diff --git a/CHANGELOG b/CHANGELOG
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/CHANGELOG.md b/CHANGELOG.md
new file mode 100644
index 0000000000000000000000000000000000000000..43ec4e433b23a3fbfd4ec2b2f6e1cb3ac2a28e2b
--- /dev/null
+++ b/CHANGELOG.md
@@ -0,0 +1,81 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.2.6] - 2018-08-23
+### Added
+- Added `src/training_dataset.nf` to build a small training dataset from NGS data
+
+### Changed
+- the structure of `src/nf_modules`: the `tests` folder was removed
+
+## [0.2.5] - 2018-08-22
+### Added
+- This fine changelog
+
+### Changed
+- the structure of `src/nf_modules`: the `tests` folder was removed
+
+
+## [0.2.4] - 2018-08-02
+### Changed
+- add `paired_id` variable in the output of every single-end data processes to match the paired output
+
+
+## [0.2.3] - 2018-07-25
+### Added
+- List of tools available as nextflow, docker or sge module to the `README.md`
+
+
+## [0.2.2] - 2018-07-23
+### Added
+- SRA module from cigogne/nextflow-master 52b510e48daa1fb7
+
+
+## [0.2.1] - 2018-07-23
+### Added
+- List of tools available as nextflow, docker or sge module
+
+
+## [0.2.0] - 2018-06-18
+### Added
+- `doc/TP_computational_biologists.md`
+- Kallisto/0.44.0
+
+### Changed
+- add `paired_id` variable in the output of every paired data processes
+- BEDtools: fixes for fasta handling
+- UrQt: fix git version in Docker
+
+
+## [0.1.2] - 2018-06-18
+### Added
+- `doc/tp_experimental_biologist.md` and Makefile to build the pdf
+- tests files for BEDtools
+
+### Changed
+- Kallisto: various fixes
+- UrQt: improve output and various fixes
+
+### Removed
+- `src/nf_test.config` modules have their own `.config`
+
+
+## [0.1.2] - 2018-06-18
+### Added
+- `doc/tp_experimental_biologist.md` and Makefile to build the pdf
+- tests files for BEDtools
+
+### Changed
+- Kallisto: various fixes
+- UrQt: improve output and various fixes
+
+### Removed
+- `src/nf_test.config` modules have their own `.config`
+
+
+## [0.1.0] - 2018-05-06
+This is the first working version of the repository as a nextflow module repository
+
diff --git a/README.md b/README.md
index 6f07ab7b151808aa7ddc91c0d7a55e54e1741d4c..2322dbb488ec7be4ec0407a8fec6c99a0fd7f9d6 100644
--- a/README.md
+++ b/README.md
@@ -5,7 +5,7 @@ You can fork this repository to build your own pipeline.
To get the last commits from this repository into your fork use the following commands:
```sh
-git remote add upstream https://gitlab.biologie.ens-lyon.fr/pipelines/nextflow.git
+git remote add upstream gitlab_lbmc:pipelines/nextflow.git
git pull upstream master
```
@@ -35,19 +35,19 @@ To install nextflow on you computer simply run the following command:
src/install_nextflow.sh
```
-Then to initialise a given tools run the following command:
+Then to initialize a given tools run the following command:
```sh
src/docker_modules/<tool_name>/<tool_version>/docker_init.sh
```
-for example to initialise `file_handle` version `0.1.1`, run:
+For example to initialize `file_handle` version `0.1.1`, run:
```sh
src/docker_modules/file_handle/0.1.1/docker_init.sh
```
-To initialise all the tools:
+To initialize all the tools:
```sh
find src/docker_modules/ -name "docker_init.sh" | awk '{system($0)}'
```
@@ -67,15 +67,44 @@ cd ..
Then to run the tests for a given tools run the following command:
```sh
-src/nf_modules/<tool_name>/<tool_version>/tests/tests.sh
+src/nf_modules/<tool_name>/<tool_version>/tests.sh
```
-for example to run the tests on `Bowtie2` run:
+For example to run the tests on `Bowtie2` run:
```sh
-src/nf_modules/Bowtie2/tests/tests.sh
+src/nf_modules/Bowtie2/tests.sh
```
+## Available tools
+
+| tool | nf module | docker module | sge module |
+|------|:---------:|:-------------:|:----------:|
+BEDtools | ok | ok | ok
+Bowtie | ok | ok | **no**
+Bowtie2 | ok | ok | ok
+canu | ok | ok | ok
+cutadapt | ok | ok | ok
+deepTools | **no** | ok | ok
+FastQC | ok | ok | ok
+file_handle | **no** | ok | ok
+HISAT2 | **no** | ok | **no**
+HTSeq | ok | ok | ok
+Kallisto | ok | ok | ok
+MACS2 | **no** | ok | ok
+MultiQC | ok | ok | ok
+MUSIC | ok | ok | ok
+picard | **no** | ok | ok
+pigz | **no** | ok | ok
+RSEM | ok | ok | ok
+SAMtools | ok | ok | ok
+SRAtoolkit | ok | ok | ok
+Salmon | **no** | ok | ok
+TopHat | **no** | ok | ok
+Trimmomatic | **no** | ok | ok
+UrQt | ok | ok | ok
+
+
## Contributing
Please read [CONTRIBUTING.md](CONTRIBUTING.md) for details on our code of conduct, and the process for submitting pull requests to us.
diff --git a/src/Rnaseq.config b/src/Rnaseq.config
deleted file mode 100644
index 1170cb83eb825ee111311c118e77de57c1c55dd7..0000000000000000000000000000000000000000
--- a/src/Rnaseq.config
+++ /dev/null
@@ -1,121 +0,0 @@
-profiles {
- docker {
- docker.temp = 'auto'
- docker.enabled = true
- process {
- $adaptor_removal {
- container = "cutadapt:1.14"
- }
- }
- }
- sge {
- process{
- $adaptor_removal {
- beforeScript = "module purge; module load cutadapt/1.14"
- executor = "sge"
- cpus = 1
- memory = "5GB"
- time = "6h"
- queueSize = 1000
- pollInterval = '60sec'
- queue = 'h6-E5-2667v4deb128'
- penv = 'openmp8'
- }
- }
- }
-}
-
-profiles {
- docker {
- docker.temp = 'auto'
- docker.enabled = true
- process {
- $trimming {
- container = "urqt:d62c1f8"
- }
- }
- }
- sge {
- process{
- $trimming {
- beforeScript = "module purge; module load UrQt/d62c1f8"
- executor = "sge"
- cpus = 4
- memory = "5GB"
- time = "6h"
- queueSize = 1000
- pollInterval = '60sec'
- queue = 'h6-E5-2667v4deb128'
- penv = 'openmp8'
- }
- }
- }
-}
-profiles {
- docker {
- docker.temp = 'auto'
- docker.enabled = true
- process {
- $fasta_from_bed {
- container = "bedtools:2.25.0"
- }
- }
- }
- sge {
- process{
- $fasta_from_bed {
- beforeScript = "module purge; module load BEDtools/2.25.0"
- executor = "sge"
- cpus = 1
- memory = "5GB"
- time = "6h"
- queueSize = 1000
- pollInterval = '60sec'
- queue = 'h6-E5-2667v4deb128'
- penv = 'openmp8'
- }
- }
- }
-}
-
-profiles {
- docker {
- docker.temp = 'auto'
- docker.enabled = true
- process {
- $index_fasta {
- container = "kallisto:0.43.1"
- }
- $mapping_fastq {
- container = "kallisto:0.43.1"
- }
- }
- }
- sge {
- process{
- $index_fasta {
- beforeScript = "module purge; module load Kallisto/0.43.1"
- executor = "sge"
- cpus = 1
- memory = "5GB"
- time = "6h"
- queueSize = 1000
- pollInterval = '60sec'
- queue = 'h6-E5-2667v4deb128'
- penv = 'openmp8'
- }
- $mapping_fastq {
- beforeScript = "module purge; module load Kallisto/0.43.1"
- executor = "sge"
- cpus = 4
- memory = "5GB"
- time = "6h"
- queueSize = 1000
- pollInterval = '60sec'
- queue = 'h6-E5-2667v4deb128'
- penv = 'openmp8'
- }
- }
- }
-}
-
diff --git a/src/Rnaseq.nf b/src/Rnaseq.nf
deleted file mode 100644
index 1b59e883aa31c4925197b580791e19d739b9190d..0000000000000000000000000000000000000000
--- a/src/Rnaseq.nf
+++ /dev/null
@@ -1,122 +0,0 @@
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-params.fasta = "$baseDir/data/fasta/*.fasta"
-params.bed = "$baseDir/data/annot/*.bed"
-
-log.info "fasta file : ${params.fasta}"
-log.info "bed file : ${params.bed}"
-log.info "fastq files : ${params.fastq}"
-
-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 }
-
-Channel
- .fromFilePairs( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
-process adaptor_removal {
- tag "$pair_id"
- publishDir "results/fastq/adaptor_removal/", mode: 'copy'
-
- input:
- set pair_id, file(reads) from fastq_files
-
- output:
- file "*_cut_R{1,2}.fastq.gz" into fastq_files_cut
-
- script:
- """
- cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT -A AGATCGGAAGAG -G CTCTTCCGATCT \
