Validation DelID using Simulated Synthetic Deletion data

paper/.gitignore

@@ -13,6 +13,8 @@ SyntheticEpitope/logs/*.err-*
 SyntheticEpitope/logs/*.out-*
 SyntheticStrain/logs/*.err-*
 SyntheticStrain/logs/*.out-*
+YKOC-wgs/logs/*.err-*
+YKOC-wgs/logs/*.out-*
 ENCODEdata-eGFP/logs/*.out-*
 ENCODEdata-eGFP/logs/*.err-*
 ENCODEdata-eGFP/results/FASTQ

paper/SyntheticDeletion/depth_simulations.txt

@@ -1,18 +1,12 @@
-sacCer3_Reb1	10K	0
-sacCer3_Reb1	100K	1000
-sacCer3_Reb1	1M	2000
-sacCer3_Reb1	10M	3000
-sacCer3_Rap1	10K	4000
-sacCer3_Rap1	100K	5000
-sacCer3_Rap1	1M	6000
-sacCer3_Rap1	10M	7000
-sacCer3_Reb1	2M	8000	
-sacCer3_Rap1	2M	9000
-#hg19_CTCF	100K	8000
-#hg19_CTCF	1M	9000
-#hg19_CTCF	10M	10000
-#hg19_CTCF	50M	11000
-#hg19_POLR2H	100K	12000
-#hg19_POLR2H	1M	13000
-#hg19_POLR2H	10M	14000
-#hg19_POLR2H	50M	15000
+sacCer3_Rap1	500K	0
+sacCer3_Rap1	1M	1000
+sacCer3_Rap1	2M	2000
+sacCer3_Rap1	3M	3000
+sacCer3_Rap1	4M	4000
+sacCer3_Rap1	5M	5000
+sacCer3_Reb1	500K	6000
+sacCer3_Reb1	1M	7000
+sacCer3_Reb1	2M	8000
+sacCer3_Reb1	3M	9000
+sacCer3_Reb1	4M	10000
+sacCer3_Reb1	5M	11000

paper/SyntheticDeletion/fig3a_config.txt

@@ -0,0 +1,15 @@
+DEPTH_ORDER	500K	1M	2M	3M	4M	5M
+STRAIN_COLOR	Rap1-del	darkorange
+STRAIN_COLOR	Reb1-del	purple
+results/RAP1_500K_tally.txt	Rap1-del	500K
+results/RAP1_1M_tally.txt	Rap1-del	1M
+results/RAP1_2M_tally.txt	Rap1-del	2M
+results/RAP1_3M_tally.txt	Rap1-del	3M
+results/RAP1_4M_tally.txt	Rap1-del	4M
+results/RAP1_5M_tally.txt	Rap1-del	5M
+results/REB1_500K_tally.txt	Reb1-del	500K
+results/REB1_1M_tally.txt	Reb1-del	1M
+results/REB1_2M_tally.txt	Reb1-del	2M
+results/REB1_3M_tally.txt	Reb1-del	3M
+results/REB1_4M_tally.txt	Reb1-del	4M
+results/REB1_5M_tally.txt	Reb1-del	5M

paper/SyntheticDeletion/fig3b_config.txt

@@ -0,0 +1,15 @@
+DEPTH_ORDER	500K	1M	2M	3M	4M	5M
+STRAIN_COLOR	Rap1-del	darkorange
+STRAIN_COLOR	Reb1-del	purple
+RAP1_500K_runtime.txt	Rap1-del	500K
+RAP1_1M_runtime.txt	Rap1-del	1M
+RAP1_2M_runtime.txt	Rap1-del	2M
+RAP1_3M_runtime.txt	Rap1-del	3M
+RAP1_4M_runtime.txt	Rap1-del	4M
+RAP1_5M_runtime.txt	Rap1-del	5M
+REB1_500K_runtime.txt	Reb1-del	500K
+REB1_1M_runtime.txt	Reb1-del	1M
+REB1_2M_runtime.txt	Reb1-del	2M
+REB1_3M_runtime.txt	Reb1-del	3M
+REB1_4M_runtime.txt	Reb1-del	4M
+REB1_5M_runtime.txt	Reb1-del	5M

