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

Quote spaces in names #208

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Quote spaces in names #208

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
88a80f1
specify tab separator for RG header
ernfrid Aug 31, 2017
ba4719e
use an array to get quoting right when sample ids have spaces
ernfrid Aug 31, 2017
30410cb
lumpyexpress tests. Needs data.
ernfrid Sep 2, 2017
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
18 changes: 18 additions & 0 deletions lumpy_tests/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,3 +151,21 @@ assert_equal 5 $(zgrep -cv ^# trio.vcf)
assert_equal 5 $(zgrep -cv ^# trio.svtyped.vcf.gz)

cd ..


cd lumpyexpress

rm -f ./*.vcf
run lumpyexpress ../../scripts/lumpyexpress -B NA12878.bam -S NA12878.split.bam -D NA12878.disc.bam -o NA12878.vcf
assert_exit_code 0
assert_equal \
0 \
$(diff <(grep -v '^#' NA12878.vcf.o ) <(grep -v '^#' NA12878.vcf) | wc -l)

run lumpyexpress ../../scripts/lumpyexpress -B NA12878.w_space.bam -S NA12878.w_space.split.bam -D NA12878.w_space.disc.bam -o NA12878.w_space.vcf
assert_exit_code 0
assert_equal \
0 \
$(diff <(grep -v '^#' NA12878.vcf.o ) <(grep -v '^#' NA12878.w_space.vcf) | wc -l)

cd ..
26 changes: 14 additions & 12 deletions scripts/lumpyexpress
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,6 +331,8 @@ trap cleanup EXIT
# If splitter and discordant BAMs not provided, generate them
# (LUMPY express)
set +o nounset
LUMPY_SPL_STRING=()
LUMPY_DISC_STRING=()
if [[ -z "${SPL_BAM_LIST}${DISC_BAM_LIST}" ]]
then
# initialize split and discordant bam lists
Expand Down Expand Up @@ -401,16 +403,16 @@ then

# generate discordant pair string for LUMPY
DISC_BAM=$TEMP_DIR/$OUTBASE.sample$(($i+1)).discordants.bam
DISC_SAMPLE=`$SAMT view $EXT_OPT -H $FULL_BAM | grep -m 1 "^@RG" | gawk -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
DISC_SAMPLE=`$SAMT view $EXT_OPT -H $FULL_BAM | grep -m 1 "^@RG" | gawk -F "\t" -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
RG_STRING=`echo "${LIB_RG_LIST[$j]}" | sed 's/,/,read_group:/g' | sed 's/^/read_group:/g'`
MEAN=`cat ${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).insert.stats | tr '\t' '\n' | grep "^mean" | sed 's/mean\://g'`
STDEV=`cat ${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).insert.stats | tr '\t' '\n' | grep "^stdev" | sed 's/stdev\://g'`
LUMPY_DISC_STRING="$LUMPY_DISC_STRING -pe bam_file:${DISC_BAM},histo_file:${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).x4.histo,mean:${MEAN},stdev:${STDEV},read_length:${READ_LENGTH},min_non_overlap:${READ_LENGTH},discordant_z:5,back_distance:10,weight:1,id:${DISC_SAMPLE},min_mapping_threshold:20,${RG_STRING}"
LUMPY_DISC_STRING+=("-pe" "bam_file:${DISC_BAM},histo_file:${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).x4.histo,mean:${MEAN},stdev:${STDEV},read_length:${READ_LENGTH},min_non_overlap:${READ_LENGTH},discordant_z:5,back_distance:10,weight:1,id:${DISC_SAMPLE},min_mapping_threshold:20,${RG_STRING}")

# generate split-read string for LUMPY
SPL_BAM=$TEMP_DIR/$OUTBASE.sample$(($i+1)).splitters.bam
SPL_SAMPLE=`$SAMT view $EXT_OPT -H $FULL_BAM | grep -m 1 "^@RG" | gawk -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
LUMPY_SPL_STRING="$LUMPY_SPL_STRING -sr bam_file:${SPL_BAM},back_distance:10,min_mapping_threshold:20,weight:1,id:${SPL_SAMPLE},min_clip:20,${RG_STRING}"
SPL_SAMPLE=`$SAMT view $EXT_OPT -H $FULL_BAM | grep -m 1 "^@RG" | gawk -F "\t" -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
LUMPY_SPL_STRING+=("-sr" "bam_file:${SPL_BAM},back_distance:10,min_mapping_threshold:20,weight:1,id:${SPL_SAMPLE},min_clip:20,${RG_STRING}")
done