- -o ${pair_id}_cut_R1.fastq.gz -p ${pair_id}_cut_R2.fastq.gz \
- ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
- """
-}
-
-process trimming {
- tag "${reads}"
- cpus 4
- publishDir "results/fastq/trimming/", mode: 'copy'
-
- input:
- file reads from fastq_files_cut
-
- output:
- file "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
-
- script:
-"""
-UrQt --t 20 --m ${task.cpus} --gz \
---in ${reads[0]} --inpair ${reads[1]} \
---out ${reads[0].baseName}_trim_R1.fastq.gz --outpair ${reads[1].baseName}_trim_R2.fastq.gz \
-> ${reads[0].baseName}_trimming_report.txt
-"""
-}
-
-process fasta_from_bed {
- tag "${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 ${bed.baseName}_extracted.fasta
-"""
-}
-
-process index_fasta {
- tag "$fasta.baseName"
- publishDir "results/mapping/index/", mode: 'copy'
-
- input:
- file fasta from fasta_files_extracted
-
- output:
- file "*.index*" into index_files
-
- script:
-"""
-kallisto index -k 31 --make-unique -i ${fasta.baseName}.index ${fasta} \
-> ${fasta.baseName}_kallisto_report.txt
-"""
-}
-
-
-process mapping_fastq {
- tag "$reads"
- cpus 4
- publishDir "results/mapping/quantification/", mode: 'copy'
-
- input:
- file reads from fastq_files_trim
- file index from index_files
-
- output:
- file "*" into counts_files
-
- script:
-"""
-mkdir ${reads[0].baseName}
-kallisto quant -i ${index} -t ${task.cpus} \
---bias --bootstrap-samples 100 -o ${reads[0].baseName} \
-${reads[0]} ${reads[1]} &> ${reads[0].baseName}_kallisto_report.txt
-"""
-}
-
-
-
-
diff --git a/src/docker_modules/Bowtie/1.2.2/Dockerfile b/src/docker_modules/Bowtie/1.2.2/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..128e68acde94e20c03130a0a3551978231f7a9cd
--- /dev/null
+++ b/src/docker_modules/Bowtie/1.2.2/Dockerfile
@@ -0,0 +1,12 @@
+FROM ubuntu:18.04
+MAINTAINER Laurent Modolo
+
+ENV BOWTIE_VERSION=1.2.2
+ENV SAMTOOLS_VERSION=1.7
+ENV PACKAGES bowtie=${BOWTIE_VERSION}* \
+ samtools=${SAMTOOLS_VERSION}*
+
+
+RUN apt-get update && \
+ apt-get install -y --no-install-recommends ${PACKAGES} && \
+ apt-get clean
diff --git a/src/docker_modules/Bowtie/1.2.2/docker_init.sh b/src/docker_modules/Bowtie/1.2.2/docker_init.sh
new file mode 100755
index 0000000000000000000000000000000000000000..8e010a67b74c0e5519d639c3cb06a14c1fb6f987
--- /dev/null
+++ b/src/docker_modules/Bowtie/1.2.2/docker_init.sh
@@ -0,0 +1,2 @@
+#!/bin/sh
+docker build src/docker_modules/Bowtie/1.2.2 -t 'bowtie:1.2.2'
diff --git a/src/docker_modules/Bowtie2/2.3.4.1/Dockerfile b/src/docker_modules/Bowtie2/2.3.4.1/Dockerfile
index f8b1c5c048257ada6d0892dc787bd943aa2739b5..0f4ac75e48b5390714a22765c93939b72650b47e 100644
--- a/src/docker_modules/Bowtie2/2.3.4.1/Dockerfile
+++ b/src/docker_modules/Bowtie2/2.3.4.1/Dockerfile
@@ -4,8 +4,8 @@ MAINTAINER Laurent Modolo
ENV BOWTIE2_VERSION=2.3.4.1
ENV SAMTOOLS_VERSION=1.7
ENV PACKAGES bowtie2=${BOWTIE2_VERSION}* \
- samtools=${SAMTOOLS_VERSION}*
-
+ samtools=${SAMTOOLS_VERSION}* \
+ perl=5.26.1*
RUN apt-get update && \
apt-get install -y --no-install-recommends ${PACKAGES} && \
diff --git a/src/docker_modules/FastQC/0.11.5/Dockerfile b/src/docker_modules/FastQC/0.11.5/Dockerfile
index f7b999e418fc358eaf063989e0ff058820164a95..999edf6a3bb5ad548289a0de1740899802ed335d 100644
--- a/src/docker_modules/FastQC/0.11.5/Dockerfile
+++ b/src/docker_modules/FastQC/0.11.5/Dockerfile
@@ -2,7 +2,8 @@ FROM ubuntu:18.04
MAINTAINER Laurent Modolo
ENV FASTQC_VERSION=0.11.5
-ENV PACKAGES fastqc=${FASTQC_VERSION}*
+ENV PACKAGES fastqc=${FASTQC_VERSION}* \
+ perl=5.26*
RUN apt-get update && \
apt-get install -y --no-install-recommends ${PACKAGES} && \
diff --git a/src/docker_modules/HISAT2/2.0.0/docker_init.sh b/src/docker_modules/HISAT2/2.0.0/docker_init.sh
old mode 100644
new mode 100755
diff --git a/src/docker_modules/HTSeq/0.8.0/Dockerfile b/src/docker_modules/HTSeq/0.8.0/Dockerfile
index c655738fea3d89292f9ef5a9068893aafb6f38a1..a786b8026f66e9538c543f79624325ccb75952c6 100644
--- a/src/docker_modules/HTSeq/0.8.0/Dockerfile
+++ b/src/docker_modules/HTSeq/0.8.0/Dockerfile
@@ -14,4 +14,5 @@ RUN apt-get update && \
apt-get clean
RUN pip3 install numpy==1.14.3
+RUN pip3 install pysam==0.15.0
RUN pip3 install HTSeq==${HTSEQ_VERSION}
diff --git a/src/docker_modules/MACS2/2.1.0/Dockerfile b/src/docker_modules/MACS2/2.1.0/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..faf2e9088ce84eadc75612627cf74aa7fd2c7381
--- /dev/null
+++ b/src/docker_modules/MACS2/2.1.0/Dockerfile
@@ -0,0 +1,20 @@
+FROM ubuntu:18.04
+MAINTAINER Laurent Modolo
+
+ENV MACS_VERSION=2.1.1.20160309
+ENV PACKAGES git=1:2.17* \
+ build-essential=12.4* \
+ python-pip=9.0.1* \
+ ca-certificates=20180409 \
+ python-setuptools=39.0.1* \
+ python-dev=2.7* \
+ python-numpy=1:1.13* \
+ python-wheel=0.30.0* \
+ zlib1g-dev=1:1.2.11*
+
+RUN apt-get update && \
+ apt-get install -y --no-install-recommends ${PACKAGES} && \
+ apt-get clean
+
+RUN pip install MACS2==${MACS_VERSION}
+
diff --git a/src/docker_modules/MACS2/2.1.0/docker_init.sh b/src/docker_modules/MACS2/2.1.0/docker_init.sh
new file mode 100755
index 0000000000000000000000000000000000000000..8af6fd7fe7139608a894fc053f987e6ef4b3380a
--- /dev/null
+++ b/src/docker_modules/MACS2/2.1.0/docker_init.sh
@@ -0,0 +1,2 @@
+#!/bin/sh
+docker build src/docker_modules/MACS2/2.1.0 -t 'macs2:2.1.0'
diff --git a/src/docker_modules/MUSIC/6613c53/Dockerfile b/src/docker_modules/MUSIC/6613c53/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..0c6f4e4c018d75cafc0812278fb9899b354d4da2
--- /dev/null
+++ b/src/docker_modules/MUSIC/6613c53/Dockerfile
@@ -0,0 +1,25 @@
+FROM samtools:1.7
+MAINTAINER Laurent Modolo
+
+ENV PACKAGES git=1:2.17* \
+ build-essential=12.4* \
+ ca-certificates=20180409 \
+ zlib1g-dev=1:1.2.11*
+
+RUN apt-get update && \
+ apt-get install -y --no-install-recommends ${PACKAGES} && \
+ apt-get clean
+
+RUN git clone https://github.com/gersteinlab/MUSIC.git && \
+ cd MUSIC && \
+ git checkout ${MUSIC_VERSION} && \
+ make clean && \
+ make && \
+ cd .. && \
+ mv MUSIC/bin/MUSIC /usr/bin/ && \
+ mv MUSIC/bin/generate_multimappability_signal.csh /usr/bin/ && \
+ mv MUSIC/bin/run_MUSIC.csh /usr/bin/ && \
+ rm -Rf MUSIC
+
+RUN chmod +x /usr/bin/*
+
diff --git a/src/docker_modules/MUSIC/6613c53/docker_init.sh b/src/docker_modules/MUSIC/6613c53/docker_init.sh
new file mode 100755
index 0000000000000000000000000000000000000000..c6163d6b58877cd3a7fd31be65fa2b9ee958c3d5
--- /dev/null
+++ b/src/docker_modules/MUSIC/6613c53/docker_init.sh
@@ -0,0 +1,2 @@
+#!/bin/sh
+docker build src/docker_modules/MUSIC/6613c53 -t 'music:6613c53'
diff --git a/src/docker_modules/MultiQC/1.0/Dockerfile b/src/docker_modules/MultiQC/1.0/Dockerfile
index 09b218a95597c3df504e78bc2043d2a139730016..d351f1c6a979de6616edce3fd276be262bad8b43 100644
--- a/src/docker_modules/MultiQC/1.0/Dockerfile
+++ b/src/docker_modules/MultiQC/1.0/Dockerfile
@@ -6,10 +6,16 @@ ENV PACKAGES build-essential=12.4* \
python3-pip=9.0.1* \
python3-setuptools=39.0.1* \
python3-dev=3.6.5* \
- python3-wheel=0.30.0*
+ python3-wheel=0.30.0* \
+ locales
RUN apt-get update && \
apt-get install -y --no-install-recommends ${PACKAGES} && \
apt-get clean
+RUN locale-gen en_US.UTF-8
+ENV LC_ALL=en_US.utf-8
+ENV LANG=en_US.utf-8
+
RUN pip3 install multiqc==${MULTIQC_VERSION}
+
diff --git a/src/docker_modules/RSEM/1.3.0/Dockerfile b/src/docker_modules/RSEM/1.3.0/Dockerfile
index 1ccdaa74586943d175058c9c9c478e4c04bcdcec..337521c0496db33c93c20c8fd4d756efcba603a8 100644
--- a/src/docker_modules/RSEM/1.3.0/Dockerfile
+++ b/src/docker_modules/RSEM/1.3.0/Dockerfile
@@ -4,7 +4,7 @@ MAINTAINER Laurent Modolo
ENV RSEM_VERSION=1.3.0
ENV BOWTIE2_VERSION=2.3.4.1
