Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found
Select Git revision
  • dev
  • master
  • v0.1.0
  • v0.1.2
  • v0.2.0
  • v0.2.1
  • v0.2.2
  • v0.2.3
  • v0.2.4
  • v0.2.5
  • v0.2.6
  • v0.2.7
  • v0.2.8
  • v0.2.9
  • v0.3.0
  • v0.4.0
  • v2.0.0
17 results

Target

Select target project
  • LBMC/regards/nextflow
  • elabaron/nextflow
  • lanani/nextflow
  • mlepetit/nextflow
  • mdjaffar/nextflow
  • LBMC/RMI2/rmi2_pipelines
  • lpicard/nextflow
  • rseraphi/nextflow
  • hregue/nextflow
  • letien02/nextflow
  • mshamjal/nextflow
  • z483801/nextflow
  • fduveau/nextflow
  • cginevra/nextflow
  • dtorresc/nextflow
  • fmortreu/nextflow
  • jshapiro/nextflow
  • carpin/nextflow
  • LBMC/Delattre/JU28_59vs17_SNP
  • jclaud01/nextflow
  • dchalopi/nextflow
  • mvilcot/nextflow
  • mherbett/nextflow
  • lestrada/nextflow
  • nfontrod/nextflow
  • gbenoit/nextflow
  • gyvert/nextflow
  • aguill09/nextflow
  • alapendr/nextflow
  • jprobin/nextflow
  • vvanoost/nextflow
  • jblin/nextflow
  • mparis/nextflow
  • ogandril/nextflow
  • cbourgeo/nextflow
  • ggirau03/nextflow
  • ecombe01/nextflow
  • acorbin/nextflow
  • pberna01/nextflow
  • pmarie01/nextflow
  • rhoury/nextflow
  • lgely/nextflow
  • jvalat/nextflow
  • cfournea/nextflow
  • mprieux/nextflow
  • hpolvech/nextflow
  • LBMC/nextflow
  • mcariou/nextflow
  • z483800/nextflow
  • yjia01/nextflow
  • jkleine/nextflow
  • LBMC/Palladino/RNAseq_nextflow
  • jseimand/nextflow
  • nlecouvr/nextflow-nathan
54 results
Select Git revision
  • dev
  • master
  • v0.1.0
  • v0.1.2
  • v0.2.0
  • v0.2.1
  • v0.2.2
  • v0.2.3
  • v0.2.4
  • v0.2.5
  • v0.2.6
  • v0.2.7
  • v0.2.8
  • v0.2.9
14 results
Show changes
Showing
with 257 additions and 431 deletions
// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
//
// SPDX-License-Identifier: AGPL-3.0-or-later
nextflow.enable.dsl=2
/*
Testing pipeline for marseq scRNASeq analysis
*/
include {
mapping;
} from "./nf_modules/bwa/main.nf"
include {
sort_bam;
} from "./nf_modules/samtools/main.nf"
include {
germline_cohort_data_variant_calling;
} from "./nf_modules/gatk4/main.nf" addParams(
variant_calling_out: "vcf/",
)
params.fastq = ""
params.fasta = ""
channel
.fromFilePairs( params.fastq, size: -1)
.set { fastq_files }
channel
.fromPath( params.fasta )
.map { it -> [it.simpleName, it]}
.set { fasta_files }
workflow {
mapping(fasta_files, fastq_files)
sort_bam(mapping.out.bam)
germline_cohort_data_variant_calling(sort_bam.out.bam, fasta_files)
}
// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
//
// SPDX-License-Identifier: AGPL-3.0-or-later
Channel
.fromPath( "data/tiny_dataset/fasta/*.fasta" )
.set { fasta_file }
process sample_fasta {
publishDir "results/sampling/", mode: 'copy'
input:
file fasta from fasta_file
output:
file "*_sample.fasta" into fasta_sample
script:
"""
head ${fasta} > ${fasta.baseName}_sample.fasta
"""
}
#!/bin/sh
# SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
#
# SPDX-License-Identifier: AGPL-3.0-or-later
#SBATCH --job-name=nextflow
#SBATCH --ntasks=1
#SBATCH --output=results/nextflow_%j.log
#SBATCH --licenses=sps
####################################
# change to your path
SCRATCH=/sps/lbmc/lmodolo/nextflow
${SCRATCH}/nextflow run ${SCRATCH}/src/solution_RNASeq.nf -profile ccin2p3 \
--fastq "${SCRATCH}/data/tiny_dataset/fastq/*_R{1,2}.fastq" \
--fasta "${SCRATCH}/data/tiny_dataset/fasta/tiny_v2.fasta" \
--bed "${SCRATCH}/data/tiny_dataset/annot/tiny.bed" \
-ansi-log \
-w "${SCRATCH}/work/"
wait
#!/bin/sh
# SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
#
# SPDX-License-Identifier: AGPL-3.0-or-later
java -version
curl -s https://get.nextflow.io | bash
// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
//
// SPDX-License-Identifier: AGPL-3.0-or-later
nextflowVersion = '>=20'
manifest {
homePage = 'https://gitbio.ens-lyon.fr/LBMC/nextflow'
