alignment/dnaseqalign.sh

@@ -12,7 +12,7 @@ usage() {
   exit 1
 }
 OPTIND=1 # Reset OPTIND
-while getopts :r:x:y:p:u:h opt
+while getopts :r:x:y:p:uh opt
 do
     case $opt in
         r) index_path=$OPTARG;;

alignment/rnaseqalign.sh

@@ -34,15 +34,18 @@ if [[ -z $pair_id ]] || [[ -z $fq1 ]]; then
 fi
 
 source /etc/profile.d/modules.sh
-module load  samtools/gcc/1.6 picard/2.10.3
+module load  samtools/1.6 picard/2.10.3
 baseDir="`dirname \"$0\"`"
 if [[ -z $SLURM_CPUS_ON_NODE ]]
 then
     SLURM_CPUS_ON_NODE=1
 fi
+
+diff $fq1 $fq2 > difffile.out
+
 if [ $algo == 'star' ]
 then
-    if ($fq1 != $fq2)
+    if (-s difffile)
     then
 	module load star/2.4.2a
 	STAR --genomeDir ${index_path}/star_index/ --readFilesIn $fq1 $fq2 --readFilesCommand zcat --genomeLoad NoSharedMemory --outFilterMismatchNmax 999 --outFilterMismatchNoverReadLmax 0.04 --outFilterMultimapNmax 20 --alignSJoverhangMin 8 --alignSJDBoverhangMin 1 --alignIntronMin 20 --alignIntronMax 1000000 --alignMatesGapMax 1000000 --outSAMheaderCommentFile COfile.txt --outSAMheaderHD @HD VN:1.4 SO:coordinate --outSAMunmapped Within --outFilterType BySJout --outSAMattributes NH HI AS NM MD --outSAMstrandField intronMotif --outSAMtype BAM SortedByCoordinate --quantMode TranscriptomeSAM --sjdbScore 1 --limitBAMsortRAM 60000000000 --outFileNamePrefix out
@@ -53,19 +56,20 @@ then
     mv outAligned.sortedByCoord.out.bam output.bam
 else
     module load hisat2/2.1.0-intel
-    if [ $fq1 == $fq2 ]
+    if [ -s difffile ]
     then
+	hisat2 -p $SLURM_CPUS_ON_NODE --rg-id ${pair_id} --rg LB:tx --rg PL:illumina --rg PU:barcode --rg SM:${pair_id} --add-chrname --no-unal --dta -x ${index_path}/hisat_index/genome -1 $fq1 -2 $fq2 -S out.sam --summary-file ${pair_id}.alignerout.txt
+    else
 	hisat2 -p $SLURM_CPUS_ON_NODE --rg-id ${pair_id} --rg LB:tx --rg PL:illumina --rg PU:barcode --rg SM:${pair_id} --add-chrname --no-unal --dta -x ${index_path}/hisat_index/genome -U $fq1 -S out.sam --summary-file ${pair_id}.alignerout.txt
+    fi
+    if [[ $umi==1 ]]
+    then
+	python ${baseDir}/add_umi_sam.py -s out.sam -o output.bam
     else
-	hisat2 -p $SLURM_CPUS_ON_NODE --rg-id ${pair_id} --rg LB:tx --rg PL:illumina --rg PU:barcode --rg SM:${pair_id} --add-chrname --no-unal --dta -x ${index_path}/hisat_index/genome -1 $fq1 -2 $fq2 -S out.sam --summary-file ${pair_id}.alignerout.txt
+	samtools view -1 --threads $SLURM_CPUS_ON_NODE -o output.bam out.sam
     fi
-    samtools view -1 --threads $SLURM_CPUS_ON_NODE -o output.bam out.sam
-fi
-if [[ $umi==1 ]]
-then
-    python ${baseDir}/add_umi_bam.py -b output.bam -o output.unsort2.bam
-    mv output.unsort2.bam output.bam
 fi
+
 samtools sort -@ $SLURM_CPUS_ON_NODE -O BAM -n -o  output.nsort.bam output.bam
 java -jar $PICARD/picard.jar FixMateInformation ASSUME_SORTED=TRUE SORT_ORDER=coordinate ADD_MATE_CIGAR=TRUE I=output.nsort.bam O=${pair_id}.bam
 samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.bam

preproc_fastq/trimgalore.sh

@@ -32,13 +32,13 @@ r2base="${fq2%.fastq*}"
 source /etc/profile.d/modules.sh
 module load trimgalore/0.4.1 cutadapt/1.9.1
 