ENV SAMTOOLS_VERSION=1.7
-ENV PACKAGES git=1:2.17.0* \
+ENV PACKAGES git=1:2.17* \
build-essential=12.4* \
ca-certificates=20180409 \
zlib1g-dev=1:1.2.11* \
diff --git a/src/docker_modules/picard/2.18.11/Dockerfile b/src/docker_modules/picard/2.18.11/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..6a358e55bf36a4be4842335f47491ec8ac3a4ced
--- /dev/null
+++ b/src/docker_modules/picard/2.18.11/Dockerfile
@@ -0,0 +1,19 @@
+FROM ubuntu:18.04
+MAINTAINER Laurent Modolo
+
+ENV PICARD_VERSION=2.18.11
+ENV PACKAGES default-jre=2:1.1* \
+ curl=7.58.0* \
+ ca-certificates=20180409
+
+
+RUN apt-get update && \
+ apt-get install -y --no-install-recommends ${PACKAGES} && \
+ apt-get clean
+
+RUN curl -k -L https://github.com/broadinstitute/picard/releases/download/${PICARD_VERSION}/picard.jar -o picard.jar && \
+ mkdir -p /usr/share/java/ && \
+ mv picard.jar /usr/share/java/
+
+COPY PicardCommandLine /usr/bin/
+RUN chmod +x /usr/bin/PicardCommandLine
diff --git a/src/docker_modules/picard/2.18.11/PicardCommandLine b/src/docker_modules/picard/2.18.11/PicardCommandLine
new file mode 100644
index 0000000000000000000000000000000000000000..ce067365785f2f03c722668eff8d80a94b9b34d3
--- /dev/null
+++ b/src/docker_modules/picard/2.18.11/PicardCommandLine
@@ -0,0 +1,15 @@
+#!/bin/sh
+set -eu
+PRG="$(basename -- "$0")"
+case "$PRG" in
+picard-tools)
+ echo 1>&2 'Warning: picard-tools is deprecated and should be replaced by PicardCommandLine'
+ ;;
+PicardCommandLine)
+ ;;
+*)
+ set -- "$PRG" "$@"
+ ;;
+esac
+
+exec java ${JAVA_OPTIONS-} -jar /usr/share/java/picard.jar "$@"
diff --git a/src/docker_modules/picard/2.18.11/docker_init.sh b/src/docker_modules/picard/2.18.11/docker_init.sh
new file mode 100755
index 0000000000000000000000000000000000000000..7546e343730c0380b749031baec984c1838b3a88
--- /dev/null
+++ b/src/docker_modules/picard/2.18.11/docker_init.sh
@@ -0,0 +1,2 @@
+#!/bin/sh
+docker build src/docker_modules/picard/2.18.11 -t 'picard:2.18.11'
diff --git a/src/fasta_sampler.nf b/src/fasta_sampler.nf
deleted file mode 100644
index d1200ed496c77756cde525835f581b71b2528990..0000000000000000000000000000000000000000
--- a/src/fasta_sampler.nf
+++ /dev/null
@@ -1,18 +0,0 @@
-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} > ${fasta.baseName}_sample.fasta
-"""
-}
diff --git a/src/nf_modules/BEDtools/bedtools.config b/src/nf_modules/BEDtools/fasta_from_bed.config
similarity index 100%
rename from src/nf_modules/BEDtools/bedtools.config
rename to src/nf_modules/BEDtools/fasta_from_bed.config
diff --git a/src/nf_modules/BEDtools/bedtools.nf b/src/nf_modules/BEDtools/fasta_from_bed.nf
similarity index 100%
rename from src/nf_modules/BEDtools/bedtools.nf
rename to src/nf_modules/BEDtools/fasta_from_bed.nf
diff --git a/src/nf_modules/BEDtools/tests/tests.sh b/src/nf_modules/BEDtools/tests.sh
similarity index 52%
rename from src/nf_modules/BEDtools/tests/tests.sh
rename to src/nf_modules/BEDtools/tests.sh
index f27c274f45cdf0fab1003f81986d96b29f50fdc2..632ba5bff13f65685e3ff521f4a1496b337b55d9 100755
--- a/src/nf_modules/BEDtools/tests/tests.sh
+++ b/src/nf_modules/BEDtools/tests.sh
@@ -1,5 +1,5 @@
-nextflow src/nf_modules/BEDtools/tests/fasta_from_bed.nf \
- -c src/nf_modules/BEDtools/bedtools.config \
+./nextflow src/nf_modules/BEDtools/fasta_from_bed.nf \
+ -c src/nf_modules/BEDtools/fasta_from_bed.config \
-profile docker \
--fasta "data/tiny_dataset/fasta/tiny_v2.fasta" \
--bed "data/tiny_dataset/annot/tiny.bed" \
diff --git a/src/nf_modules/BEDtools/tests/fasta_from_bed.nf b/src/nf_modules/BEDtools/tests/fasta_from_bed.nf
deleted file mode 100644
index 372f89e958f5fcf9256c37000f86e6b552e31def..0000000000000000000000000000000000000000
--- a/src/nf_modules/BEDtools/tests/fasta_from_bed.nf
+++ /dev/null
@@ -1,33 +0,0 @@
-params.fastq = "$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
-"""
-}
diff --git a/src/nf_modules/Bowtie/indexing.config b/src/nf_modules/Bowtie/indexing.config
new file mode 100644
index 0000000000000000000000000000000000000000..d5851003aa4c3c95b34eb78de95e20ff17aee390
--- /dev/null
+++ b/src/nf_modules/Bowtie/indexing.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $index_fasta {
+ container = "bowtie:1.2.2"
+ }
+ }
+ }
+ sge {
+ process{
+ $index_fasta {
+ beforeScript = "module purge; module load Bowtie/1.2.2"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/Bowtie/indexing.nf b/src/nf_modules/Bowtie/indexing.nf
new file mode 100644
index 0000000000000000000000000000000000000000..537d684b4bb39412eccfe31aec7c07d9312981d9
--- /dev/null
+++ b/src/nf_modules/Bowtie/indexing.nf
@@ -0,0 +1,33 @@
+/* fasta indexing */
+
+params.fasta = "$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
+"""
+}
+
diff --git a/src/nf_modules/Bowtie/mapping_paired.config b/src/nf_modules/Bowtie/mapping_paired.config
new file mode 100644
index 0000000000000000000000000000000000000000..86cc4bb7f3c6c553811f18ed64f03c003e4780ab
--- /dev/null
+++ b/src/nf_modules/Bowtie/mapping_paired.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $mapping_fastq {
+ container = "bowtie:1.2.2"
+ }
+ }
+ }
+ sge {
+ process{
+ $mapping_fastq {
+ beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie/1.2.2"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/Bowtie/mapping_paired.nf b/src/nf_modules/Bowtie/mapping_paired.nf
new file mode 100644
index 0000000000000000000000000000000000000000..cc9f40b265c61cf0609970fe7501d7267318cf9f
--- /dev/null
+++ b/src/nf_modules/Bowtie/mapping_paired.nf
@@ -0,0 +1,54 @@
+/*
+* mapping paired fastq
+*/
+
+params.fastq = "$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
+"""
+}
+
+
diff --git a/src/nf_modules/Bowtie/mapping_single.config b/src/nf_modules/Bowtie/mapping_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..86cc4bb7f3c6c553811f18ed64f03c003e4780ab
--- /dev/null
+++ b/src/nf_modules/Bowtie/mapping_single.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $mapping_fastq {
+ container = "bowtie:1.2.2"
+ }
+ }
+ }
+ sge {
+ process{
+ $mapping_fastq {
+ beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie/1.2.2"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/Bowtie/mapping_single.nf b/src/nf_modules/Bowtie/mapping_single.nf
new file mode 100644
index 0000000000000000000000000000000000000000..ad9754d1545e1154e2fa9bf18bcfde065738723a
--- /dev/null
+++ b/src/nf_modules/Bowtie/mapping_single.nf
@@ -0,0 +1,50 @@
+/*
+* mapping single end fastq
+*/
+
+params.fastq = "$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" ${file_id}_bowtie_report.txt; then
+ exit 1
+fi
+"""
+}
diff --git a/src/nf_modules/Bowtie/tests.sh b/src/nf_modules/Bowtie/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..803f62814bc7d12e6b595b6a17ae9e96f684b6e2
--- /dev/null
+++ b/src/nf_modules/Bowtie/tests.sh
@@ -0,0 +1,17 @@
+./nextflow src/nf_modules/Bowtie/indexing.nf \
+ -c src/nf_modules/Bowtie/indexing.config \
+ -profile docker \
+ --fasta "data/tiny_dataset/fasta/tiny_v2.fasta"
+
+./nextflow src/nf_modules/Bowtie/mapping_single.nf \
+ -c src/nf_modules/Bowtie/mapping_single.config \
+ -profile docker \
+ --index "results/mapping/index/*.ebwt" \
+ --fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
+
+./nextflow src/nf_modules/Bowtie/mapping_paired.nf \
+ -c src/nf_modules/Bowtie/mapping_paired.config \
+ -profile docker \
+ --index "results/mapping/index/*.ebwt" \
+ --fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
+
diff --git a/src/nf_modules/Bowtie2/bowtie2.nf b/src/nf_modules/Bowtie2/bowtie2.nf
deleted file mode 100644
index 30b75312ceba63ba5df43fb2c17e7d2a73102e2a..0000000000000000000000000000000000000000
