[med-svn] [adapterremoval] 01/01: Try more adaptations to run the benchmarking suite
Andreas Tille
tille at debian.org
Wed Aug 17 08:05:39 UTC 2016
This is an automated email from the git hooks/post-receive script.
tille pushed a commit to branch master
in repository adapterremoval.
commit 4d9f5f4a403c0081b5694adc96cd0c71ceff0a75
Author: Andreas Tille <tille at debian.org>
Date: Wed Aug 17 09:59:35 2016 +0200
Try more adaptations to run the benchmarking suite
---
debian/patches/adapt-benchmarking.patch | 81 ++++++++++++++++------
.../delete_adapterremoval1x_completely.patch | 80 +++++++++++++++++++++
debian/patches/reduce_benchmark_length.patch | 4 +-
debian/patches/series | 2 +-
4 files changed, 142 insertions(+), 25 deletions(-)
diff --git a/debian/patches/adapt-benchmarking.patch b/debian/patches/adapt-benchmarking.patch
index 56e69ff..0b8562b 100644
--- a/debian/patches/adapt-benchmarking.patch
+++ b/debian/patches/adapt-benchmarking.patch
@@ -1,6 +1,16 @@
--- a/benchmark/benchmark.sh
+++ b/benchmark/benchmark.sh
-@@ -46,11 +46,13 @@ MAX_THREADS=4
+@@ -34,7 +34,8 @@ NUM_REPLICATES=10
+ # Read lengths to examine
+ # Lengths > 100 use an interpolated profile, and should therefore not be used
+ # to estimate anything other than runtime (see 'simulate_reads').
+-READ_LENGTHS=(100 200)
++# READ_LENGTHS=(100 200) # 200 is accessing specific profiles which seems not to work with pIRS 2.0 syntax
++READ_LENGTHS=(100)
+
+ # Insert sizes of reads to simulate for adapter ID
+ ADAPTER_ID_INSERT_SIZES=($(seq 250 5 350))
+@@ -46,11 +47,13 @@ MAX_THREADS=4
# Number of read (pairs) to simulate using pIRS for each replicate
SIMULATED_NREADS=1000000
@@ -19,7 +29,7 @@
###############################################################################
-@@ -84,63 +86,79 @@ function check_for_jar()
+@@ -84,63 +87,79 @@ function check_for_jar()
fi
}
@@ -122,7 +132,7 @@
check_for_executable "fastq-mcf" ${EXEC_FASTQ_MCF}
# https://code.google.com/p/ea-utils/
-@@ -149,7 +167,7 @@ EXEC_TIME=/usr/bin/time
+@@ -149,7 +168,7 @@ EXEC_TIME=/usr/bin/time
check_for_executable "GNU time" ${EXEC_TIME}
# Needed for time / RAM usage
@@ -131,7 +141,7 @@
check_for_executable "Java JRE" ${EXEC_JAVA}
# Needed for Trimmomatic
-@@ -240,14 +258,16 @@ function fetch_reference()
+@@ -240,14 +259,16 @@ function fetch_reference()
echo "------------------------------------------------------------" > /dev/stderr
echo "Fetching reference sequence ..." > /dev/stderr
@@ -151,16 +161,40 @@
fi