-if [ $fq1 == $fq2 ]
+if [ -s $fq2 ]
 then
-    trim_galore -q 25 --illumina --gzip --length 35 ${fq1}
-    mv ${r1base}_trimmed.fq.gz ${pair_id}.trim.R1.fastq.gz
-    cp ${pair_id}.trim.R1.fastq.gz ${pair_id}.trim.R2.fastq.gz 
-else
     trim_galore --paired -q 25 --illumina --gzip --length 35 ${fq1} ${fq2}
     mv ${r1base}_val_1.fq.gz ${pair_id}.trim.R1.fastq.gz
     mv ${r2base}_val_2.fq.gz ${pair_id}.trim.R2.fastq.gz
+else
+    trim_galore -q 25 --illumina --gzip --length 35 ${fq1}
+    mv ${r1base}_trimmed.fq.gz ${pair_id}.trim.R1.fastq.gz
+    cp ${pair_id}.trim.R1.fastq.gz ${pair_id}.trim.R2.fastq.gz 
 fi

variants/cnvkit.sh

@@ -21,6 +21,8 @@ done
 
 shift $(($OPTIND -1))
 
+index_path='/project/shared/bicf_workflow_ref/GRCh38/clinseq_prj/'
+
 # Check for mandatory options
 if [[ -z $pair_id ]] || [[ -z $sbam ]]; then
     usage
@@ -33,13 +35,13 @@ baseDir="`dirname \"$0\"`"
 
 source /etc/profile.d/modules.sh
 module load cnvkit/0.9.0
-cnvkit.py coverage ${sbam} /project/shared/bicf_workflow_ref/GRCh38/UTSWV2.cnvkit_targets.bed -o ${pair_id}.targetcoverage.cnn
-cnvkit.py coverage ${sbam} /project/shared/bicf_workflow_ref/GRCh38/UTSWV2.cnvkit_antitargets.bed -o ${pair_id}.antitargetcoverage.cnn
+cnvkit.py coverage ${sbam} ${index_path}/UTSWV2.cnvkit_targets.bed -o ${pair_id}.targetcoverage.cnn
+cnvkit.py coverage ${sbam} ${index_path}/UTSWV2.cnvkit_antitargets.bed -o ${pair_id}.antitargetcoverage.cnn
 if [[ $umi == 'umi' ]]
 then
-cnvkit.py fix ${pair_id}.targetcoverage.cnn ${pair_id}.antitargetcoverage.cnn /project/shared/bicf_workflow_ref/GRCh38/UTSWV2.uminormals.cnn -o ${pair_id}.cnr
+cnvkit.py fix ${pair_id}.targetcoverage.cnn ${pair_id}.antitargetcoverage.cnn ${index_path}/UTSWV2.uminormals.cnn -o ${pair_id}.cnr
 else
-cnvkit.py fix ${pair_id}.targetcoverage.cnn ${pair_id}.antitargetcoverage.cnn /project/shared/bicf_workflow_ref/GRCh38/UTSWV2.normals.cnn -o ${pair_id}.cnr
+cnvkit.py fix ${pair_id}.targetcoverage.cnn ${pair_id}.antitargetcoverage.cnn ${index_path}/UTSWV2.normals.cnn -o ${pair_id}.cnr
 fi   
 
 cnvkit.py segment ${pair_id}.cnr -o ${pair_id}.cns