diff --git a/src/RNAseq.config b/src/RNAseq.config
index ed86a1f44faed4a8c48d273632b571b09ed8472c..30c302096a5db023ce8b18d45e65fd795e559d0f 100644
--- a/src/RNAseq.config
+++ b/src/RNAseq.config
@@ -51,16 +51,6 @@ profiles {
time = "12h"
queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
}
- withName: dedup {
- beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
- module = "umi_tools_1.0.0"
- executor = "sge"
- clusterOptions = "-cwd -V"
- cpus = 1
- memory = "20GB"
- time = "12h"
- queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
- }
withName: counting {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
module = "htseq/0.11.2"
diff --git a/src/RNAseq.nf b/src/RNAseq.nf
index 084b9ff2e84260fddfe215d13913faacb4f2c191..3b6e39574f9c2c80914226443b629ea2b762df57 100644
--- a/src/RNAseq.nf
+++ b/src/RNAseq.nf
@@ -146,49 +146,6 @@ cat ${report} > ${file_id}_hisat_hg38.txt
"""
}
-
-/* deduplicating reads
-
-params.dedup_options = "--paired"
-
-process dedup {
- tag "$file_id"
-
- input:
- set file_id, file(bam) from for_dedup
-
- output:
- set file_id, "*dedup.bam" into dedup_bam
- file "*.txt" into dedup_report
-
- script:
-"""
-umi_tools dedup -I ${bam[0]} \
- ${params.dedup_options} \
- -S ${file_id}_dedup.bam > report.txt
-"""
-}
-
-process sort_bam {
- tag "$file_id"
- publishDir "${params.output}/03_hisat2_hg38_dedup/", mode: 'copy'
-
- input:
- set file_id, file(bam) from dedup_bam
- file dedup from dedup_report
-
- output:
- set file_id, "*_sorted.{bam,bam.bai}" into sorted_bam_files_2
- file "*.txt" into report_dedup
-
- script:
-"""
-samtools sort -@ ${task.cpus} -O BAM -o ${file_id}_sorted.bam ${bam}
-samtools index ${file_id}_sorted.bam
-cat ${dedup} > ${file_id}_dedup_report.txt
-"""
-} */
-
/* HTseq */
process sort_bam {
diff --git a/src/RibosomeProfiling.config b/src/RibosomeProfiling.config
index 6837f9cc1217343f7067a3a7a0eff8019c7391c0..b4abd97ecbdddc78a7222e821846157f9e295cec 100644
--- a/src/RibosomeProfiling.config
+++ b/src/RibosomeProfiling.config
@@ -3,13 +3,13 @@ profiles {
process{
withName: trimming {
beforeScript = "source $baseDir/.conda_psmn.sh"
- conda = "$baseDir/.conda_envs/cutadapt_2.1"
+ conda = "$baseDir/.conda_envs/cutadapt_2.4"
executor = "sge"
clusterOptions = "-cwd -V"
cpus = 1
memory = "20GB"
time = "12h"
- queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
}
withName: rRNA_removal {
beforeScript = "source $baseDir/.conda_psmn.sh"
@@ -19,7 +19,7 @@ profiles {
cpus = 16
memory = "30GB"
time = "24h"
- queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
penv = 'openmp16'
}
withName: hisat2_human {
@@ -30,19 +30,9 @@ profiles {
memory = "20GB"
cpus = 16
time = "12h"
- queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
penv = 'openmp16'
}
- withName: sort_bam {
- beforeScript = "source $baseDir/.conda_psmn.sh"
- conda = "$baseDir/.conda_envs/samtools_1.7"
- executor = "sge"
- clusterOptions = "-cwd -V"
- cpus = 1
- memory = "20GB"
- time = "12h"
- queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
- }
withName: index_bam {
beforeScript = "source $baseDir/.conda_psmn.sh"
conda = "$baseDir/.conda_envs/samtools_1.7"
@@ -51,17 +41,7 @@ profiles {
cpus = 1
memory = "20GB"
time = "12h"
- queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
- }
- withName: dedup {
- beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
- module = "umi_tools/1.0.0"
- executor = "sge"
- clusterOptions = "-cwd -V"
- cpus = 1
- memory = "20GB"
- time = "12h"
- queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
}
withName: counting {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