--- a/src/nf_modules/Bowtie2/bowtie2.nf
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
-* Bowtie2 :
-* Imputs : fastq files
-* Imputs : fasta files
-* Output : bam files
-*/
-
-/* fasta indexing */
-params.fasta = "$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
-
- script:
-"""
-bowtie2-build --threads ${task.cpus} ${fasta} ${fasta.baseName}.index &> ${fasta.baseName}_bowtie2_report.txt
-
-if grep -q "Error" ${fasta.baseName}_bowtie2_report.txt; then
- exit 1
-fi
-"""
-}
-
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$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.toList()
-
- output:
- set pair_id, "*.bam" into bam_files
-
- script:
-"""
- bowtie2 --very-sensitive -p ${task.cpus} -x ${index[0].baseName} \
- -1 ${reads[0]} -2 ${reads[1]} 2> \
- ${pair_id}_bowtie2_report.txt | \
- samtools view -Sb - > ${pair_id}.bam
-
-if grep -q "Error" ${pair_id}_bowtie2_report.txt; then
- exit 1
-fi
-"""
-}
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$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}" }
- .set { fastq_files }
-Channel
- .fromPath( params.index )
- .ifEmpty { error "Cannot find any index files matching: ${params.index}" }
- .set { index_files }
-
-process mapping_fastq {
- tag "$reads.baseName"
- cpus 4
- publishDir "results/mapping/bams/", mode: 'copy'
-
- input:
- file reads from fastq_files
- file index from index_files.toList()
-
- output:
- file "*.bam" into bam_files
-
- script:
-"""
-bowtie2 --very_sensitive -p ${task.cpus} -x ${index[0].baseName} \
--U ${reads} 2> \
-${reads.baseName}_bowtie2_report.txt | \
-samtools view -Sb - > ${reads.baseName}.bam
-
-if grep -q "Error" ${fasta.baseName}_bowtie2_report.txt; then
- exit 1
-fi
-"""
-}
diff --git a/src/nf_modules/Bowtie2/indexing.config b/src/nf_modules/Bowtie2/indexing.config
new file mode 100644
index 0000000000000000000000000000000000000000..60f60547c31e5c6fea842e3c798940a2ba6b98c5
--- /dev/null
+++ b/src/nf_modules/Bowtie2/indexing.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $index_fasta {
+ container = "bowtie2:2.3.4.1"
+ }
+ }
+ }
+ sge {
+ process{
+ $index_fasta {
+ beforeScript = "module purge; module load Bowtie2/2.3.4.1"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/Bowtie2/tests/index.nf b/src/nf_modules/Bowtie2/indexing.nf
similarity index 93%
rename from src/nf_modules/Bowtie2/tests/index.nf
rename to src/nf_modules/Bowtie2/indexing.nf
index 2636f4be09ab1ff24142ab64ba9bf932f44a2233..4f3cde5e990f3528f2f000c8e68131edafdecf97 100644
--- a/src/nf_modules/Bowtie2/tests/index.nf
+++ b/src/nf_modules/Bowtie2/indexing.nf
@@ -17,6 +17,7 @@ process index_fasta {
output:
file "*.index*" into index_files
+ file "*_report.txt" into indexing_report
script:
"""
diff --git a/src/nf_modules/Bowtie2/bowtie2.config b/src/nf_modules/Bowtie2/mapping_paired.config
similarity index 66%
rename from src/nf_modules/Bowtie2/bowtie2.config
rename to src/nf_modules/Bowtie2/mapping_paired.config
index e34b42f06980b9d1ac941fe184a899f2081f1ece..a8cd2991e8775c96045263645cf98079002275b1 100644
--- a/src/nf_modules/Bowtie2/bowtie2.config
+++ b/src/nf_modules/Bowtie2/mapping_paired.config
@@ -3,9 +3,6 @@ profiles {
docker.temp = 'auto'
docker.enabled = true
process {
- $index_fasta {
- container = "bowtie2:2.3.4.1"
- }
$mapping_fastq {
container = "bowtie2:2.3.4.1"
}
@@ -13,9 +10,6 @@ profiles {
}
sge {
process{
- $index_fasta {
- beforeScript = "module purge; module load Bowtie2/2.3.4.1"
- }
$mapping_fastq {
beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie2/2.3.4.1"
}
diff --git a/src/nf_modules/Bowtie2/tests/mapping_paired.nf b/src/nf_modules/Bowtie2/mapping_paired.nf
similarity index 63%
rename from src/nf_modules/Bowtie2/tests/mapping_paired.nf
rename to src/nf_modules/Bowtie2/mapping_paired.nf
index 835d0ca3c96e5f68c1650aeadff280eced9d5a11..7422b143606e720138d07ea3b04fe16d4301c117 100644
--- a/src/nf_modules/Bowtie2/tests/mapping_paired.nf
+++ b/src/nf_modules/Bowtie2/mapping_paired.nf
@@ -20,17 +20,24 @@ process mapping_fastq {
input:
set pair_id, file(reads) from fastq_files
- file index from index_files.toList()
+ file index from index_files.collect()
output:
set pair_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\.bt2/ && !(index_file =~ /.*\.rev\.1\.bt2/)) {
+ index_id = ( index_file =~ /(.*)\.1\.bt2/)[0][1]
+ }
+ }
"""
- bowtie2 --very-sensitive -p ${task.cpus} -x ${index[0].baseName} \
- -1 ${reads[0]} -2 ${reads[1]} 2> \
- ${pair_id}_bowtie2_report.txt | \
- samtools view -Sb - > ${pair_id}.bam
+bowtie2 --very-sensitive -p ${task.cpus} -x ${index_id} \
+-1 ${reads[0]} -2 ${reads[1]} 2> \
+${pair_id}_bowtie2_report.txt | \
+samtools view -Sb - > ${pair_id}.bam
if grep -q "Error" ${pair_id}_bowtie2_report.txt; then
exit 1
diff --git a/src/nf_modules/Bowtie2/mapping_single.config b/src/nf_modules/Bowtie2/mapping_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..a8cd2991e8775c96045263645cf98079002275b1
--- /dev/null
+++ b/src/nf_modules/Bowtie2/mapping_single.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $mapping_fastq {
+ container = "bowtie2:2.3.4.1"
+ }
+ }
+ }
+ sge {
+ process{
+ $mapping_fastq {
+ beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie2/2.3.4.1"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/Bowtie2/mapping_single.nf b/src/nf_modules/Bowtie2/mapping_single.nf
new file mode 100644
index 0000000000000000000000000000000000000000..66676991aae710a5263d763dee2ad7dbde6b7a51
--- /dev/null
+++ b/src/nf_modules/Bowtie2/mapping_single.nf
@@ -0,0 +1,46 @@
+params.fastq = "$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\.bt2/ && !(index_file =~ /.*\.rev\.1\.bt2/)) {
+ index_id = ( index_file =~ /(.*)\.1\.bt2/)[0][1]
+ }
+ }
+"""
+bowtie2 --very-sensitive -p ${task.cpus} -x ${index_id} \
+-U ${reads} 2> \
+${file_id}_bowtie2_report.txt | \
+samtools view -Sb - > ${file_id}.bam
+
+if grep -q "Error" ${file_id}_bowtie2_report.txt; then
+ exit 1
+fi
+"""
+}
diff --git a/src/nf_modules/Bowtie2/tests/tests.sh b/src/nf_modules/Bowtie2/tests.sh
similarity index 50%
rename from src/nf_modules/Bowtie2/tests/tests.sh
rename to src/nf_modules/Bowtie2/tests.sh
index 55e88edb145255aea143a632aea6e4b3cb5f2833..ab1483824cd1f9755d09495cd050c45cc4a82d30 100755
--- a/src/nf_modules/Bowtie2/tests/tests.sh
+++ b/src/nf_modules/Bowtie2/tests.sh
@@ -1,16 +1,16 @@
-nextflow src/nf_modules/Bowtie2/tests/index.nf \
- -c src/nf_modules/Bowtie2/bowtie2.config \
+./nextflow src/nf_modules/Bowtie2/indexing.nf \
+ -c src/nf_modules/Bowtie2/indexing.config \
-profile docker \
--fasta "data/tiny_dataset/fasta/tiny_v2.fasta"
-nextflow src/nf_modules/Bowtie2/tests/mapping_single.nf \
- -c src/nf_modules/Bowtie2/bowtie2.config \
+./nextflow src/nf_modules/Bowtie2/mapping_single.nf \
+ -c src/nf_modules/Bowtie2/mapping_single.config \
-profile docker \
--index "data/tiny_dataset/fasta/*.bt2" \
--fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
-nextflow src/nf_modules/Bowtie2/tests/mapping_paired.nf \
- -c src/nf_modules/Bowtie2/bowtie2.config \
+./nextflow src/nf_modules/Bowtie2/mapping_paired.nf \
+ -c src/nf_modules/Bowtie2/mapping_paired.config \
-profile docker \
--index "data/tiny_dataset/fasta/*.bt2" \
--fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
diff --git a/src/nf_modules/Bowtie2/tests/mapping_single.nf b/src/nf_modules/Bowtie2/tests/mapping_single.nf
deleted file mode 100644
index c5c7f585514c7ba97da98a660c02964a4d5a91b1..0000000000000000000000000000000000000000
--- a/src/nf_modules/Bowtie2/tests/mapping_single.nf
+++ /dev/null
@@ -1,38 +0,0 @@
-params.fastq = "$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}" }
- .set { fastq_files }