paper/SyntheticDeletion/job/make_figs.sh

@@ -0,0 +1,2 @@
+python scripts/make_barplot.py -c fig3a_config.txt -t Figure3A
+python scripts/make_boxplot.py -c fig3b_config.txt -t Figure3B

paper/SyntheticDeletion/job/run_DeletionID_on_Rap1_1M.pbs

@@ -0,0 +1,74 @@
+#!/bin/bash
+#PBS -l nodes=1:ppn=4
+#PBS -l pmem=16gb
+#PBS -l walltime=00:10:00
+#PBS -A open
+#PBS -o logs/depth.did.Rap1.1M.log.out
+#PBS -e logs/depth.did.Rap1.1M.log.err
+#PBS -t 1-1000
+
+# This script will check that 1000 BAM files have been generated before executing DeletionID.
+
+module load gcc/8.3.1
+module load bedtools/2.27.1
+module load bwa/0.7.15
+module load samtools/1.5
+module load anaconda3
+source activate genopipe
+
+# FIRST CHANGE PATH TO EXECUTE
+WRK=/path/to/GenoPipe/paper/SyntheticDeletion
+cd $WRK
+
+INFO=`sed "2q;d" depth_simulations.txt`
+LOCUS=`awk '{print $1}'  <(echo $INFO)`
+DEPTH=`awk '{print $2}'  <(echo $INFO)`
+
+REF=`echo $LOCUS | awk -F'_' '{print $1}'`
+
+OUTPUT=$WRK/results/$LOCUS\_$DEPTH
+BAM=$WRK/results/$LOCUS\_$DEPTH/BAM
+TEMP=$WRK/temp2-$PBS_ARRAYID
+
+[ -d $OUTPUT/ID ] || mkdir $OUTPUT/ID
+[ -d logs ] || mkdir logs
+[ -d $ID ] || mkdir $ID
+[ -d $TEMP ] || mkdir $TEMP
+
+#Check that BAM file was generated first
+if [ -f $BAM.bam ];
+then
+	echo "BAM input for ${LOCUS}_${DEPTH}_${PBS_ARRAYID} does not exist. Exiting."
+	exit
+fi
+#Check that BAM Index file exists
+if [ -f $BAM.bam.bai ];
+then
+	echo "BAI missing for for ${LOCUS}_${DEPTH}_${PBS_ARRAYID}. Exiting."
+	exit
+fi
+#Check if ID file alrady generated
+#if [[ -f $ID/Simulation_$PBS_ARRAYID\_R1-ID.tab ]]; then
+#	echo "ID already generated ($PBS_ARRAYID). Exiting.."
+#	exit
+#fi
+
+# Set-up Temp directory
+cd $TEMP
+echo $BAM
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam.bai
+
+DATABASE=$WRK/../db/sacCer3_Del
+GENOPIPE=$WRK/../..
+
+## Execute Single DeletionID and record time
+cd $GENOPIPE/DeletionID
+echo "**Begin executing DeletionID for ${LOCUS}_${DEPTH}..."
+time bash identify-Deletion.sh -i $TEMP -o $OUTPUT/ID -d $DATABASE
+MESSAGE="...single DeletionID for ${LOCUS} ${DEPTH} finished."
+echo $MESSAGE
+cd $WRK
+
+## Clean-up
+rm -r $TEMP

