Updated pipeline and generation files.

arriba_helper.sh

@@ -5,11 +5,17 @@
 #SBATCH --time 12:00:00
 #SBATCH --mem=128G
 
+DATADIR=/datastore/scratch/users/vantwisk/sim/shortreads_training${6}k
+MAPPING_DIR=/datastore/scratch/users/vantwisk/sim/shortreads_training${6}k_mapping
+ARRIBA_DIR=/datastore/scratch/users/vantwisk/sim/shortreads_training${6}k_arriba
+
+[ ! -d ${ARRIBA_DIR} ] && mkdir ${ARRIBA_DIR}
+
 #for j in $(seq 1 10); do
 #singularity exec --pid --bind /datastore arriba_latest.sif \
 /home/vantwisk/arriba_v2.2.1/arriba \
-    -x i_hun/Star_Homo_sapiens_coverage-${3}-length-${2}-${4}Aligned.sortedByCoord.out.bam \
-    -o i_hun/Star_Homo_sapiens_coverage-${3}-length-${2}-${4}.tsv -O i_hun/Star_Homo_sapiens_coverage-${3}-length-${2}-${4}.discarded.tsv \
+    -x ${MAPPING_DIR}/fusions-${1}-${4}-${5}-Aligned.sortedByCoord.out.bam \
+    -o ${ARRIBA_DIR}/fusions-${1}-${4}-${5}.tsv -O ${ARRIBA_DIR}/fusions-${1}-${4}-${5}.discarded.tsv \
     -a Homo_sapiens.GRCh38.dna.primary_assembly.fa -g Homo_sapiens.GRCh38.105.chr.gtf \
     -b /home/vantwisk/arriba_v2.2.1/database/blacklist_hg38_GRCh38_v2.2.1.tsv -k /home/vantwisk/arriba_v2.2.1/database/known_fusions_hg38_GRCh38_v2.2.1.tsv -t /home/vantwisk/arriba_v2.2.1/database/known_fusions_hg38_GRCh38_v2.2.1.tsv -p /home/vantwisk/arriba_v2.2.1/database/protein_domains_hg38_GRCh38_v2.2.1.gff3
 #done

badread_helper.sh

@@ -5,8 +5,7 @@
 #SBATCH -n 1
 #SBATCH --time 24:00:00
 
-OUTDIR=longreads
-
+OUTDIR=/datastore/scratch/users/vantwisk/sim/longreads_training${8}k
 
 [ ! -d ${OUTDIR} ] && mkdir ${OUTDIR}
 echo $1
@@ -16,11 +15,12 @@ echo $4
 echo $5
 echo $6
 echo $7
+echo $8
 
 #for j in $(seq 1 10); do
 rustyread --threads 32 simulate --reference ${7} \
     --quantity ${1}x \
-    --qscore_model ${6} --glitches 0,0,0 --junk_reads 0 --random_reads 0 \
-    --error_model ${6} --identity ${5} \
+    --qscore_model /home/vantwisk/Badread/badread/qscore_models/${6} --glitches 0,0,0 --junk_reads 0 --random_reads 0 \
+    --error_model /home/vantwisk/Badread/badread/error_models/${6} --identity ${5} \
     --chimera 0 --seed $RANDOM | gzip > ${OUTDIR}/fusions-${1}-${5}-${6}-${4}.fq.gz #pfun/fuse-${1}-${4}.fq.gz  #fuse-transcript-${1}-${4}.fq.gz
 #done