-@@ -286,7 +306,7 @@ function simulate_reads()
+@@ -268,7 +289,8 @@ function simulate_reads()
+ if [ "${readlen}" -gt 100 ];
+ then
+ # Use fake profiles, built using scripts/extend_profile.py
+- PROFILE_CLI="-b profiles/phixv2.InDel.matrix -s profiles/humNew.PE100.matrix.gz"
++ # PROFILE_CLI="-b profiles/phixv2.InDel.matrix -s profiles/humNew.PE100.matrix.gz"
++ PROFILE_CLI="--indel-profile=profiles/phixv2.InDel.matrix --base-calling-profile=profiles/humNew.PE100.matrix.gz"
+ else
+ PROFILE_CLI=
+ fi
+@@ -285,15 +307,19 @@ function simulate_reads()
+ rm -rf "${DST:?}/"
mkdir -p "${DST}/"
- # -c 0 = uncompressed output
+- # -c 0 = uncompressed output
- if ! ${EXEC_PIRS} simulate ${PROFILE_CLI} -x "${SIMULATED_NREADS}" -l "${readlen}" -i "${REFSEQ}" -c 0 -m "${INSERT_MEAN}" -v "${INSERT_SD}" -Q 33 -o "${DST}/reads" \
-+ if ! ${EXEC_PIRS} simulate ${PROFILE_CLI} -x "${SIMULATED_NREADS}" -l "${readlen}" "${REFSEQ}" -c gzip -m "${INSERT_MEAN}" -v "${INSERT_SD}" -Q 33 -o "${DST}/reads" \
++ # -c text = uncompressed output
++ set -x
++ if ! ${EXEC_PIRS} simulate ${PROFILE_CLI} -x "${SIMULATED_NREADS}" -l "${readlen}" "${REFSEQ}" -c text -m "${INSERT_MEAN}" -v "${INSERT_SD}" -Q 33 -o "${DST}/reads" \
> "${DST}/reads.stdout" 2> "${DST}/reads.stderr";
then
echo "Error simulated reads ..." > /dev/stderr
-@@ -813,14 +833,16 @@ function benchmark_se()
+ exit 1
+ fi
++ set +x
+
+- gunzip "${DST}/reads_${readlen}_${INSERT_MEAN}.read.info.gz"
++ if [ -e "${DST}/reads_${readlen}_${INSERT_MEAN}.read.info.gz" ] ; then
++ gunzip "${DST}/reads_${readlen}_${INSERT_MEAN}.read.info.gz"
++ fi
+ ln -sf "$(basename "${DST}")/reads_${readlen}_${INSERT_MEAN}_1.fq" "${DST}_1.fq"
+ ln -sf "$(basename "${DST}")/reads_${readlen}_${INSERT_MEAN}_2.fq" "${DST}_2.fq"
+ ln -sf "$(basename "${DST}")/reads_${readlen}_${INSERT_MEAN}.read.info" "${DST}.read.info"
+@@ -813,14 +839,16 @@ function benchmark_se()
SIMULATED_MATE1="${SIMULATED_PREFIX}_${run_n}_${readlen}_1.fq"
SIMULATED_MATE2="${SIMULATED_PREFIX}_${run_n}_${readlen}_2.fq"
SIMULATED_INFO="${SIMULATED_PREFIX}_${run_n}_${readlen}.read.info"
@@ -173,7 +207,7 @@
- "${SIMULATED_INFO}" \
- --file1 "${SIMULATED_MATE1}" \
- --mm 3
-+ if [ "${EXEC_ADAPTERREMOVAL1x}" != "" } ; then
++ if [ -z ${EXEC_ADAPTERREMOVAL1x+x} ] ; then
+ echo run_adapterremoval SE ${EXEC_ADAPTERREMOVAL1x} 1 \
+ "${RESULTS}/adapterremoval1x_mm3" \
+ "${SIMULATED_INFO}" \
@@ -183,7 +217,7 @@
# -mm 3 --minadapteroverlap 3 (test)
echo run_adapterremoval SE ${EXEC_ADAPTERREMOVAL2x} 1 \