paper/SyntheticDeletion/job/run_DeletionID_on_Rap1_2M.pbs

@@ -0,0 +1,74 @@
+#!/bin/bash
+#PBS -l nodes=1:ppn=4
+#PBS -l pmem=16gb
+#PBS -l walltime=00:10:00
+#PBS -A open
+#PBS -o logs/depth.did.Rap1.2M.log.out
+#PBS -e logs/depth.did.Rap1.2M.log.err
+#PBS -t 1-1000
+
+# This script will check that 1000 BAM files have been generated before executing DeletionID.
+
+module load gcc/8.3.1
+module load bedtools/2.27.1
+module load bwa/0.7.15
+module load samtools/1.5
+module load anaconda3
+source activate genopipe
+
+# FIRST CHANGE PATH TO EXECUTE
+WRK=/path/to/GenoPipe/paper/SyntheticDeletion
+cd $WRK
+
+INFO=`sed "3q;d" depth_simulations.txt`
+LOCUS=`awk '{print $1}'  <(echo $INFO)`
+DEPTH=`awk '{print $2}'  <(echo $INFO)`
+
+REF=`echo $LOCUS | awk -F'_' '{print $1}'`
+
+OUTPUT=$WRK/results/$LOCUS\_$DEPTH
+BAM=$WRK/results/$LOCUS\_$DEPTH/BAM
+TEMP=$WRK/temp3-$PBS_ARRAYID
+
+[ -d $OUTPUT/ID ] || mkdir $OUTPUT/ID
+[ -d logs ] || mkdir logs
+[ -d $ID ] || mkdir $ID
+[ -d $TEMP ] || mkdir $TEMP
+
+#Check that BAM file was generated first
+if [ -f $BAM.bam ];
+then
+	echo "BAM input for ${LOCUS}_${DEPTH}_${PBS_ARRAYID} does not exist. Exiting."
+	exit
+fi
+#Check that BAM Index file exists
+if [ -f $BAM.bam.bai ];
+then
+	echo "BAI missing for for ${LOCUS}_${DEPTH}_${PBS_ARRAYID}. Exiting."
+	exit
+fi
+#Check if ID file alrady generated
+#if [[ -f $ID/Simulation_$PBS_ARRAYID\_R1-ID.tab ]]; then
+#	echo "ID already generated ($PBS_ARRAYID). Exiting.."
+#	exit
+#fi
+
+# Set-up Temp directory
+cd $TEMP
+echo $BAM
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam.bai
+
+DATABASE=$WRK/../db/sacCer3_Del
+GENOPIPE=$WRK/../..
+
+## Execute Single DeletionID and record time
+cd $GENOPIPE/DeletionID
+echo "**Begin executing DeletionID for ${LOCUS}_${DEPTH}..."
+time bash identify-Deletion.sh -i $TEMP -o $OUTPUT/ID -d $DATABASE
+MESSAGE="...single DeletionID for ${LOCUS} ${DEPTH} finished."
+echo $MESSAGE
+cd $WRK
+
+## Clean-up
+rm -r $TEMP

paper/SyntheticDeletion/job/run_DeletionID_on_Rap1_3M.pbs

@@ -0,0 +1,74 @@
+#!/bin/bash
+#PBS -l nodes=1:ppn=4
+#PBS -l pmem=16gb
+#PBS -l walltime=00:20:00
+#PBS -A open
+#PBS -o logs/depth.did.Rap1.3M.log.out
+#PBS -e logs/depth.did.Rap1.3M.log.err
+#PBS -t 1-1000
+
+# This script will check that 1000 BAM files have been generated before executing DeletionID.
+
+module load gcc/8.3.1
+module load bedtools/2.27.1
+module load bwa/0.7.15
+module load samtools/1.5
+module load anaconda3
+source activate genopipe
+
+# FIRST CHANGE PATH TO EXECUTE
+WRK=/path/to/GenoPipe/paper/SyntheticDeletion
+cd $WRK
+
+INFO=`sed "4q;d" depth_simulations.txt`
+LOCUS=`awk '{print $1}'  <(echo $INFO)`
+DEPTH=`awk '{print $2}'  <(echo $INFO)`
+
+REF=`echo $LOCUS | awk -F'_' '{print $1}'`
+
+OUTPUT=$WRK/results/$LOCUS\_$DEPTH
+BAM=$WRK/results/$LOCUS\_$DEPTH/BAM
+TEMP=$WRK/temp4-$PBS_ARRAYID
+
+[ -d $OUTPUT/ID ] || mkdir $OUTPUT/ID
+[ -d logs ] || mkdir logs
+[ -d $ID ] || mkdir $ID
+[ -d $TEMP ] || mkdir $TEMP
+
+#Check that BAM file was generated first
+if [ -f $BAM.bam ];
+then
+	echo "BAM input for ${LOCUS}_${DEPTH}_${PBS_ARRAYID} does not exist. Exiting."
+	exit
+fi
+#Check that BAM Index file exists
+if [ -f $BAM.bam.bai ];
+then
+	echo "BAI missing for for ${LOCUS}_${DEPTH}_${PBS_ARRAYID}. Exiting."
+	exit
+fi
+#Check if ID file alrady generated
+#if [[ -f $ID/Simulation_$PBS_ARRAYID\_R1-ID.tab ]]; then
+#	echo "ID already generated ($PBS_ARRAYID). Exiting.."
+#	exit
+#fi
+
+# Set-up Temp directory
+cd $TEMP
+echo $BAM
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam.bai
+
+DATABASE=$WRK/../db/sacCer3_Del
+GENOPIPE=$WRK/../..
+
+## Execute Single DeletionID and record time
+cd $GENOPIPE/DeletionID
+echo "**Begin executing DeletionID for ${LOCUS}_${DEPTH}..."
+time bash identify-Deletion.sh -i $TEMP -o $OUTPUT/ID -d $DATABASE
+MESSAGE="...single DeletionID for ${LOCUS} ${DEPTH} finished."
+echo $MESSAGE
+cd $WRK
+
+## Clean-up
+rm -r $TEMP