fusionseeker_helper.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+#SBATCH --job-name longgf
+#SBATCH --partition allnodes
+#SBATCH --time UNLIMITED
+#SBATCH --cpus-per-task 1
+#SBATCH --mem-per-cpu 10g
+
+DATADIR_MINIMAP=/datastore/scratch/users/vantwisk/sim/longreads_training${12}k_minimap2
+FUSIONSEEKER_DIR=/datastore/scratch/users/vantwisk/sim/longreads_training${12}k_fusionseeker
+
+[ ! -d ${FUSIONSEEKER_DIR} ] && mkdir ${FUSIONSEEKER_DIR}
+
+#singularity exec --pid --bind /datastore longgf_0.1.2--h05f6578_1.sif \
+fusionseeker \
+  --tread 16 \
+  --bam ${DATADIR_MINIMAP}/fusions-${1}-${5}-${6}-${4}-sorted.bam \
+  --gtf Homo_sapiens.GRCh38.105.gtf \
+  --ref ../hg38.fa \
+  -o ${FUSIONSEEKER_DIR}/fusions-${1}-${5}-${6}-${4}-fusionseeker \
+  -s 2

generate_arriba.sh

@@ -0,0 +1,55 @@
+
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
+
+N_TRANSCRIPTS=('1')
+REPLICATES=10
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
+TECH=('pacbio2016' 'nanopore2020')
+
+READ_LENGTHS=(100 150)
+
+#module load R-4.0.3
+
+#Rscript split_transcripts.R ${TRANSCRIPTOME} ${FUSE_TRANSCRIPTS} ${FUSE_META} ${NFUSIONS}
+
+#cp ${TRANSCRIPTOME} ${FUSE_TRANSCRIPTOME}
+#cat ${FUSE_TRANSCRIPTS} >> ${FUSE_TRANSCRIPTOME}
+
+#for i in $(seq 1 ${REPLICATES}); do
+#  for q in ${!COVERAGE[@]}; do
+#    for j in ${!QUALITY[@]}; do
+#      for k in ${!TECH[@]}; do
+#	 for n in ${!N_TRANSCRIPTS[@]}; do
+#           sbatch minimap2_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${N_TRANSCRIPTS[$n]}
+#	 done
+#      done
+#    done
+#  done
+#done
+
+#for i in $(seq 1 ${REPLICATES}); do
+#  for q in ${!COVERAGE[@]}; do
+#    for j in ${!QUALITY[@]}; do
+#      for k in ${!TECH[@]}; do
+#	 for n in ${!N_TRANSCRIPTS[@]}; do
+#           sbatch genself_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${N_TRANSCRIPTS[$n]}
+#	 done
+#      done
+#    done
+#  done
+#done
+
+for i in $(seq 1 ${REPLICATES}); do
+  for q in ${!COVERAGE[@]}; do
+    for j in ${!READ_LENGTHS[@]}; do
+      for n in ${!N_TRANSCRIPTS[@]}; do
+        sbatch arriba_helper.sh ${COVERAGE[$q]} 1 1 ${READ_LENGTHS[$j]} ${i} ${N_TRANSCRIPTS[$n]}
+      done
+    done
+  done
+done

generate_fusionseeker.sh

@@ -0,0 +1,26 @@
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
+
+N_TRANSCRIPTS=('1')
+REPLICATES=10
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
+TECH=('pacbio2016' 'nanopore2020')
+MIN_OVERLAP_LEN=100
+BIN_SIZE=50
+MIN_MAP_LENGTH=100
+
+for i in $(seq 1 ${REPLICATES}); do
+  for q in ${!COVERAGE[@]}; do
+    for j in ${!QUALITY[@]}; do
+      for k in ${!TECH[@]}; do
+        for n in ${!N_TRANSCRIPTS[@]}; do
+           sbatch fusionseeker_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${MIN_OVERLAP_LEN} ${BIN_SIZE} ${MIN_MAP_LENGTH} ${N_TRANSCRIPTS[$n]}
+        done
+      done
+    done
+  done
+done

generate_genion.sh

@@ -0,0 +1,24 @@
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
+
+N_TRANSCRIPTS=('1')
+REPLICATES=10
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
+TECH=('pacbio2016' 'nanopore2020')
+MIN_SUPPORT=2
+
+for i in $(seq 1 ${REPLICATES}); do
+  for q in ${!COVERAGE[@]}; do
+    for j in ${!QUALITY[@]}; do
+      for k in ${!TECH[@]}; do
+        for n in ${!N_TRANSCRIPTS[@]}; do
+           sbatch genion_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${MIN_SUPPORT} ${N_TRANSCRIPTS[$n]}
+        done
+      done
+    done
+  done
+done