@@ -71,7 +51,7 @@ profiles {
cpus = 1
memory = "20GB"
time = "12h"
- queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
}
}
}
@@ -91,18 +71,10 @@ profiles {
cpus = 4
container = "lbmc/hisat2:2.1.0"
}
- withName: sort_bam {
- container = "lbmc/samtools:1.7"
- cpus = 1
- }
withName: index_bam {
container = "lbmc/samtools:1.7"
cpus = 1
}
- withName: dedup {
- container = "lbmc/umi_tools:1.0.0"
- cpus = 1
- }
withName: counting {
container = "lbmc/htseq:0.11.2"
cpus = 1
diff --git a/src/RibosomeProfiling.nf b/src/RibosomeProfiling.nf
index 9586d01e71ab885c4a733c8d439eb3c388352491..faeb37f2402504642be76281ab7a57462073c3a0 100644
--- a/src/RibosomeProfiling.nf
+++ b/src/RibosomeProfiling.nf
@@ -110,72 +110,52 @@ hisat2 -x ${index_id} -p ${task.cpus} \
--end-to-end --rna-strandness 'F' \
2> ${file_id}_hisat2_hg38.txt | samtools view -bS -F 4 -o ${file_id}.bam
+if grep -q "Error " ${file_id}_hisat2_hg38.txt; then
+ exit 1
+fi
"""
}
-/* sorting */
-
-process index_bam {
+process save_hisat {
tag "$file_id"
publishDir "${params.output}/03_hisat2/", mode: 'copy'
input:
- set file_id, file(bam) from reads_aligned_hg38
+ set file_id, file(fastq) from reads_non_aligned_hg38
output:
- set file_id, "*_sorted.{bam,bam.bai}" into sorted_bam_files
+ file "*" into saved_hisat
script:
"""
-samtools sort -@ ${task.cpus} -O BAM -o ${file_id}_sorted.bam ${bam}
-samtools index ${file_id}_sorted.bam
+cat ${fastq} > ${file_id}_nonhuman.fastq.gz
"""
}
-sorted_bam_files.into{for_dedup;for_htseq}
-
-/* deduplicating reads
-
-params.dedup_options = ""
-
-process dedup {
- tag "$file_id"
-
- input:
- set file_id, file(bam) from for_dedup
-
- output:
- set file_id, "*dedup.bam" into dedup_bam
- file "*.txt" into dedup_report
+/* sorting */
- script:
-"""
-umi_tools dedup -I ${bam[0]} \
- ${params.dedup_options} \
- -S ${file_id}_dedup.bam > report.txt
-"""
-}*/
-/*
-process sort_bam {
+process index_bam {
tag "$file_id"
- publishDir "${params.output}/03_hisat2_dedup/", mode: 'copy'
+ publishDir "${params.output}/03_hisat2/", mode: 'copy'
input:
- set file_id, file(bam) from dedup_bam
- file dedup from dedup_report
+ set file_id, file(bam) from reads_aligned_hg38
+ file report from hisat_report
output:
- set file_id, "*_sorted.{bam,bam.bai}" into sorted_bam_files_2
- file "*.txt" into report_dedup
+ set file_id, "*_sorted.{bam,bam.bai}" into sorted_bam_files
+ file "*.txt" into report_hisat2
script:
"""
samtools sort -@ ${task.cpus} -O BAM -o ${file_id}_sorted.bam ${bam}
samtools index ${file_id}_sorted.bam
-cat ${dedup} > ${file_id}_dedup_report.txt
+
+cat ${report} > ${file_id}_hg38_hisat2.txt
"""
}
-*/
+
+
/* HTseq */
params.gtf = "$baseDir/data/annotation/*.gtf"
@@ -189,9 +169,11 @@ Channel
process counting {
tag "$file_id"
publishDir "${params.output}/04_HTseq/", mode: 'copy'
+ errorStrategy 'retry'
+ maxRetries 2
input:
- set file_id, file(bam) from for_htseq
+ set file_id, file(bam) from sorted_bam_files
file gtf from gtf_file.toList()
output:
diff --git a/src/dual_mapping.config b/src/dual_mapping.config
index fdf3c362c7b45fb23ffe5bf44ddcdf15bbb0a964..2c186ba6681f939276042d6d2a2e2040742293ec 100644
--- a/src/dual_mapping.config
+++ b/src/dual_mapping.config
@@ -7,21 +7,19 @@ profiles {
executor = "sge"
clusterOptions = "-cwd -V"
memory = "20GB"
- cpus = 16
+ cpus = 16
time = "12h"
- queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
- penv = 'openmp16'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
+ penv = 'openmp16'
}
withName: index_fasta_bowtie {
- beforeScript = "source $baseDir/.conda_psmn.sh"