description = 'pipeline to '
mainScript = 'main.nf'
version = '0.0.0'
}
report {
enabled = true
file = "$baseDir/../results/report.html"
}
profiles {
docker {
docker.temp = "auto"
docker.enabled = true
process {
errorStrategy = 'finish'
memory = '16GB'
withLabel: big_mem_mono_cpus {
cpus = 1
}
withLabel: big_mem_multi_cpus {
cpus = 4
}
withLabel: small_mem_mono_cpus {
cpus = 1
memory = '2GB'
}
withLabel: small_mem_multi_cpus {
cpus = 4
memory = '2GB'
}
}
}
podman {
charliecloud.enabled = true
charliecloud.cacheDir = "./bin/"
process {
errorStrategy = 'finish'
memory = '16GB'
withLabel: big_mem_mono_cpus {
cpus = 1
}
withLabel: big_mem_multi_cpus {
cpus = 4
}
withLabel: small_mem_mono_cpus {
cpus = 1
memory = '2GB'
}
withLabel: small_mem_multi_cpus {
cpus = 4
memory = '2GB'
}
}
}
singularity {
singularity.enabled = true
singularity.cacheDir = "./bin/"
process {
errorStrategy = 'finish'
memory = '16GB'
withLabel: big_mem_mono_cpus {
cpus = 1
}
withLabel: big_mem_multi_cpus {
cpus = 4
}
withLabel: small_mem_mono_cpus {
cpus = 1
memory = '2GB'
}
withLabel: small_mem_multi_cpus {
cpus = 4
memory = '2GB'
}
}
}
psmn {
charliecloud.enabled = true
charliecloud.cacheDir = "/Xnfs/abc/charliecloud"
charliecloud.runOptions = "--bind /scratch:/scratch --bind /Xnfs:/Xnfs --bind /home:/home"
charliecloud.readOnlyInputs = true
process{
errorStrategy = { sleep(Math.pow(2, task.attempt) * 200 as long); return 'retry' }
maxRetries = 3
executor = "slurm"
queue = "Lake"
withLabel: big_mem_mono_cpus {
cpus = 1
memory = "128GB"
time = "24h"
}
withLabel: big_mem_multi_cpus {
cpus = 32
memory = "192GB"
time = "24h"
}
withLabel: small_mem_mono_cpus {
cpus = 1
memory = "16GB"
time = "24h"
}
withLabel: small_mem_multi_cpus {
cpus = 32
memory = "16GB"
time = "24h"
}
}
}
ccin2p3 {
singularity.enabled = true
singularity.cacheDir = "$baseDir/../bin/"
singularity.runOptions = "--bind /pbs,/sps,/scratch,/tmp"
process{
maxRetries = 3
withLabel: big_mem_mono_cpus {
scratch = true
stageInMode = "copy"
stageOutMode = "rsync"
executor = "slurm"
clusterOptions = "--licenses=sps"
cpus = 1
memory = "8GB"
queue = "htc"
}
withLabel: big_mem_multi_cpus {
scratch = true
stageInMode = "copy"
stageOutMode = "rsync"
executor = "slurm"
clusterOptions = "--licenses=sps"
cpus = 1
memory = "8GB"
queue = "htc"
}
withLabel: small_mem_mono_cpus {
scratch = true
stageInMode = "copy"
stageOutMode = "rsync"
executor = "slurm"
clusterOptions = "--licenses=sps"
cpus = 1
memory = "8GB"
queue = "htc"
}
withLabel: small_mem_multi_cpus {
scratch = true
stageInMode = "copy"
stageOutMode = "rsync"
executor = "slurm"
clusterOptions = "--licenses=sps"
cpus = 1
memory = "8GB"
queue = "htc"
}
}
}
}
profiles {
docker {
docker.temp = 'auto'
docker.enabled = true
process {
withName: fasta_from_bed {
container = "bedtools:2.25.0"
}
}
}
psmn {
process{
withName: fasta_from_bed {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
module = "BEDtools/2.25.0"
executor = "sge"
clusterOptions = "-m e -cwd -V"
memory = "20GB"
time = "12h"
queue = 'monointeldeb128'
}
}
}
}
/*
* bedtools :
* Imputs : fasta files
* Imputs : bed files
* Output : fasta files
*/
/* fasta extraction */
params.fasta = "$baseDir/data/fasta/*.fasta"
params.bed = "$baseDir/data/annot/*.bed"
log.info "fasta file : ${params.fasta}"
log.info "bed file : ${params.bed}"
Channel
.fromPath( params.fasta )
.ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
.set { fasta_files }
Channel
.fromPath( params.bed )
.ifEmpty { error "Cannot find any bed files matching: ${params.bed}" }
.set { bed_files }
process fasta_from_bed {
tag "${bed.baseName}"
cpus 4
publishDir "results/fasta/", mode: 'copy'
input:
file fasta from fasta_files
file bed from bed_files
output:
file "*_extracted.fasta" into fasta_files_extracted
script:
"""
bedtools getfasta -name \
-fi ${fasta} -bed ${bed} -fo ${bed.baseName}_extracted.fasta