generate_jaffal.sh

@@ -0,0 +1,23 @@
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
+
+N_TRANSCRIPTS=('1')
+REPLICATES=10
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
+TECH=('pacbio2016' 'nanopore2020')
+
+for i in $(seq 1 ${REPLICATES}); do
+  for q in ${!COVERAGE[@]}; do
+    for j in ${!QUALITY[@]}; do
+      for k in ${!TECH[@]}; do
+        for n in ${!N_TRANSCRIPTS[@]}; do
+           sbatch jaffal_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${N_TRANSCRIPTS[$n]}
+        done
+      done
+    done
+  done
+done

generate_longgf.sh

@@ -0,0 +1,26 @@
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
+
+N_TRANSCRIPTS=('1')
+REPLICATES=10
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
+TECH=('pacbio2016' 'nanopore2020')
+MIN_OVERLAP_LEN=100
+BIN_SIZE=50
+MIN_MAP_LENGTH=100
+
+for i in $(seq 1 ${REPLICATES}); do
+  for q in ${!COVERAGE[@]}; do
+    for j in ${!QUALITY[@]}; do
+      for k in ${!TECH[@]}; do
+        for n in ${!N_TRANSCRIPTS[@]}; do
+           sbatch longgf_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${MIN_OVERLAP_LEN} ${BIN_SIZE} ${MIN_MAP_LENGTH} ${N_TRANSCRIPTS[$n]}
+        done
+      done
+    done
+  done
+done

generate_mapping.sh

@@ -0,0 +1,67 @@
+
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
+
+N_TRANSCRIPTS=('1')
+REPLICATES=10
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
+TECH=('pacbio2016' 'nanopore2020')
+
+READ_LENGTHS=(100 150)
+
+#module load R-4.0.3
+
+#Rscript split_transcripts.R ${TRANSCRIPTOME} ${FUSE_TRANSCRIPTS} ${FUSE_META} ${NFUSIONS}
+
+#cp ${TRANSCRIPTOME} ${FUSE_TRANSCRIPTOME}
+#cat ${FUSE_TRANSCRIPTS} >> ${FUSE_TRANSCRIPTOME}
+
+for i in $(seq 1 ${REPLICATES}); do
+  for q in ${!COVERAGE[@]}; do
+    for j in ${!QUALITY[@]}; do
+      for k in ${!TECH[@]}; do
+	 for n in ${!N_TRANSCRIPTS[@]}; do
+           sbatch minimap2_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${N_TRANSCRIPTS[$n]}
+	 done
+      done
+    done
+  done
+done
+
+#for i in $(seq 1 ${REPLICATES}); do
+#  for q in ${!COVERAGE[@]}; do
+#    for j in ${!QUALITY[@]}; do
+#      for k in ${!TECH[@]}; do
+#	 for n in ${!N_TRANSCRIPTS[@]}; do
+#           sbatch genself_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${N_TRANSCRIPTS[$n]}
+#	 done
+#      done
+#    done
+#  done
+#done
+
+#for i in $(seq 1 ${REPLICATES}); do
+#  for q in ${!COVERAGE[@]}; do
+#    for j in ${!QUALITY[@]}; do
+#      for k in ${!TECH[@]}; do
+#	 for n in ${!N_TRANSCRIPTS[@]}; do
+#           sbatch pbmm2_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${N_TRANSCRIPTS[$n]}
+#	 done
+#      done
+#    done
+#  done
+#done
+
+#for i in $(seq 1 ${REPLICATES}); do
+#  for q in ${!COVERAGE[@]}; do
+#    for j in ${!READ_LENGTHS[@]}; do
+#      for n in ${!N_TRANSCRIPTS[@]}; do
+#        sbatch star_helper2.sh ${COVERAGE[$q]} 1 1 ${READ_LENGTHS[$j]} ${i} ${N_TRANSCRIPTS[$n]}
+#      done
+#    done
+#  done
+#done