-Channel
- .fromPath( params.index )
- .ifEmpty { error "Cannot find any index files matching: ${params.index}" }
- .set { index_files }
-
-process mapping_fastq {
- tag "$reads.baseName"
- cpus 4
- publishDir "results/mapping/bams/", mode: 'copy'
-
- input:
- file reads from fastq_files
- file index from index_files.toList()
-
- output:
- file "*.bam" into bam_files
-
- script:
-"""
-bowtie2 --very_sensitive -p ${task.cpus} -x ${index[0].baseName} \
--U ${reads} 2> \
-${reads.baseName}_bowtie2_report.txt | \
-samtools view -Sb - > ${reads.baseName}.bam
-
-if grep -q "Error" ${reads.baseName}_bowtie2_report.txt; then
- exit 1
-fi
-"""
-}
diff --git a/src/nf_modules/FastQC/fastqc_paired.config b/src/nf_modules/FastQC/fastqc_paired.config
new file mode 100644
index 0000000000000000000000000000000000000000..a6589845aa98db0b4f6eaa663246db2604eb210b
--- /dev/null
+++ b/src/nf_modules/FastQC/fastqc_paired.config
@@ -0,0 +1,25 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $fastqc_fastq {
+ container = "fastqc:0.11.5"
+ }
+ }
+ }
+ sge {
+ process{
+ $fastqc_fastq {
+ beforeScript = "module purge; module load FastQC/0.11.5"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'monointeldeb128'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/FastQC/fastqc_paired.nf b/src/nf_modules/FastQC/fastqc_paired.nf
new file mode 100644
index 0000000000000000000000000000000000000000..6755edec7dca244b1c1581dc6459cd2b8afcc996
--- /dev/null
+++ b/src/nf_modules/FastQC/fastqc_paired.nf
@@ -0,0 +1,26 @@
+params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
+
+log.info "fastq files : ${params.fastq}"
+
+Channel
+ .fromFilePairs( params.fastq )
+ .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .set { fastq_files }
+
+process fastqc_fastq {
+ tag "$pair_id"
+ publishDir "results/fastq/fastqc/", mode: 'copy'
+
+ input:
+ set pair_id, file(reads) from fastq_files
+
+ output:
+ file "*.{zip,html}" into fastqc_report
+
+ script:
+"""
+fastqc --quiet --threads ${task.cpus} --format fastq --outdir ./ \
+${reads[0]} ${reads[1]}
+"""
+}
+
diff --git a/src/nf_modules/FastQC/fastqc_single.config b/src/nf_modules/FastQC/fastqc_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..a6589845aa98db0b4f6eaa663246db2604eb210b
--- /dev/null
+++ b/src/nf_modules/FastQC/fastqc_single.config
@@ -0,0 +1,25 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $fastqc_fastq {
+ container = "fastqc:0.11.5"
+ }
+ }
+ }
+ sge {
+ process{
+ $fastqc_fastq {
+ beforeScript = "module purge; module load FastQC/0.11.5"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'monointeldeb128'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/FastQC/fastqc_single.nf b/src/nf_modules/FastQC/fastqc_single.nf
new file mode 100644
index 0000000000000000000000000000000000000000..459841651ec85102f38a980bc621d0ca1c8626bb
--- /dev/null
+++ b/src/nf_modules/FastQC/fastqc_single.nf
@@ -0,0 +1,27 @@
+params.fastq = "$baseDir/data/fastq/*.fastq"
+
+log.info "fastq files : ${params.fastq}"
+
+Channel
+ .fromPath( params.fastq )
+ .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
+ .set { fastq_files }
+
+process fastqc_fastq {
+ tag "$file_id"
+ publishDir "results/fastq/fastqc/", mode: 'copy'
+ cpus = 1
+
+ input:
+ set file_id, file(reads) from fastq_files
+
+ output:
+ file "*.{zip,html}" into fastqc_report
+
+ script:
+"""
+fastqc --quiet --threads ${task.cpus} --format fastq --outdir ./ ${reads}
+"""
+}
+
diff --git a/src/nf_modules/FastQC/tests.sh b/src/nf_modules/FastQC/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..de58b1028e221f05b7d084a7df6df5e8a077c4ec
--- /dev/null
+++ b/src/nf_modules/FastQC/tests.sh
@@ -0,0 +1,9 @@
+./nextflow src/nf_modules/FastQC/fastqc_paired.nf \
+ -c src/nf_modules/FastQC/fastqc_paired.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
+
+./nextflow src/nf_modules/FastQC/fastqc_single.nf \
+ -c src/nf_modules/FastQC/fastqc_single.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_S.fastq"
diff --git a/src/nf_modules/HTSeq/htseq.config b/src/nf_modules/HTSeq/htseq.config
index ab3cc3a268f8c3d0f0233beb184c2ace5d9b7031..00f2fafb921828b21fe18d57240b9a943dcd2fb9 100644
--- a/src/nf_modules/HTSeq/htseq.config
+++ b/src/nf_modules/HTSeq/htseq.config
@@ -3,6 +3,9 @@ profiles {
docker.temp = 'auto'
docker.enabled = true
process {
+ $sort_bam {
+ container = "samtools:1.7"
+ }
$counting {
container = "htseq:0.8.0"
}
@@ -10,6 +13,9 @@ profiles {
}
sge {
process{
+ $sort_bam {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
$trimming {
beforeScript = "module purge; module load HTSeq/0.8.0"
}
diff --git a/src/nf_modules/HTSeq/htseq.nf b/src/nf_modules/HTSeq/htseq.nf
index 5aa2f739bd64381724450640e9828a0b4fce1494..7cade9a55b17ced135f32a36ffd90dc5354b72af 100644
--- a/src/nf_modules/HTSeq/htseq.nf
+++ b/src/nf_modules/HTSeq/htseq.nf
@@ -1,11 +1,3 @@
-/*
-* htseq :
-* Imputs : sorted bams files
-* Imputs : gtf
-* Output : counts files
-*/
-/* quality trimming */
-
params.bam = "$baseDir/data/bam/*.bam"
params.gtf = "$baseDir/data/annotation/*.gtf"
@@ -15,18 +7,36 @@ log.info "gtf files : ${params.gtf}"
Channel
.fromPath( params.bam )
.ifEmpty { error "Cannot find any fastq files matching: ${params.bam}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { bam_files }
Channel
.fromPath( params.gtf )
.ifEmpty { error "Cannot find any gtf file matching: ${params.gtf}" }
.set { gtf_file }
+process sort_bam {
+ tag "$file_id"
+ cpus 4
+
+ input:
+ set file_id, file(bam) from bam_files
+
+ output:
+ set file_id, "*_sorted.sam" into sorted_bam_files
+
+ script:
+"""
+# sort bam by name
+samtools sort -@ ${task.cpus} -n -O SAM -o ${file_id}_sorted.sam ${bam}
+"""
+}
+
process counting {
- tag "$bam.baseName"
+ tag "$file_id"
publishDir "results/quantification/", mode: 'copy'
input:
- file bam from bam_files
+ set file_id, file(bam) from sorted_bam_files
file gtf from gtf_file
output:
@@ -34,7 +44,9 @@ process counting {
script:
"""
-htseq-count -r pos --mode=intersection-nonempty -a 10 -s no -t exon -i gene_id \
---format=bam ${bam} ${gtf} > ${bam.baseName}.count
+htseq-count ${bam} ${gtf} \
+-r pos --mode=intersection-nonempty -a 10 -s no -t exon -i gene_id \
+> ${file_id}.count
"""
}
+
diff --git a/src/nf_modules/HTSeq/tests/tests.sh b/src/nf_modules/HTSeq/tests.sh
similarity index 75%
rename from src/nf_modules/HTSeq/tests/tests.sh
rename to src/nf_modules/HTSeq/tests.sh
index 7ccef1815eb2f2e430095f764230160b26be85a6..4a2b5ceb62651dc0178fd026f29cd4310ecab29b 100755
--- a/src/nf_modules/HTSeq/tests/tests.sh
+++ b/src/nf_modules/HTSeq/tests.sh
@@ -1,4 +1,4 @@
-nextflow src/nf_modules/HTSeq/tests/counting.nf \
+./nextflow src/nf_modules/HTSeq/htseq.nf \
-c src/nf_modules/HTSeq/htseq.config \
-profile docker \
--gtf "data/tiny_dataset/annot/tiny.gff" \
diff --git a/src/nf_modules/HTSeq/tests/counting.nf b/src/nf_modules/HTSeq/tests/counting.nf
deleted file mode 100644
index f11736b1443f36e13b1986518f5de1c9187ca62e..0000000000000000000000000000000000000000
--- a/src/nf_modules/HTSeq/tests/counting.nf
+++ /dev/null
@@ -1,33 +0,0 @@
-params.bam = "$baseDir/data/bam/*.bam"
-params.gtf = "$baseDir/data/annotation/*.gtf"
-
-log.info "bam files : ${params.bam}"
-log.info "gtf files : ${params.gtf}"
-
-Channel
- .fromPath( params.bam )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.bam}" }
- .set { bam_files }
-Channel
- .fromPath( params.gtf )
- .ifEmpty { error "Cannot find any gtf file matching: ${params.gtf}" }
- .set { gtf_file }
-
-process counting {
- tag "$bam.baseName"
- publishDir "results/quantification/", mode: 'copy'
-
- input:
- file bam from bam_files
- file gtf from gtf_file