# merge the splitters and discordants files
Expand Down Expand Up @@ -487,22 +489,22 @@ else
echo "done"

# construct LUMPY_SPL_STRING
SPL_SAMPLE=`$SAMT view -H $SPL_BAM | grep -m 1 "^@RG" | gawk -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
LUMPY_SPL_STRING="$LUMPY_SPL_STRING -sr bam_file:${SPL_BAM},back_distance:10,min_mapping_threshold:20,weight:1,id:${SPL_SAMPLE},min_clip:20"
SPL_SAMPLE=`$SAMT view -H $SPL_BAM | grep -m 1 "^@RG" | gawk -F "\t" -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
LUMPY_SPL_STRING+=("-sr" "bam_file:${SPL_BAM},back_distance:10,min_mapping_threshold:20,weight:1,id:${SPL_SAMPLE},min_clip:20")

# construct LUMPY_DISC_STRING
for j in $( seq 0 $(( ${#LIB_RG_LIST[@]}-1 )) )
do
echo $(( ${#FULL_BAM_LIST[@]}-1 ))
DISC_BAM=${DISC_BAM_LIST[$i]}
DISC_SAMPLE=`$SAMT view -H $DISC_BAM | grep -m 1 "^@RG" | gawk -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
DISC_SAMPLE=`$SAMT view -H $DISC_BAM | grep -m 1 "^@RG" | gawk -F "\t" -v i=$i '{ for (j=1;j<=NF;++j) {if ($j~"^SM:") { gsub("^SM:","",$j); print $j } } }'`
MEAN=`cat ${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).insert.stats | tr '\t' '\n' | grep "^mean" | sed 's/mean\://g'`
STDEV=`cat ${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).insert.stats | tr '\t' '\n' | grep "^stdev" | sed 's/stdev\://g'`
RG_STRING=`echo "${LIB_RG_LIST[$j]}" | sed 's/,/,read_group:/g' | sed 's/^/read_group:/g'`

if [[ "$MEAN" != "NA" ]] && [[ "$STDEV" != "NA" ]]
then
LUMPY_DISC_STRING="$LUMPY_DISC_STRING -pe bam_file:${DISC_BAM},histo_file:${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).x4.histo,mean:${MEAN},stdev:${STDEV},read_length:${LIB_READ_LENGTH_LIST[$j]},min_non_overlap:${LIB_READ_LENGTH_LIST[$j]},discordant_z:5,back_distance:10,weight:1,id:${DISC_SAMPLE},min_mapping_threshold:20,${RG_STRING}"
LUMPY_DISC_STRING+=("-pe" "bam_file:${DISC_BAM},histo_file:${TEMP_DIR}/$OUTBASE.sample$(($i+1)).lib$(($j+1)).x4.histo,mean:${MEAN},stdev:${STDEV},read_length:${LIB_READ_LENGTH_LIST[$j]},min_non_overlap:${LIB_READ_LENGTH_LIST[$j]},discordant_z:5,back_distance:10,weight:1,id:${DISC_SAMPLE},min_mapping_threshold:20,${RG_STRING}")
fi
done
done
Expand Down Expand Up @@ -534,17 +536,17 @@ $LUMPY ${PROB_CURVE} \\
-tt $TRIM_THRES \\
$LUMPY_DEPTH_STRING \\
$EXCLUDE_BED_FMT \\
$LUMPY_DISC_STRING \\
$LUMPY_SPL_STRING \\
"${LUMPY_DISC_STRING[@]}" \\
"${LUMPY_SPL_STRING[@]}" \\
> $OUTPUT"
fi
# call lumpy
$LUMPY $PROB_CURVE -t ${TEMP_DIR}/${OUTBASE} -msw $MIN_SAMPLE_WEIGHT -tt $TRIM_THRES \
$LUMPY_DEPTH_STRING \
$EXCLUDE_BED_FMT \
$LUMPY_DISC_STRING \
"${LUMPY_DISC_STRING[@]}" \
$EXCLUDE_BED_FMT \
$LUMPY_SPL_STRING \
"${LUMPY_SPL_STRING[@]}" \
> $OUTPUT

# clean up
Expand Down