generate_pbfusion.sh

@@ -0,0 +1,23 @@
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
+
+N_TRANSCRIPTS=('1')
+REPLICATES=10
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
+TECH=('pacbio2016' 'nanopore2020')
+
+for i in $(seq 1 ${REPLICATES}); do
+  for q in ${!COVERAGE[@]}; do
+    for j in ${!QUALITY[@]}; do
+      for k in ${!TECH[@]}; do
+        for n in ${!N_TRANSCRIPTS[@]}; do
+           sbatch pbfusion_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ax sam ${N_TRANSCRIPTS[$n]}
+        done
+      done
+    done
+  done
+done

generate_simulated_data.sh

@@ -1,18 +1,19 @@
 
-TRANSCRIPTOME=Homo_sapiens.cdna_50k.fa
-FUSE_TRANSCRIPTS=test_fusions1.fa
-FUSE_TRANSCRIPTOME=test_transcriptome.fa
-FUSE_META=test_fusions1.txt
-NFUSIONS=500
+TRANSCRIPTOME=Homo_sapiens.GRCh38.105.cdna.gtf_confirmed_new_16k.fa
+FUSE_TRANSCRIPTS=training16k_fusions.fa
+FUSE_TRANSCRIPTOME=training16k_transcriptome.fa
+FUSE_META=training16k_fusions.txt
+NFUSIONS=100
 
+N_TRANSCRIPTS=('1')
 REPLICATES=10
-COVERAGE=(3 5 10 30 50)
-QUALITY=('87,97,5')   #('75,90,8' '87.5,97.5,5'  '95,100,4')
+COVERAGE=(3 5 10 30 50 100)
+QUALITY=('75,90,8' '87,97,5'  '95,100,4')
 TECH=('pacbio2016' 'nanopore2020')
 
 READ_LENGTHS=(100 150)
 
-module load R-4.0.3
+#module load R-4.0.3
 
 #Rscript split_transcripts.R ${TRANSCRIPTOME} ${FUSE_TRANSCRIPTS} ${FUSE_META} ${NFUSIONS}
 
@@ -23,17 +24,21 @@ for i in $(seq 1 ${REPLICATES}); do
   for q in ${!COVERAGE[@]}; do
     for j in ${!QUALITY[@]}; do
       for k in ${!TECH[@]}; do
-        sbatch badread_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} ${FUSE_TRANSCRIPTOME} 
+	 for n in ${!N_TRANSCRIPTS[@]}; do
+           sbatch badread_helper.sh ${COVERAGE[$q]} 1 1 ${i} ${QUALITY[$j]} ${TECH[$k]} training${N_TRANSCRIPTS[$n]}k_transcriptome.fa ${N_TRANSCRIPTS[$n]}
+	 done
       done
     done
   done
 done
 
 
-for i in $(seq 1 ${REPLICATES}); do
-  for q in ${!COVERAGE[@]}; do
-    for j in ${!READ_LENGTHS[@]}; do
-      sbatch art_helper.sh ${COVERAGE[$q]} ${READ_LENGTHS[$j]} ${FUSE_TRANSCRIPTOME} ${i}
-    done
-  done
-done
+#for i in $(seq 1 ${REPLICATES}); do
+#  for q in ${!COVERAGE[@]}; do
+#    for j in ${!READ_LENGTHS[@]}; do
+#      for n in ${!N_TRANSCRIPTS[@]}; do
+#        sbatch art_helper.sh ${COVERAGE[$q]} ${READ_LENGTHS[$j]} training${N_TRANSCRIPTS[$n]}k_transcriptome.fa ${i} ${N_TRANSCRIPTS[$n]}
+#      done
+#    done
+#  done
+#done