-
- output:
- file "*.count" into count_files
-
- script:
-"""
-htseq-count -r pos --mode=intersection-nonempty -a 10 -s no -t exon -i gene_id \
---format=bam ${bam} ${gtf} > ${bam.baseName}.count
-"""
-}
-
diff --git a/src/nf_modules/Kallisto/indexing.config b/src/nf_modules/Kallisto/indexing.config
new file mode 100644
index 0000000000000000000000000000000000000000..94c14cd210981318ff555888b96f3c43796a9c66
--- /dev/null
+++ b/src/nf_modules/Kallisto/indexing.config
@@ -0,0 +1,26 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $index_fasta {
+ container = "kallisto:0.44.0"
+ }
+ }
+ }
+ sge {
+ process{
+ $index_fasta {
+ beforeScript = "module purge; module load Kallisto/0.44.0"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/Kallisto/tests/index.nf b/src/nf_modules/Kallisto/indexing.nf
similarity index 83%
rename from src/nf_modules/Kallisto/tests/index.nf
rename to src/nf_modules/Kallisto/indexing.nf
index cae4bb03384a919d998562aeefe98c9b1557fea3..9e38260f87e9bfa4384b69ef440c73acb6feba05 100644
--- a/src/nf_modules/Kallisto/tests/index.nf
+++ b/src/nf_modules/Kallisto/indexing.nf
@@ -17,11 +17,12 @@ process index_fasta {
output:
file "*.index*" into index_files
+ file "*_kallisto_report.txt" into index_files_report
script:
"""
kallisto index -k 31 --make-unique -i ${fasta.baseName}.index ${fasta} \
-> ${fasta.baseName}_kallisto_report.txt
+2> ${fasta.baseName}_kallisto_report.txt
"""
}
diff --git a/src/nf_modules/Kallisto/kallisto.nf b/src/nf_modules/Kallisto/kallisto.nf
deleted file mode 100644
index 8867a0c3ab74393a43229e9bee4a39e71f4eddc2..0000000000000000000000000000000000000000
--- a/src/nf_modules/Kallisto/kallisto.nf
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
-* Kallisto :
-* Imputs : fastq files
-* Imputs : fasta files
-* Output : bam files
-*/
-
-/* fasta indexing */
-params.fasta = "$baseDir/data/bam/*.fasta"
-
-log.info "fasta files : ${params.fasta}"
-
-Channel
- .fromPath( params.fasta )
- .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
- .set { fasta_file }
-
-process index_fasta {
- tag "$fasta.baseName"
- publishDir "results/mapping/index/", mode: 'copy'
-
- input:
- file fasta from fasta_file
-
- output:
- file "*.index*" into index_files
-
- script:
-"""
-kallisto index -k 31 --make-unique -i ${fasta.baseName}.index ${fasta} \
-> ${fasta.baseName}_kallisto_report.txt
-"""
-}
-
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$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: ${params.index}" }
- .set { index_files }
-
-process mapping_fastq {
- tag "$reads"
- cpus 4
- publishDir "results/mapping/quantification/", mode: 'copy'
-
- input:
- set pair_id, file(reads) from fastq_files
- file index from index_files.toList()
-
- output:
- file "*" into counts_files
-
- script:
-"""
-mkdir ${reads[0].baseName}
-kallisto quant -i ${index} -t ${task.cpus} \
---bias --bootstrap-samples 100 -o ${pair_id} \
-${reads[0]} ${reads[1]} &> ${pair_id}_kallisto_report.txt
-"""
-}
-
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*.fastq"
-params.index = "$baseDir/data/index/*.index*"
-params.mean = 200
-params.sd = 100
-
-log.info "fastq files : ${params.fastq}"
-log.info "index files : ${params.index}"
-log.info "mean read size: ${params.mean}"
-log.info "sd read size: ${params.sd}"
-
-Channel
- .fromPath( 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: ${params.index}" }
- .set { index_files }
-
-process mapping_fastq {
- tag "$reads.baseName"
- cpus 4
- publishDir "results/mapping/quantification/", mode: 'copy'
-
- input:
- file reads from fastq_files
- file index from index_files.toList()
-
- output:
- file "*" into count_files
-
- script:
-"""
-mkdir ${reads.baseName}
-kallisto quant -i ${index} -t ${task.cpus} --single
---bias --bootstrap-samples 100 -o ${reads.baseName} \
--l ${params.mean} -s ${params.sd} -o ./ \
-${reads} > ${reads.baseName}_kallisto_report.txt
-"""
-}
-
diff --git a/src/nf_modules/Kallisto/kallisto.config b/src/nf_modules/Kallisto/mapping_paired.config
similarity index 57%
rename from src/nf_modules/Kallisto/kallisto.config
rename to src/nf_modules/Kallisto/mapping_paired.config
index da7f54e0dfa345ef1b599ce328ceca40747dd9c6..de674527ae0735b3797dc69fe7ae90b6557e1fa1 100644
--- a/src/nf_modules/Kallisto/kallisto.config
+++ b/src/nf_modules/Kallisto/mapping_paired.config
@@ -3,9 +3,6 @@ profiles {
docker.temp = 'auto'
docker.enabled = true
process {
- $index_fasta {
- container = "kallisto:0.44.0"
- }
$mapping_fastq {
container = "kallisto:0.44.0"
}
@@ -13,17 +10,6 @@ profiles {
}
sge {
process{
- $index_fasta {
- beforeScript = "module purge; module load Kallisto/0.44.0"
- executor = "sge"
- cpus = 1
- memory = "5GB"
- time = "6h"
- queueSize = 1000
- pollInterval = '60sec'
- queue = 'h6-E5-2667v4deb128'
- penv = 'openmp8'
- }
$mapping_fastq {
beforeScript = "module purge; module load Kallisto/0.44.0"
executor = "sge"
diff --git a/src/nf_modules/Kallisto/tests/mapping_paired.nf b/src/nf_modules/Kallisto/mapping_paired.nf
similarity index 86%
rename from src/nf_modules/Kallisto/tests/mapping_paired.nf
rename to src/nf_modules/Kallisto/mapping_paired.nf
index 8e8f94c9172c409a5af3be0be02f3970e5983030..4f4ad3d167292dcf9919506f89103dbbbab7f709 100644
--- a/src/nf_modules/Kallisto/tests/mapping_paired.nf
+++ b/src/nf_modules/Kallisto/mapping_paired.nf
@@ -20,17 +20,17 @@ process mapping_fastq {
input:
set pair_id, file(reads) from fastq_files
- file index from index_files.toList()
+ file index from index_files.collect()
output:
file "*" into counts_files
script:
"""
-mkdir ${reads[0].baseName}
+mkdir ${pair_id}
kallisto quant -i ${index} -t ${task.cpus} \
--bias --bootstrap-samples 100 -o ${pair_id} \
-${reads[0]} ${reads[1]} &> ${pair_id}_kallisto_report.txt
+${reads[0]} ${reads[1]} &> ${pair_id}/kallisto_report.txt
"""
}
diff --git a/src/nf_modules/Kallisto/mapping_single.config b/src/nf_modules/Kallisto/mapping_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..de674527ae0735b3797dc69fe7ae90b6557e1fa1
--- /dev/null
+++ b/src/nf_modules/Kallisto/mapping_single.config
@@ -0,0 +1,26 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $mapping_fastq {
+ container = "kallisto:0.44.0"
+ }
+ }
+ }
+ sge {
+ process{
+ $mapping_fastq {
+ beforeScript = "module purge; module load Kallisto/0.44.0"
+ executor = "sge"
+ cpus = 4
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/Kallisto/tests/mapping_single.nf b/src/nf_modules/Kallisto/mapping_single.nf
similarity index 75%
rename from src/nf_modules/Kallisto/tests/mapping_single.nf
rename to src/nf_modules/Kallisto/mapping_single.nf
index 2a46cbe6dc1274a2c46044f01a54e43c981126ad..97861e76faad7a266b279bb6fe8ac77964c94284 100644
--- a/src/nf_modules/Kallisto/tests/mapping_single.nf
+++ b/src/nf_modules/Kallisto/mapping_single.nf
@@ -11,6 +11,7 @@ log.info "sd read size: ${params.sd}"
Channel
.fromPath( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fastq_files }
Channel
.fromPath( params.index )
@@ -18,24 +19,24 @@ Channel
.set { index_files }
process mapping_fastq {
- tag "$reads.baseName"
+ tag "$file_id"
cpus 4
publishDir "results/mapping/quantification/", mode: 'copy'
input:
- file reads from fastq_files
- file index from index_files.toList()
+ set file_id, file(reads) from fastq_files
+ file index from index_files.collect()
output:
file "*" into count_files
script:
"""
-mkdir ${reads.baseName}
+mkdir ${file_id}
kallisto quant -i ${index} -t ${task.cpus} --single \
---bias --bootstrap-samples 100 -o ${reads.baseName} \
+--bias --bootstrap-samples 100 -o ${file_id} \
-l ${params.mean} -s ${params.sd} \
-${reads} > ${reads.baseName}_kallisto_report.txt
