Skip to content

Commit 64e52ba

Browse files
author
OLIVIA LANG
committed
add PBS scripts for simulating sid human
The set of human simulation PBS job submission scripts are added here across K562 and HELA strains at depths of 1M, 2M, 5M, 10M, and 20M.
1 parent 1a579c0 commit 64e52ba

12 files changed

Lines changed: 363 additions & 0 deletions

‎paper/.gitignore‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -25,3 +25,4 @@ SyntheticStrain/synthetic_genome/
2525
SyntheticStrain/logs/*.err-*
2626
SyntheticStrain/logs/*.out-*
2727
SyntheticStrain/results/sacCer3*
28+
SyntheticStrain/results/hg19*

‎paper/SyntheticStrain/depth_simulations.txt‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -18,4 +18,6 @@ hg19_K562 20M 16000
1818
hg19_HELA 1M 17000
1919
hg19_HELA 2M 18000
2020
hg19_HELA 5M 19000
21+
hg19_HELA 10M 20000
22+
hg19_HELA 20M 21000
2123

‎paper/SyntheticStrain/job/run_depth_HELA_10M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=01:30:00
5+
#PBS -A open
6+
#PBS -o logs/depth.HELA.10M.log.out
7+
#PBS -e logs/depth.HELA.10M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "21q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

‎paper/SyntheticStrain/job/run_depth_HELA_1M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=00:10:00
5+
#PBS -A open
6+
#PBS -o logs/depth.HELA.1M.log.out
7+
#PBS -e logs/depth.HELA.1M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "18q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

‎paper/SyntheticStrain/job/run_depth_HELA_20M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=03:00:00
5+
#PBS -A open
6+
#PBS -o logs/depth.HELA.20M.log.out
7+
#PBS -e logs/depth.HELA.20M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "22q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

‎paper/SyntheticStrain/job/run_depth_HELA_2M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=00:40:00
5+
#PBS -A open
6+
#PBS -o logs/depth.HELA.2M.log.out
7+
#PBS -e logs/depth.HELA.2M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "19q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

‎paper/SyntheticStrain/job/run_depth_HELA_5M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=00:40:00
5+
#PBS -A open
6+
#PBS -o logs/depth.HELA.5M.log.out
7+
#PBS -e logs/depth.HELA.5M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "20q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

‎paper/SyntheticStrain/job/run_depth_K562_10M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=01:30:00
5+
#PBS -A open
6+
#PBS -o logs/depth.K562.10M.log.out
7+
#PBS -e logs/depth.K562.10M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "16q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

‎paper/SyntheticStrain/job/run_depth_K562_1M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=00:10:00
5+
#PBS -A open
6+
#PBS -o logs/depth.K562.1M.log.out
7+
#PBS -e logs/depth.K562.1M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "13q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

‎paper/SyntheticStrain/job/run_depth_K562_20M.pbs‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
#!/bin/bash
2+
#PBS -l nodes=1:ppn=4
3+
#PBS -l pmem=16gb
4+
#PBS -l walltime=03:00:00
5+
#PBS -A open
6+
#PBS -o logs/depth.K562.20M.log.out
7+
#PBS -e logs/depth.K562.20M.log.err
8+
#PBS -t 1-1000
9+
10+
# FIRST CHANGE PATH TO EXECUTE
11+
WRK=/path/to/GenoPipe/paper/SyntheticStrain
12+
cd $WRK
13+
14+
module load gcc/8.3.1
15+
module load bedtools/2.27.1
16+
module load bwa/0.7.15
17+
module load samtools/1.5
18+
module load anaconda3
19+
source activate genopipe
20+
21+
INFO=`sed "17q;d" depth_simulations.txt`
22+
STRAIN=`awk '{print $1}' <(echo $INFO)`
23+
DEPTH=`awk '{print $2}' <(echo $INFO)`
24+
BASE=`awk '{print $3}' <(echo $INFO)`
25+
REF=`awk -F"_" '{print $1}' <(echo $STRAIN)`
26+
27+
GENOME=synthetic_genome/$STRAIN.fa
28+
OUTPUT=results/$STRAIN\_$DEPTH
29+
SEED=$(($BASE+$PBS_ARRAYID))
30+
31+
start=`date +%s`
32+
bash ../scripts/simulate.sh -i $PBS_ARRAYID -d $DEPTH -s $SEED -g $GENOME -o $OUTPUT
33+
bash ../scripts/align.sh -i $PBS_ARRAYID -g ../input/$REF.fa -o $OUTPUT -t 4
34+
end=`date +%s`
35+
runtime=$((end-start))
36+
echo "${STRAIN} ${DEPTH} simulate in ${runtime}"

0 commit comments

Comments
 (0)