Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

check for empty Platform (PL) in bam RG #364

Merged
merged 7 commits into from
Nov 10, 2022
Merged

check for empty Platform (PL) in bam RG #364

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
aae31bf
check for empty Platform (PL) in bam RG
Aug 26, 2022
79b1855
Merge branch 'dev' into RG_handle
nickhsmith Aug 26, 2022
710dd42
Merge branch 'dev' into RG_handle
nickhsmith Oct 18, 2022
a55e72b
Merge branch 'dev' into RG_handle
nickhsmith Oct 18, 2022
26ea71f
Merge branch 'dev' into RG_handle
nickhsmith Nov 8, 2022
9ab1c4c
Merge branch 'dev' into RG_handle
nickhsmith Nov 8, 2022
be5b436
Merge branch 'dev' into RG_handle
nickhsmith Nov 10, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 27 additions & 18 deletions drop/modules/rvc-pipeline/GATK_BASH/changeHeader.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,41 +18,50 @@ output_bai=$6
output_newHeader=$7


SM_internalHeader=""
PL_internalHeader=""
samtools view -H $input_bam |grep "^@RG" |grep SM |head -1|
while read header ; do
for i in $header; do
if [[ $i == "SM:"* ]]; then
internalHeader=${i:3}
break
else
internalHeader=""
SM_internalHeader=${i:3}
fi
if [[ $i == "PL:"* ]]; then
PL_internalHeader=${i:3}
fi
done

if [[ $internalHeader == $sample ]]; then
echo "Internal Header $internalHeader matches $sample" |tee $log
echo "Internal Header is designated: $internalHeader" |tee -a $log
if [[ $SM_internalHeader == $sample && $PL_internalHeader != "" ]]; then
echo "Internal Header $SM_internalHeader matches $sample" |tee $log
echo "Internal Header is designated: $SM_internalHeader" |tee -a $log
echo "SampleID is $sample" |tee -a $log
ln -f $input_bam $output_bam
ln -f $input_bai $output_bai
echo "Done Linking files"
samtools view -H $input_bam > $output_newHeader
else
echo "WARNING"
echo "Internal Header is designated: $internalHeader" |tee $log
echo "SampleID is $sample" |tee -a $log
echo "Forcing $internalHeader to match $sample" |tee -a $log

samtools view -H $input_bam > $output_newHeader
echo $output_newHeader
if [[ $SM_internalHeader != $sample ]]; then
echo "WARNING"
echo "Internal Header is designated: $SM_internalHeader" |tee $log
echo "SampleID is $sample" |tee -a $log
echo "Forcing $SM_internalHeader to match $sample" |tee -a $log

# sed using regEx in place substitiute 'SM:' followed by any thing that isn't tab or newLine. and then replace it with the sampleID and the delimiter (tab or newLine) that matched in the 1st expression.
sed -E -i "s/(SM:[^\t|\n]*)(\t|\n*)/SM:${sample}\2/" ${output_newHeader}
# sed using regEx in place substitiute 'SM:' followed by any thing that isn't tab or newLine. and then replace it with the sampleID and the delimiter (tab or newLine) that matched in the 1st expression.
samtools view -H $input_bam > $output_newHeader
sed -E -i "s/(SM:[^\t|\n]*)(\t|\n*)/SM:${sample}\2/" ${output_newHeader}
fi
if [[ $PL_internalHeader == "" ]]; then
echo "WARNING"
echo "Internal PL Header is not designated: $PL_internalHeader" |tee $log
echo "PL cannot be empty. Using a Dummy: dummyPL " |tee -a $log
echo "Forcing $PL_internalHeader to dummyPL" |tee -a $log

# sed using regEx in place substitiute '@RG' with @RG\tPL:dummyPL
samtools view -H $input_bam > $output_newHeader
sed -E -i "s/^@RG/@RG\tPL:dummyPL/" ${output_newHeader}
fi
samtools reheader $output_newHeader $input_bam > $output_bam

samtools index -b $output_bam

fi
echo "new header can be found here:$output_newHeader" |tee -a $log
done