+${reads} &> ${file_id}/kallisto_report.txt
"""
}
diff --git a/src/nf_modules/Kallisto/tests/tests.sh b/src/nf_modules/Kallisto/tests.sh
similarity index 50%
rename from src/nf_modules/Kallisto/tests/tests.sh
rename to src/nf_modules/Kallisto/tests.sh
index f83a4cacb2caaa66490b00ba224205af13e92967..0f69fcc40a2cc72aba93094560b2a239d2d42a76 100755
--- a/src/nf_modules/Kallisto/tests/tests.sh
+++ b/src/nf_modules/Kallisto/tests.sh
@@ -1,16 +1,16 @@
-nextflow src/nf_modules/Kallisto/tests/index.nf \
- -c src/nf_modules/Kallisto/kallisto.config \
+./nextflow src/nf_modules/Kallisto/indexing.nf \
+ -c src/nf_modules/Kallisto/indexing.config \
-profile docker \
--fasta "data/tiny_dataset/fasta/tiny_v2.fasta"
-nextflow src/nf_modules/Kallisto/tests/mapping_single.nf \
- -c src/nf_modules/Kallisto/kallisto.config \
+./nextflow src/nf_modules/Kallisto/mapping_single.nf \
+ -c src/nf_modules/Kallisto/mapping_single.config \
-profile docker \
--index "results/mapping/index/tiny_v2.index" \
--fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
-nextflow src/nf_modules/Kallisto/tests/mapping_paired.nf \
- -c src/nf_modules/Kallisto/kallisto.config \
+./nextflow src/nf_modules/Kallisto/mapping_paired.nf \
+ -c src/nf_modules/Kallisto/mapping_paired.config \
-profile docker \
--index "results/mapping/index/tiny_v2.index" \
--fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
diff --git a/src/nf_modules/MUSIC/peak_calling_single.config b/src/nf_modules/MUSIC/peak_calling_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..4685752be3d8e66da4e76aeffc82ce58d50389b3
--- /dev/null
+++ b/src/nf_modules/MUSIC/peak_calling_single.config
@@ -0,0 +1,30 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $compute_mappability {
+ container = "music:6613c53"
+ }
+ $music_preprocessing {
+ container = "music:6613c53"
+ }
+ $music_computation {
+ container = "music:6613c53"
+ }
+ }
+ }
+ sge {
+ process{
+ $compute_mappability {
+ beforeScript = "module purge; module load MUSIC/6613c53"
+ }
+ $music_preprocessing {
+ beforeScript = "module purge; module load MUSIC/6613c53"
+ }
+ $music_computation {
+ beforeScript = "module purge; module load MUSIC/6613c53"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/MUSIC/peak_calling_single.nf b/src/nf_modules/MUSIC/peak_calling_single.nf
new file mode 100644
index 0000000000000000000000000000000000000000..be280394b80e6ddd9644da85f62e8d2be5d843ed
--- /dev/null
+++ b/src/nf_modules/MUSIC/peak_calling_single.nf
@@ -0,0 +1,104 @@
+params.read_size = 100
+params.frag_size = 200
+params.step_l = 50
+params.min_l = 200
+params.max_l = 5000
+log.info "bam files : ${params.bam}"
+log.info "index files : ${params.index}"
+log.info "fasta files : ${params.fasta}"
+
+Channel
+ .fromPath( params.fasta )
+ .ifEmpty { error "Cannot find any bam files matching: ${params.fasta}" }
+ .set { fasta_files }
+Channel
+ .fromPath( params.bam )
+ .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
+ .set { bam_files }
+Channel
+ .fromPath( params.index )
+ .ifEmpty { error "Cannot find any index files matching: ${params.index}" }
+ .set { index_files }
+
+process compute_mappability {
+ tag "${fasta.baseName}"
+
+ input:
+ file index from index_files.collect()
+ file fasta from fasta_files
+
+ output:
+ file "*.bin" into mappability
+ file "temp/chr_ids.txt" into chr_ids
+
+ script:
+
+"""
+generate_multimappability_signal.csh ${fasta} ${params.read_size} ./
+bash temp_map_reads.csh
+bash temp_process_mapping.csh
+"""
+}
+
+process music_preprocessing {
+ tag "${file_id}"
+
+ input:
+ set file_id, file(bam) from bam_files
+ file chr_ids from chr_ids.collect()
+
+ output:
+ set file_id, "preprocessed/*.tar" into preprocessed_bam_files
+
+ script:
+
+"""
+mkdir preprocessed
+samtools view *.bam | \
+MUSIC -preprocess SAM stdin preprocessed/
+mkdir preprocessed/sorted
+MUSIC -sort_reads preprocessed/ preprocessed/sorted/
+mkdir preprocessed/dedup
+MUSIC -remove_duplicates ./preprocessed/sorted 2 preprocessed/dedup/
+cd preprocessed
+tar -c -f ${file_id}.tar *
+"""
+}
+
+preprocessed_bam_files_control = Channel.create()
+preprocessed_bam_files_chip = Channel.create()
+preprocessed_bam_files.choice(
+ preprocessed_bam_files_control,
+ preprocessed_bam_files_chip ) { a -> a[0] =~ /.*control.*/ ? 0 : 1 }
+
+process music_computation {
+ tag "${file_id}"
+ publishDir "results/peak_calling/${file_id}", mode: 'copy'
+
+ input:
+ set file_id, file(control) from preprocessed_bam_files_chip
+ set file_id_control, file(chip) from preprocessed_bam_files_control.collect()
+ file mapp from mappability.collect()
+
+ output:
+ file "*" into music_output_forward
+ file "*.bed" into peaks_forward
+
+ script:
+
+"""
+mkdir mappability control chip
+mv ${mapp} mappability/
+tar -xf ${control} -C control/
+tar -xf ${chip} -C chip/
+
+MUSIC -get_per_win_p_vals_vs_FC -chip chip/ -control control/ \
+ -l_win_step ${params.step_l} \
+ -l_win_min ${params.min_l} -l_win_max ${params.max_l}
+MUSIC -get_multiscale_punctate_ERs \
+ -chip chip/ -control control/ -mapp mappability/ \
+ -l_mapp ${params.read_size} -l_frag ${params.frag_size} -q_val 1 -l_p 0
+ls -l
+"""
+}
diff --git a/src/nf_modules/MUSIC/tests.sh b/src/nf_modules/MUSIC/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..7c6ad078ad2c27cbb378f8cdd6c505be9527fdef
--- /dev/null
+++ b/src/nf_modules/MUSIC/tests.sh
@@ -0,0 +1,8 @@
+cp results/training/bams/sBNLN18.bam results/training/bams/sBNLN18_control.bam
+./nextflow src/nf_modules/MUSIC/peak_calling_single.nf \
+ -c src/nf_modules/MUSIC/peak_calling_single.config \
+ -profile docker \
+ --fasta "results/training/fasta/*.fasta" \
+ --bam "results/training/bams/s*.bam" \
+ --index "results/training/mapping/index/*" \
+ --read_size 50 --frag_size 300
diff --git a/src/nf_modules/MultiQC/multiqc_paired.config b/src/nf_modules/MultiQC/multiqc_paired.config
new file mode 100644
index 0000000000000000000000000000000000000000..c1bda95e70a612c7caf4825930e740faedd1c62d
--- /dev/null
+++ b/src/nf_modules/MultiQC/multiqc_paired.config
@@ -0,0 +1,38 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $fastqc_fastq {
+ container = "fastqc:0.11.5"
+ }
+ $multiqc {
+ container = "multiqc:1.0"
+ }
+ }
+ }
+ sge {
+ process{
+ $fastqc_fastq {
+ beforeScript = "module purge; module load FastQC/0.11.5"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'monointeldeb128'
+ }
+ $multiqc {
+ beforeScript = "module purge; module load FastQC/1.0"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'monointeldeb128'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/MultiQC/multiqc_paired.nf b/src/nf_modules/MultiQC/multiqc_paired.nf
new file mode 100644
index 0000000000000000000000000000000000000000..b459a9bbc8ddd4c89cd51f164d3ef3a14c814841
--- /dev/null
+++ b/src/nf_modules/MultiQC/multiqc_paired.nf
@@ -0,0 +1,43 @@
+params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
+
+log.info "fastq files : ${params.fastq}"
+
+Channel
+ .fromFilePairs( params.fastq )
+ .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .set { fastq_files }
+
+process fastqc_fastq {
+ tag "$pair_id"
+ publishDir "results/fastq/fastqc/", mode: 'copy'
+
+ input:
+ set pair_id, file(reads) from fastq_files
+
+ output:
+ file "*.{zip,html}" into fastqc_report
+
+ script:
+"""
+fastqc --quiet --threads ${task.cpus} --format fastq --outdir ./ \
+${reads[0]} ${reads[1]}
+"""
+}
+
+process multiqc {
+ tag "$report[0].baseName"
+ publishDir "results/fastq/multiqc/", mode: 'copy'
+ cpus = 1
+
+ input:
+ file report from fastqc_report.collect()
+
+ output:
+ file "*multiqc_*" into multiqc_report
+
+ script:
+"""
+multiqc -f .