- conda = "$baseDir/.conda_envs/bowtie_1.2.2"
+ beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
+ module = "GCC/6.4.0/Bowtie/1.1.2:samtools/1.7"
executor = "sge"
clusterOptions = "-cwd -V"
memory = "20GB"
- cpus = 16
time = "12h"
- queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
- penv = 'openmp16'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
}
withName: hisat2 {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
@@ -31,7 +29,7 @@ profiles {
memory = "20GB"
cpus = 16
time = "12h"
- queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
penv = 'openmp16'
}
withName: sort_bam {
@@ -42,7 +40,7 @@ profiles {
cpus = 1
memory = "20GB"
time = "12h"
- queue = 'monointeldeb128,monointeldeb48,h48-E5-2670deb128,h6-E5-2667v4deb128'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
}
withName: merge_bam {
beforeScript = "source $baseDir/.conda_psmn.sh"
@@ -52,7 +50,7 @@ profiles {
cpus = 16
memory = "30GB"
time = "24h"
- queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
penv = 'openmp16'
}
}
diff --git a/src/dual_mapping.nf b/src/dual_mapping.nf
index c8509b9a7b698ebd6a35c0507cf042a887ab4ccc..1fec02e2069276a9af71984598bcf0ca03438274 100644
--- a/src/dual_mapping.nf
+++ b/src/dual_mapping.nf
@@ -4,6 +4,8 @@
params.fasta = "data/genome/NC001802.1.fa"
log.info "fasta files : ${params.fasta}"
+params.output = "results"
+log.info "output folder : ${params.output}"
Channel
.fromPath( params.fasta )
@@ -15,7 +17,6 @@ fasta_file.into{fasta_hisat ; fasta_bowtie}
/* HISAT */
process index_fasta_hisat {
tag "$fasta.baseName"
- publishDir "data/indexes/${fasta.baseName}_hisat/", mode: 'copy'
input:
file fasta from fasta_hisat
@@ -33,7 +34,6 @@ hisat2-build -p ${task.cpus} ${fasta} ${fasta.baseName}
process index_fasta_bowtie {
tag "$fasta.baseName"
- publishDir "results/${fasta.baseName}_bowtie/", mode: 'copy'
input:
file fasta from fasta_bowtie
@@ -44,7 +44,7 @@ process index_fasta_bowtie {
script:
"""
-bowtie-build --threads ${task.cpus} -f ${fasta} ${fasta.baseName} \
+bowtie-build -f ${fasta} ${fasta.baseName} \
&> ${fasta.baseName}_bowtie_report.txt
if grep -q "Error" ${fasta.baseName}_bowtie_report.txt; then
@@ -123,8 +123,8 @@ for (index_file in index) {
}
}
"""
-bowtie --best --fr -v 3 -k 1 --sam -p ${task.cpus} ${index_id} \
--q ${reads} 2> \
+zcat ${reads} | bowtie --best --fr -v 3 -k 1 --sam -p ${task.cpus} ${index_id} \
+-q - 2> \
${file_id}_bowtie_report_tmp.txt | \
samtools view -F 4 -F 16 -Sb - > ${file_id}_bowtie.bam
@@ -145,7 +145,7 @@ bam_bowtie.join(bam_hisat)
//merged_bam.println()
process merge_bam{
- publishDir "results/05_${index_id}_mergedBAM/", mode: 'copy'
+ publishDir "${params.output}/05_${index_id}_mergedBAM/", mode: 'copy'
input:
set file_id, index_id, file(bam_bowtie), file(bam_hisat) from merged_bam
diff --git a/src/dual_mapping_paired.config b/src/dual_mapping_paired.config
new file mode 100644
index 0000000000000000000000000000000000000000..fd8de75af39c1840acd8e6b3afbdf3df5c0747c0
--- /dev/null
+++ b/src/dual_mapping_paired.config
@@ -0,0 +1,85 @@
+profiles {
+ sge {
+ process{
+ withName: index_fasta_hisat {
+ beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
+ module = "hisat2/2.1.0:samtools/1.7"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ memory = "20GB"
+ cpus = 16
+ time = "12h"
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
+ penv = 'openmp16'
+ }
+ withName: index_fasta_bowtie {
+ beforeScript = "source $baseDir/.conda_psmn.sh"
+ conda = "$baseDir/.conda_envs/bowtie2_2.3.4.1"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ memory = "20GB"