paper/SyntheticDeletion/job/run_DeletionID_on_Rap1_4M.pbs

@@ -0,0 +1,74 @@
+#!/bin/bash
+#PBS -l nodes=1:ppn=4
+#PBS -l pmem=16gb
+#PBS -l walltime=00:20:00
+#PBS -A open
+#PBS -o logs/depth.did.Rap1.4M.log.out
+#PBS -e logs/depth.did.Rap1.4M.log.err
+#PBS -t 1-1000
+
+# This script will check that 1000 BAM files have been generated before executing DeletionID.
+
+module load gcc/8.3.1
+module load bedtools/2.27.1
+module load bwa/0.7.15
+module load samtools/1.5
+module load anaconda3
+source activate genopipe
+
+# FIRST CHANGE PATH TO EXECUTE
+WRK=/path/to/GenoPipe/paper/SyntheticDeletion
+cd $WRK
+
+INFO=`sed "5q;d" depth_simulations.txt`
+LOCUS=`awk '{print $1}'  <(echo $INFO)`
+DEPTH=`awk '{print $2}'  <(echo $INFO)`
+
+REF=`echo $LOCUS | awk -F'_' '{print $1}'`
+
+OUTPUT=$WRK/results/$LOCUS\_$DEPTH
+BAM=$WRK/results/$LOCUS\_$DEPTH/BAM
+TEMP=$WRK/temp5-$PBS_ARRAYID
+
+[ -d $OUTPUT/ID ] || mkdir $OUTPUT/ID
+[ -d logs ] || mkdir logs
+[ -d $ID ] || mkdir $ID
+[ -d $TEMP ] || mkdir $TEMP
+
+#Check that BAM file was generated first
+if [ -f $BAM.bam ];
+then
+	echo "BAM input for ${LOCUS}_${DEPTH}_${PBS_ARRAYID} does not exist. Exiting."
+	exit
+fi
+#Check that BAM Index file exists
+if [ -f $BAM.bam.bai ];
+then
+	echo "BAI missing for for ${LOCUS}_${DEPTH}_${PBS_ARRAYID}. Exiting."
+	exit
+fi
+#Check if ID file alrady generated
+#if [[ -f $ID/Simulation_$PBS_ARRAYID\_R1-ID.tab ]]; then
+#	echo "ID already generated ($PBS_ARRAYID). Exiting.."
+#	exit
+#fi
+
+# Set-up Temp directory
+cd $TEMP
+echo $BAM
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam
+ln -s $BAM/Simulation_$PBS_ARRAYID.bam.bai
+
+DATABASE=$WRK/../db/sacCer3_Del
+GENOPIPE=$WRK/../..
+
+## Execute Single DeletionID and record time
+cd $GENOPIPE/DeletionID
+echo "**Begin executing DeletionID for ${LOCUS}_${DEPTH}..."
+time bash identify-Deletion.sh -i $TEMP -o $OUTPUT/ID -d $DATABASE
+MESSAGE="...single DeletionID for ${LOCUS} ${DEPTH} finished."
+echo $MESSAGE
+cd $WRK
+
+## Clean-up
+rm -r $TEMP