-@@ -901,7 +923,7 @@ function benchmark_se()
+@@ -901,7 +929,7 @@ function benchmark_se()
done
done
@@ -192,7 +226,7 @@
}
-@@ -921,17 +943,19 @@ function benchmark_pe()
+@@ -921,17 +949,19 @@ function benchmark_pe()
SIMULATED_MATE1="${SIMULATED_PREFIX}_${run_n}_${readlen}_1.fq"
SIMULATED_MATE2="${SIMULATED_PREFIX}_${run_n}_${readlen}_2.fq"
SIMULATED_INFO="${SIMULATED_PREFIX}_${run_n}_${readlen}.read.info"
@@ -208,7 +242,7 @@
- --file1 "${SIMULATED_MATE1}" \
- --file2 "${SIMULATED_MATE2}" \
- --mm 3
-+ if [ "${EXEC_ADAPTERREMOVAL1x}" != "" ] ; then
++ if [ -z ${EXEC_ADAPTERREMOVAL1x+x} ] ; then
+ echo run_adapterremoval PE ${EXEC_ADAPTERREMOVAL1x} 1 \
+ "${RESULTS}/adapterremoval1x_mm3" \
+ "${SIMULATED_INFO}" \
@@ -219,7 +253,7 @@
for nthreads in $(seq 1 ${MAX_THREADS});
do
-@@ -997,7 +1021,7 @@ function benchmark_pe()
+@@ -997,7 +1027,7 @@ function benchmark_pe()
done
done
@@ -228,7 +262,7 @@
}
-@@ -1017,17 +1041,19 @@ function benchmark_collapse()
+@@ -1017,17 +1047,19 @@ function benchmark_collapse()
SIMULATED_MATE1="${SIMULATED_PREFIX}_${run_n}_${readlen}_1.fq"
SIMULATED_MATE2="${SIMULATED_PREFIX}_${run_n}_${readlen}_2.fq"
SIMULATED_INFO="${SIMULATED_PREFIX}_${run_n}_${readlen}.read.info"
@@ -244,7 +278,7 @@
- --file1 "${SIMULATED_MATE1}" \
- --file2 "${SIMULATED_MATE2}" \
- --mm 3 --collapse
-+ if [ "${EXEC_ADAPTERREMOVAL1x}" != "" ] ; then
++ if [ -z ${EXEC_ADAPTERREMOVAL1x+x} ] ; then
+ echo run_adapterremoval COLLAPSE ${EXEC_ADAPTERREMOVAL1x} 1 \
+ "${RESULTS}/adapterremoval1x_mm3" \
+ "${SIMULATED_INFO}" \
@@ -255,7 +289,7 @@
for nthreads in $(seq 1 ${MAX_THREADS});
do
-@@ -1063,7 +1089,7 @@ function benchmark_collapse()
+@@ -1063,7 +1095,7 @@ function benchmark_collapse()
done
done
@@ -264,7 +298,7 @@
}
-@@ -1084,7 +1110,7 @@ function benchmark_mixed_se
+@@ -1084,7 +1116,7 @@ function benchmark_mixed_se
SIMULATED_MATE1="${SIMULATED_MIXED_PREFIX}_${run_n}_${readlen}_1.fq"
SIMULATED_MATE2="${SIMULATED_MIXED_PREFIX}_${run_n}_${readlen}_2.fq"
SIMULATED_INFO="${SIMULATED_MIXED_PREFIX}_${run_n}_${readlen}.read.info"
@@ -273,7 +307,7 @@
DEFAULT_ARGS=("${SIMULATED_INFO}" "${SIMULATED_MATE1}" "${SIMULATED_MATE2}")
AR_PREFIX="${RESULTS}/adapterremoval2x"
-@@ -1139,7 +1165,7 @@ function benchmark_mixed_se
+@@ -1139,7 +1171,7 @@ function benchmark_mixed_se
done
done
@@ -282,7 +316,7 @@
}
-@@ -1159,7 +1185,7 @@ function benchmark_mixed_pe
+@@ -1159,7 +1191,7 @@ function benchmark_mixed_pe
SIMULATED_MATE1="${SIMULATED_MIXED_PREFIX}_${run_n}_${readlen}_1.fq"