+ time = "12h"
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
+ }
+ withName: hisat2 {
+ beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
+ module = "hisat2/2.1.0:samtools/1.7"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ memory = "20GB"
+ cpus = 16
+ time = "12h"
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
+ penv = 'openmp16'
+ }
+ withName: bowtie{
+ beforeScript = "source $baseDir/.conda_psmn.sh"
+ conda = "$baseDir/.conda_envs/bowtie2_2.3.4.1"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ cpus = 8
+ memory = "20GB"
+ time = "12h"
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
+ penv = 'openmp8'
+ }
+ withName: merge_bam {
+ beforeScript = "source $baseDir/.conda_psmn.sh"
+ conda = "$baseDir/.conda_envs/samtools_1.7"
+ executor = "sge"
+ clusterOptions = "-cwd -V"
+ cpus = 16
+ memory = "30GB"
+ time = "24h"
+ queue = 'CLG6242deb384A,CLG6242deb384C,CLG5218deb192A,CLG5218deb192B,CLG5218deb192C,CLG5218deb192D,SLG5118deb96,SLG6142deb384A,SLG6142deb384B,SLG6142deb384C,SLG6142deb384D'
+ penv = 'openmp16'
+ }
+ }
+ }
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ withName: index_fasta_hisat {
+ cpus = 4
+ container = "lbmc/hisat2:2.1.0"
+ }
+ withName: index_fasta_bowtie {
+ cpus = 4
+ container = "lbmc/bowtie:1.2.2"
+ }
+ withName: hisat2 {
+ cpus = 4
+ container = "lbmc/hisat2:2.1.0"
+ }
+ withName: bowtie {
+ cpus = 4
+ container = "lbmc/bowtie2:2.3.4.1"
+ }
+ withName: merge_bam {
+ container = "lbmc/samtools:1.7"
+ cpus = 4
+ }
+ }
+ }
+}
diff --git a/src/dual_mapping_paired.nf b/src/dual_mapping_paired.nf
index f5a5fe5fc5b08e2078f6164559a15a4d95739608..16490f7e88d7a683dbadf5e9e821d0268b7fa5a3 100644
--- a/src/dual_mapping_paired.nf
+++ b/src/dual_mapping_paired.nf
@@ -29,23 +29,23 @@ hisat2-build -p ${task.cpus} ${fasta} ${fasta.baseName}
"""
}
-/* BOWTIE 1 */
+/* BOWTIE 2 */
process index_fasta_bowtie {
tag "$fasta.baseName"
- publishDir "results/${fasta.baseName}_bowtie/", mode: 'copy'
+ publishDir "results/${fasta.baseName}_bowtie2/", mode: 'copy'
input:
file fasta from fasta_bowtie
output:
- file "*ebwt" into index_files_bowtie
+ file "*bt2" into index_files_bowtie
file "*_report.txt" into indexing_report
script:
"""
-bowtie-build --threads ${task.cpus} -f ${fasta} ${fasta.baseName} \
-&> ${fasta.baseName}_bowtie_report.txt
+bowtie2-build --threads ${task.cpus} -f ${fasta} ${fasta.baseName} \
+&> ${fasta.baseName}_bowtie2_report.txt
if grep -q "Error" ${fasta.baseName}_bowtie_report.txt; then
exit 1
@@ -97,7 +97,6 @@ process hisat2 {
hisat2 -x ${index_id} -p ${task.cpus} \
-1 ${fastq_filtred[0]} -2 ${fastq_filtred[1]} --un-conc-gz ${file_id}_notaligned_hisat_R%.fastq.gz \
--rna-strandness 'F' --dta --no-temp-splicesite \
---novel-splicesite-outfile ${file_id}splicesite.txt
2> ${file_id}_hisat2_NY5.txt | samtools view -F 4 -F 16 -Sb - > ${file_id}.bam
"""
}
@@ -118,14 +117,14 @@ process bowtie {
script:
index_id = index[0]
for (index_file in index) {
- if (index_file =~ /.*\.1\.ebwt/ && !(index_file =~ /.*\.rev\.1\.ebwt/)) {
- index_id = ( index_file =~ /(.*)\.1\.ebwt/)[0][1]
+ if (index_file =~ /.*\.1\.bt2/ && !(index_file =~ /.*\.rev\.1\.bt2/)) {
+ index_id = ( index_file =~ /(.*)\.1\.bt2/)[0][1]
}
}
"""
-bowtie --best --fr -v 3 -k 1 --sam -p ${task.cpus} ${index_id} \
+bowtie2 --best --fr -v 3 -k 1 --sam -p ${task.cpus} ${index_id} \
-1 ${reads[0]} -2 ${reads[1]} 2> \
-${file_id}_bowtie_report_tmp.txt | \
+${file_id}_bowtie2_report_tmp.txt | \
samtools view -F 4 -F 16 -Sb - > ${file_id}_bowtie.bam
if grep -q "Error" ${file_id}_bowtie_report_tmp.txt; then