"""
}
./nextflow src/nf_modules/BEDtools/fasta_from_bed.nf \
-c src/nf_modules/BEDtools/fasta_from_bed.config \
-profile docker \
--fasta "data/tiny_dataset/fasta/tiny_v2.fasta" \
--bed "data/tiny_dataset/annot/tiny.bed" \
profiles {
docker {
docker.temp = 'auto'
docker.enabled = true
process {
withName: index_fasta {
container = "bwa:0.7.17"
}
}
}
psmn {
process{
withName: index_fasta {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
module = "BWA/0.7.17"
executor = "sge"
clusterOptions = "-m e -cwd -V"
memory = "30GB"
time = "12h"
queue = 'monointeldeb128'
}
}
}
}
params.fasta = "$baseDir/data/bam/*.fasta"
log.info "fasta files : ${params.fasta}"
Channel
.fromPath( params.fasta )
.ifEmpty { error "Cannot find any bam files matching: ${params.fasta}" }
.map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fasta_file }
process index_fasta {
tag "$fasta_id"
cpus 4
publishDir "results/mapping/index/", mode: 'copy'
input:
set fasta_id, file(fasta) from fasta_file
output:
set fasta_id, "${fasta.baseName}.*" into index_files
file "*_bwa_report.txt" into index_files_report
script:
"""
bwa index -p ${fasta.baseName} ${fasta} \
&> ${fasta.baseName}_bwa_report.txt
"""
}
profiles {
docker {
docker.temp = 'auto'
docker.enabled = true
process {
withName: mapping_fastq {
container = "bwa:0.7.17"
}
}
}
psmn {
process{
withName: mapping_fastq {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
module = "BWA/0.7.17"
executor = "sge"
clusterOptions = "-m e -cwd -V"
memory = "30GB"
time = "24h"
queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
penv = 'openmp16'
}
}
}
}
params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
params.index = "$baseDir/data/index/*.index.*"
log.info "fastq files : ${params.fastq}"
log.info "index files : ${params.index}"
Channel
.fromFilePairs( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
.set { fastq_files }
Channel
.fromPath( params.index )
.ifEmpty { error "Cannot find any index files matching: ${params.index}" }
.map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.groupTuple()
.set { index_files }
process mapping_fastq {
tag "$reads"
cpus 4
publishDir "results/mapping/sam/", mode: 'copy'
input:
set pair_id, file(reads) from fastq_files
set index_id, file(index) from index_files.collect()
output:
file "${pair_id}.sam" into sam_files
file "${pair_id}_bwa_report.txt" into mapping_repport_files
script:
"""
bwa mem -t ${task.cpus} \
${index_id} ${reads[0]} ${reads[1]} \
-o ${pair_id}.sam &> ${pair_id}_bwa_report.txt
"""
}
./nextflow src/nf_modules/BWA/indexing.nf \
-c src/nf_modules/BWA/indexing.config \
-profile docker \
--fasta "data/tiny_dataset/fasta/tiny_v2.fasta"
# ./nextflow src/nf_modules/BWA/mapping_single.nf \
# -c src/nf_modules/BWA/mapping_single.config \
# -profile docker \
# --index "results/mapping/index/tiny_v2.index" \
# --fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
./nextflow src/nf_modules/BWA/mapping_paired.nf \
-c src/nf_modules/BWA/mapping_paired.config \
-profile docker \
--index "results/mapping/index/tiny_v2*" \
--fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
profiles {
docker {
docker.temp = 'auto'
docker.enabled = true
process {
withName: index_fasta {
container = "bowtie:1.2.2"
}
}
}
psmn {
process{
withName: index_fasta {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
module = "Bowtie/1.2.2"
executor = "sge"
clusterOptions = "-m e -cwd -V"
memory = "20GB"
time = "12h"
queue = 'monointeldeb128'
}
}
}
}
/* fasta indexing */
params.fasta = "$baseDir/data/bam/*.fasta"
log.info "fasta files : ${params.fasta}"
Channel
.fromPath( params.fasta )
.ifEmpty { error "Cannot find any bam files matching: ${params.fasta}" }
.set { fasta_file }
process index_fasta {
tag "$fasta.baseName"
cpus 4
publishDir "results/mapping/index/", mode: 'copy'
input:
file fasta from fasta_file
output:
file "*.index*" into index_files
file "*_report.txt" into indexing_report
script:
"""
bowtie-build --threads ${task.cpus} -f ${fasta} ${fasta.baseName}.index &> ${fasta.baseName}_bowtie_report.txt
if grep -q "Error" ${fasta.baseName}_bowtie_report.txt; then
exit 1
fi
"""
}
profiles {
docker {
docker.temp = 'auto'
docker.enabled = true
process {
withName: mapping_fastq {
container = "bowtie:1.2.2"
}
}
}
psmn {
process{
withName: mapping_fastq {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
module = "Bowtie/1.2.2:SAMtools/1.7"
executor = "sge"
clusterOptions = "-m e -cwd -V"
memory = "30GB"
time = "24h"
queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
penv = 'openmp16'
}
}
}
}
/*
* mapping paired fastq
*/
params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
params.index = "$baseDir/data/index/*.index.*"
log.info "fastq files : ${params.fastq}"
log.info "index files : ${params.index}"
Channel
.fromFilePairs( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
.set { fastq_files }
Channel
.fromPath( params.index )
.ifEmpty { error "Cannot find any index files matching: ${params.index}" }
.set { index_files }
process mapping_fastq {
tag "$pair_id"
cpus 4
publishDir "results/mapping/bams/", mode: 'copy'
input:
set pair_id, file(reads) from fastq_files
file index from index_files.collect()
output:
file "*.bam" into bam_files
file "*_report.txt" into mapping_report
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]
}
}
"""
# -v specify the max number of missmatch, -k the number of match reported per
# reads
bowtie --best -v 3 -k 1 --sam -p ${task.cpus} ${index_id} \
-1 ${reads[0]} -2 ${reads[1]} 2> \
${pair_id}_bowtie_report.txt | \
samtools view -Sb - > ${pair_id}.bam
if grep -q "Error" ${pair_id}_bowtie_report.txt; then
exit 1
fi
"""
}
profiles {
docker {
docker.temp = 'auto'
docker.enabled = true
process {
withName: mapping_fastq {
container = "bowtie:1.2.2"
}
}
}
psmn {
process{
withName: mapping_fastq {
beforeScript = "source /usr/share/lmod/lmod/init/bash; module use ~/privatemodules"
module = "Bowtie/1.2.2:SAMtools/1.7"
executor = "sge"
clusterOptions = "-m e -cwd -V"
memory = "30GB"
time = "24h"
queue = 'E5-2670deb128A,E5-2670deb128B,E5-2670deb128C,E5-2670deb128D,E5-2670deb128E,E5-2670deb128F'
penv = 'openmp16'
}
}
}
}
/*
* mapping single end fastq
*/
params.fastq = "$baseDir/data/fastq/*.fastq"
log.info "fastq files : ${params.fastq}"
log.info "index files : ${params.index}"
Channel
.fromPath( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
.map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fastq_files }
Channel
.fromPath( params.index )
.ifEmpty { error "Cannot find any index files matching: ${params.index}" }
.set { index_files }
process mapping_fastq {
tag "$file_id"
cpus 4
publishDir "results/mapping/bams/", mode: 'copy'
input:
set file_id, file(reads) from fastq_files
file index from index_files.collect()
output:
set file_id, "*.bam" into bam_files
file "*_report.txt" into mapping_report
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]
}
}
"""
bowtie --best -v 3 -k 1 --sam -p ${task.cpus} ${index_id} \
-q ${reads} 2> \
${file_id}_bowtie_report.txt | \
samtools view -Sb - > ${file_id}.bam
if grep -q "Error" ${file_id}_bowtie_report.txt; then
exit 1
fi
"""
}
./nextflow src/nf_modules/Bowtie/indexing.nf \
-c src/nf_modules/Bowtie/indexing.config \
-profile docker \
--fasta "data/tiny_dataset/fasta/tiny_v2.fasta"
./nextflow src/nf_modules/Bowtie/mapping_single.nf \
-c src/nf_modules/Bowtie/mapping_single.config \
-profile docker \
--index "results/mapping/index/*.ebwt" \
--fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
./nextflow src/nf_modules/Bowtie/mapping_paired.nf \
-c src/nf_modules/Bowtie/mapping_paired.config \
-profile docker \
--index "results/mapping/index/*.ebwt" \
--fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"