SIMULATED_MATE2="${SIMULATED_MIXED_PREFIX}_${run_n}_${readlen}_2.fq"
SIMULATED_INFO="${SIMULATED_MIXED_PREFIX}_${run_n}_${readlen}.read.info"
@@ -291,7 +325,7 @@
DEFAULT_ARGS=("${SIMULATED_INFO}" "${SIMULATED_MATE1}" "${SIMULATED_MATE2}")
-@@ -1204,7 +1230,7 @@ function benchmark_mixed_pe
+@@ -1204,7 +1236,7 @@ function benchmark_mixed_pe
done
done
@@ -300,7 +334,7 @@
}
-@@ -1224,7 +1250,7 @@ function benchmark_adapter_id
+@@ -1224,7 +1256,7 @@ function benchmark_adapter_id
SIMULATED_MATE1="${SIMULATED_ADAPTER_ID_PREFIX}_${run_n}_${readlen}_${INSERT_MEAN}_1.fq"
SIMULATED_MATE2="${SIMULATED_ADAPTER_ID_PREFIX}_${run_n}_${readlen}_${INSERT_MEAN}_2.fq"
SIMULATED_INFO="${SIMULATED_ADAPTER_ID_PREFIX}_${run_n}_${readlen}_${INSERT_MEAN}.read.info"
@@ -309,7 +343,7 @@
run_minion "${RESULTS}/minion" \
"${SIMULATED_MATE1}" \
-@@ -1236,13 +1262,14 @@ function benchmark_adapter_id
+@@ -1236,15 +1268,17 @@ function benchmark_adapter_id
done
done
@@ -325,4 +359,7 @@
+#mkdir -p results
fetch_reference
++cp -a profiles $results
+
+ echo > /dev/stderr
diff --git a/debian/patches/delete_adapterremoval1x_completely.patch b/debian/patches/delete_adapterremoval1x_completely.patch
new file mode 100644
index 0000000..f030db7
--- /dev/null
+++ b/debian/patches/delete_adapterremoval1x_completely.patch
@@ -0,0 +1,80 @@
+--- a/benchmark/benchmark.sh
++++ b/benchmark/benchmark.sh
+@@ -843,15 +843,6 @@ function benchmark_se()
+ SIMULATED_INFO="${SIMULATED_PREFIX}_${run_n}_${readlen}.read.info"
+ RESULTS="$results/se/${readlen}_${run_n}"
+
+- # -mm 3 corresponds to AR 2.x defaults
+- if [ -z ${EXEC_ADAPTERREMOVAL1x+x} ] ; then
+- echo run_adapterremoval SE ${EXEC_ADAPTERREMOVAL1x} 1 \
+- "${RESULTS}/adapterremoval1x_mm3" \
+- "${SIMULATED_INFO}" \
+- --file1 "${SIMULATED_MATE1}" \
+- --mm 3
+- fi
+-
+ # -mm 3 --minadapteroverlap 3 (test)
+ echo run_adapterremoval SE ${EXEC_ADAPTERREMOVAL2x} 1 \
+ "${RESULTS}/adapterremoval2x_min3_mm3" \
+@@ -912,16 +903,18 @@ function benchmark_se()
+ -c "adapters/adapter_1.txt" \
+ -q 0
+
+- echo run_leeHom SE \
+- "${RESULTS}/leeHom" \
+- "${SIMULATED_INFO}" \
+- -fq1 "${SIMULATED_MATE1}"
++ if [ -z ${EXEC_LEEHOM+x} ]; then
++ echo run_leeHom SE \
++ "${RESULTS}/leeHom" \
++ "${SIMULATED_INFO}" \
++ -fq1 "${SIMULATED_MATE1}"
+
+- echo run_leeHom SE \
+- "${RESULTS}/leeHom_ancient" \
+- "${SIMULATED_INFO}" \
+- -fq1 "${SIMULATED_MATE1}" \
+- --ancientdna
++ echo run_leeHom SE \
++ "${RESULTS}/leeHom_ancient" \
++ "${SIMULATED_INFO}" \
