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

fix VariantCalling for Unknown genders + bugfixing #458

Merged
merged 1 commit into from
Mar 11, 2016
Merged

fix VariantCalling for Unknown genders + bugfixing #458

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions compute5/NGS_DNA/protocols/CheckIlluminaEncoding.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ checkIlluminaEncoding() {
barcodeFqGz=$1
echo ${barcodeFqGz}

lines=(`zcat ${barcodeFqGz} | head -96 | awk 'NR % 4 == 0'`)
lines=(`zcat ${barcodeFqGz} | head -8000 | tail -192 | awk 'NR % 4 == 0'`)
count=1
nodecision=0
numberoflines=0
Expand Down Expand Up @@ -80,7 +80,7 @@ else
gzip -d -c ${barcodeFqGz} > ${barcodeFqGz}.fq
mkdir -p ${projectRawTmpDataDir}/IlluminaEncoding1.5
mv ${barcodeFqGz} ${projectRawTmpDataDir}/IlluminaEncoding1.5/

echo "start encoding for ${barcodeFqGz}.fq"
#convert Phreds+64 to Phred+33 (Illumna 1.5 TO Illumina / Sanger 1.9)
sed -e '4~4y/@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghi/!"#$%&'\''()*+,-.\/0123456789:;<=>?@ABCDEFGHIJ/' ${barcodeFqGz}.fq > ${barcodeFqGz}.fq.encoded
gzip ${barcodeFqGz}.fq.encoded
Expand Down
31 changes: 16 additions & 15 deletions compute5/NGS_DNA/protocols/CreateExternSamplesProjects.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,8 @@
#list sequencer
#list run
#list flowcell
#list externalFastQ
#list externalFastQ_1
#list externalFastQ_2

#string mainParameters
#string worksheet
Expand Down Expand Up @@ -64,25 +65,25 @@ do
then
if [[ ${barcode[samplenumber]} == "None" ]]
then
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
else
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
fi
elif [[ ${seqType[samplenumber]} == "PE" ]]
then
if [[ ${barcode[samplenumber]} == "None" ]]
then
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz.md5
else
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.md5
fi
fi
done
Expand All @@ -91,7 +92,7 @@ cd $ROCKETPOINT

echo "before splitting"
echo `pwd`
module load NGS_DNA/$ngsversion
module load $ngsversion
module load ${ngsUtilsVersion}

#
Expand All @@ -118,7 +119,7 @@ echo "before run second rocket"
echo pwd

sh ${EBROOTMOLGENISMINCOMPUTE}/molgenis_compute.sh -p ${mainParameters} \
-p environment_parameters \
-p ${environment_parameters} \
-p ${batchIDList} \
-p ${projectJobsDir}/${project}.csv \
-rundir ${projectJobsDir} \
Expand Down
2 changes: 1 addition & 1 deletion compute5/NGS_DNA/protocols/VariantGVCFCalling.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,7 @@ else
elif [[ "${capturedBatchBed}" == *batch-[0-9]*Y.bed ]]
then
echo "Y"
if [ "${sex}" == "Female" ]
if [[ "${sex}" == "Female" || "${sex}" == "Unknown" ]]
then
java -Xmx12g -XX:ParallelGCThreads=2 -Djava.io.tmpdir=${tempDir} -jar \
${EBROOTGATK}/${gatkJar} \
Expand Down
2 changes: 1 addition & 1 deletion compute5/NGS_DNA/samplesize.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,5 +11,5 @@ do
count=$((count + 1))
done

cat $DIR/countRows.txt | uniq | wc -l
cat $DIR/countRows.txt | sort-V | uniq | wc -l
rm $DIR/countRows.txt