genome.fa I=${pair_id}.ontarget.bam OUTPUT=${pair_id}.alignmentsummarymetrics.txt
     java -Xmx64g -jar $PICARD/picard.jar EstimateLibraryComplexity I=${pair_id}.ontarget.bam OUTPUT=${pair_id}.libcomplex.txt
     samtools view -F 1024 ${pair_id}.ontarget.bam | awk '{sum+=$5} END { print "Mean MAPQ =",sum/NR}' > ${pair_id}.meanmap.txt
-    java -Xmx4g -jar $PICARD/picard.jar CollectInsertSizeMetrics INPUT=${pair_id}.bam HISTOGRAM_FILE=${pair_id}.hist.ps REFERENCE_SEQUENCE=${reffa} OUTPUT=${pair_id}.hist.txt
+    java -Xmx4g -jar $PICARD/picard.jar CollectInsertSizeMetrics INPUT=${sbam} HISTOGRAM_FILE=${pair_id}.hist.ps REFERENCE_SEQUENCE=${index_path}/genome.fa OUTPUT=${pair_id}.hist.txt
     samtools view -b -q 1 ${pair_id}.ontarget.bam | bedtools coverage -sorted -hist -g ${index_path}/genomefile.txt -b stdin -a ${bed}  >  ${pair_id}.mapqualcov.txt
     bedtools coverage -sorted -g  ${index_path}/genomefile.txt -a ${bed} -b ${sbam} -hist > ${pair_id}.covhist.txt
     perl $baseDir/scripts/calculate_depthcov.pl ${pair_id}.covhist.txt

alignment/dnaseqalign.sh

@@ -42,14 +42,14 @@ baseDir="`dirname \"$0\"`"
 
 if [[ $fq1 == $fq2 ]]
 then
-   bwa mem -M -t $SLURM_CPUS_ON_NODE -R "@RG\tID:${pair_id}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${pair_id}" ${index_path}/genome.fa ${fq1} > out.sam
+    bwa mem -M -t $SLURM_CPUS_ON_NODE -R "@RG\tID:${pair_id}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${pair_id}" ${index_path}/genome.fa ${fq1} > out.sam
 else
-   bwa mem -M -t $SLURM_CPUS_ON_NODE -R "@RG\tID:${pair_id}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${pair_id}" ${index_path}/genome.fa ${fq1} ${fq2} > out.sam
+    bwa mem -M -t $SLURM_CPUS_ON_NODE -R "@RG\tID:${pair_id}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${pair_id}" ${index_path}/genome.fa ${fq1} ${fq2} > out.sam
 fi
 
 if [[ $umi=='umi' ]]
 then
-    k8 /cm/shared/apps/bwakit/0.7.15/bwa-postalt.js -p ${pair_id}.hla ${index_path}/genome.fa.alt out.sam | python ${baseDir}/add_umi_bam.py -s - -o output.unsort.bam
+    k8 /cm/shared/apps/bwakit/0.7.15/bwa-postalt.js -p ${pair_id}.hla ${index_path}/genome.fa.alt out.sam | python ${baseDir}/add_umi_sam.py -s - -o output.unsort.bam
 elif [[ $index_path == '/project/shared/bicf_workflow_ref/GRCh38' ]]
 then
     k8 /cm/shared/apps/bwakit/0.7.15/bwa-postalt.js -p ${pair_id}.hla ${index_path}/genome.fa.alt out.sam| samtools view -1 - > output.unsort.bam

alignment/markdups.sh

@@ -56,7 +56,7 @@ elif [ $algo == 'fgbio_umi' ]
 then
     samtools index -@ $SLURM_CPUS_ON_NODE ${sbam}
     source activate fgbiotools
-    fgbio GroupReadsByUmi -s identity -i ${sbam} -o ${pair_id}.group.bam -m 10
+    fgbio GroupReadsByUmi -s identity -i ${sbam} -o ${pair_id}.group.bam -m 0
     fgbio CallMolecularConsensusReads -i ${pair_id}.group.bam -p consensus -M 1 -o ${pair_id}.consensus.bam -S ':none:'
     source deactivate
     module load bwa/intel/0.7.15