++ -fq1 "${SIMULATED_MATE1}" \
++ --ancientdna
++ fi
+
+ echo run_fastq_mcf_se "${RESULTS}/fastq_mcf" \
+ "${SIMULATED_INFO}" \
+@@ -955,16 +948,6 @@ function benchmark_pe()
+
+ DEFAULT_ARGS=("${SIMULATED_INFO}" "${SIMULATED_MATE1}" "${SIMULATED_MATE2}")
+
+- # -mm 3 corresponds to AR 2.x defaults
+- if [ -z ${EXEC_ADAPTERREMOVAL1x+x} ] ; then
+- echo run_adapterremoval PE ${EXEC_ADAPTERREMOVAL1x} 1 \
+- "${RESULTS}/adapterremoval1x_mm3" \
+- "${SIMULATED_INFO}" \
+- --file1 "${SIMULATED_MATE1}" \
+- --file2 "${SIMULATED_MATE2}" \
+- --mm 3
+- fi
+-
+ for nthreads in $(seq 1 ${MAX_THREADS});
+ do
+ AR_PREFIX="${RESULTS}/adapterremoval2x"
+@@ -1053,16 +1036,6 @@ function benchmark_collapse()
+
+ DEFAULT_ARGS=("${SIMULATED_INFO}" "${SIMULATED_MATE1}" "${SIMULATED_MATE2}")
+
+- # -mm 3 corresponds to AR 2.x defaults
+- if [ -z ${EXEC_ADAPTERREMOVAL1x+x} ] ; then
+- echo run_adapterremoval COLLAPSE ${EXEC_ADAPTERREMOVAL1x} 1 \
+- "${RESULTS}/adapterremoval1x_mm3" \
+- "${SIMULATED_INFO}" \
+- --file1 "${SIMULATED_MATE1}" \
+- --file2 "${SIMULATED_MATE2}" \
+- --mm 3 --collapse
+- fi
+-
+ for nthreads in $(seq 1 ${MAX_THREADS});
+ do
+ AR_PREFIX="${RESULTS}/adapterremoval2x"
diff --git a/debian/patches/reduce_benchmark_length.patch b/debian/patches/reduce_benchmark_length.patch
index 4b0c8f0..2f35199 100644
--- a/debian/patches/reduce_benchmark_length.patch
+++ b/debian/patches/reduce_benchmark_length.patch
@@ -1,6 +1,6 @@
--- a/benchmark/benchmark.sh
+++ b/benchmark/benchmark.sh
-@@ -44,7 +44,7 @@ ADAPTER_ID_INSERT_SIZES=($(seq 250 5 350
+@@ -45,7 +45,7 @@ ADAPTER_ID_INSERT_SIZES=($(seq 250 5 350
MAX_THREADS=4
# Number of read (pairs) to simulate using pIRS for each replicate
@@ -9,7 +9,7 @@
results=$(mktemp -d /tmp/adapter-benchmark.XXXXXX)
echo "*** Results will be found in $results ***"
-@@ -266,8 +266,10 @@ function fetch_reference()
+@@ -267,8 +267,10 @@ function fetch_reference()
echo "" > /dev/stderr
# wget -O $results/reference.fasta.gz http://hgdownload.soe.ucsc.edu/goldenPath/hg38/chromosomes/chr1.fa.gz
# gunzip $results/reference.fasta.gz
diff --git a/debian/patches/series b/debian/patches/series
index ec30ca0..bcaa682 100644
--- a/debian/patches/series
+++ b/debian/patches/series
@@ -1,4 +1,4 @@
hardening.patch
adapt-benchmarking.patch
reduce_benchmark_length.patch
-do_not_gunzip.patch
+delete_adapterremoval1x_completely.patch
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-med/adapterremoval.git
More information about the debian-med-commit
mailing list