+"""
+}
+
diff --git a/src/nf_modules/MultiQC/multiqc_single.config b/src/nf_modules/MultiQC/multiqc_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..c1bda95e70a612c7caf4825930e740faedd1c62d
--- /dev/null
+++ b/src/nf_modules/MultiQC/multiqc_single.config
@@ -0,0 +1,38 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $fastqc_fastq {
+ container = "fastqc:0.11.5"
+ }
+ $multiqc {
+ container = "multiqc:1.0"
+ }
+ }
+ }
+ sge {
+ process{
+ $fastqc_fastq {
+ beforeScript = "module purge; module load FastQC/0.11.5"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'monointeldeb128'
+ }
+ $multiqc {
+ beforeScript = "module purge; module load FastQC/1.0"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'monointeldeb128'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/MultiQC/multiqc_single.nf b/src/nf_modules/MultiQC/multiqc_single.nf
new file mode 100644
index 0000000000000000000000000000000000000000..ea1115b546f0776a4970e4a56fefcce5e3b90de9
--- /dev/null
+++ b/src/nf_modules/MultiQC/multiqc_single.nf
@@ -0,0 +1,44 @@
+params.fastq = "$baseDir/data/fastq/*.fastq"
+
+log.info "fastq files : ${params.fastq}"
+
+Channel
+ .fromPath( params.fastq )
+ .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
+ .set { fastq_files }
+
+process fastqc_fastq {
+ tag "$file_id"
+ publishDir "results/fastq/fastqc/", mode: 'copy'
+ cpus = 1
+
+ input:
+ set file_id, file(reads) from fastq_files
+
+ output:
+ file "*.{zip,html}" into fastqc_report
+
+ script:
+"""
+fastqc --quiet --threads ${task.cpus} --format fastq --outdir ./ ${reads}
+"""
+}
+
+process multiqc {
+ tag "$report[0].baseName"
+ publishDir "results/fastq/multiqc/", mode: 'copy'
+ cpus = 1
+
+ input:
+ file report from fastqc_report.collect()
+
+ output:
+ file "*multiqc_*" into multiqc_report
+
+ script:
+"""
+multiqc -f .
+"""
+}
+
diff --git a/src/nf_modules/MultiQC/tests.sh b/src/nf_modules/MultiQC/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..0e38a8e9e9710ec9e0d43a15432c8c8e96c0dfe0
--- /dev/null
+++ b/src/nf_modules/MultiQC/tests.sh
@@ -0,0 +1,9 @@
+./nextflow src/nf_modules/MultiQC/multiqc_paired.nf \
+ -c src/nf_modules/MultiQC/multiqc_paired.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
+
+./nextflow src/nf_modules/MultiQC/multiqc_single.nf \
+ -c src/nf_modules/MultiQC/multiqc_single.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_S.fastq"
diff --git a/src/nf_modules/RSEM/indexing.config b/src/nf_modules/RSEM/indexing.config
new file mode 100644
index 0000000000000000000000000000000000000000..ddf93b6ec57c876681fc508a737b3287e20fdd61
--- /dev/null
+++ b/src/nf_modules/RSEM/indexing.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $index_fasta {
+ container = "rsem:1.3.0"
+ }
+ }
+ }
+ sge {
+ process{
+ $index_fasta {
+ beforeScript = "module purge; module load RSEM/1.3.0; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/RSEM/tests/index.nf b/src/nf_modules/RSEM/indexing.nf
similarity index 100%
rename from src/nf_modules/RSEM/tests/index.nf
rename to src/nf_modules/RSEM/indexing.nf
diff --git a/src/nf_modules/RSEM/rsem.config b/src/nf_modules/RSEM/quantification_paired.config
similarity index 63%
rename from src/nf_modules/RSEM/rsem.config
rename to src/nf_modules/RSEM/quantification_paired.config
index 3209b6bcd480b36b1f5e48a1055db2cc8fc93e93..344ab1e30497454826a5e45537f0e8182fb8dc63 100644
--- a/src/nf_modules/RSEM/rsem.config
+++ b/src/nf_modules/RSEM/quantification_paired.config
@@ -3,9 +3,6 @@ profiles {
docker.temp = 'auto'
docker.enabled = true
process {
- $index_fasta {
- container = "rsem:1.3.0"
- }
$mapping_fastq {
container = "rsem:1.3.0"
}
@@ -13,9 +10,6 @@ profiles {
}
sge {
process{
- $index_fasta {
- beforeScript = "module purge; module load RSEM/1.3.0; module load SAMtools/1.7"
- }
$mapping_fastq {
beforeScript = "module purge; module load RSEM/1.3.0; module load SAMtools/1.7"
}
diff --git a/src/nf_modules/RSEM/tests/quantification_paired.nf b/src/nf_modules/RSEM/quantification_paired.nf
similarity index 71%
rename from src/nf_modules/RSEM/tests/quantification_paired.nf
rename to src/nf_modules/RSEM/quantification_paired.nf
index 75ae42f49524ac0b251a53700220680f0f8f13b4..a22950fd2b4a0548ea7a45bc0a0965992246047f 100644
--- a/src/nf_modules/RSEM/tests/quantification_paired.nf
+++ b/src/nf_modules/RSEM/quantification_paired.nf
@@ -26,14 +26,23 @@ process mapping_fastq {
file "*" into counts_files
script:
-index_name = (index[0].baseName =~ /(.*)\.\d/)[0][1]
+ index_id = index[0]
+ for (index_file in index) {
+ if (index_file =~ /.*\.1\.bt2/ && !(index_file =~ /.*\.rev\.1\.bt2/)) {
+ index_id = ( index_file =~ /(.*)\.1\.bt2/)[0][1]
+ }
+ }
"""
rsem-calculate-expression --bowtie2 \
--bowtie2-path \$(which bowtie2 | sed 's/bowtie2\$//g') \
--bowtie2-sensitivity-level "very_sensitive" \
-output-genome-bam -p ${task.cpus} \
---paired-end ${reads[0]} ${reads[1]} ${index_name} ${pair_id} \
-> ${pair_id}_rsem_bowtie2_report.txt
+--paired-end ${reads[0]} ${reads[1]} ${index_id} ${pair_id} \
+2> ${pair_id}_rsem_bowtie2_report.txt
+
+if grep -q "Error" ${pair_id}_rsem_bowtie2_report.txt; then
+ exit 1
+fi
"""
}
diff --git a/src/nf_modules/RSEM/quantification_single.config b/src/nf_modules/RSEM/quantification_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..344ab1e30497454826a5e45537f0e8182fb8dc63
--- /dev/null
+++ b/src/nf_modules/RSEM/quantification_single.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $mapping_fastq {
+ container = "rsem:1.3.0"
+ }
+ }
+ }
+ sge {
+ process{
+ $mapping_fastq {
+ beforeScript = "module purge; module load RSEM/1.3.0; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/RSEM/tests/quantification_single.nf b/src/nf_modules/RSEM/quantification_single.nf
similarity index 67%
rename from src/nf_modules/RSEM/tests/quantification_single.nf
rename to src/nf_modules/RSEM/quantification_single.nf
index 0fd26f0ce83f1c11f2eea62846fad566beac3e8c..d52b7f446049abac081b5a17f2202909f070e600 100644
--- a/src/nf_modules/RSEM/tests/quantification_single.nf
+++ b/src/nf_modules/RSEM/quantification_single.nf
@@ -1,6 +1,6 @@
params.fastq = "$baseDir/data/fastq/*.fastq"
params.index = "$baseDir/data/index/*.index*"
-params.mean = 300
+params.mean = 200
params.sd = 100
log.info "fastq files : ${params.fastq}"
@@ -11,6 +11,7 @@ log.info "sd read size: ${params.sd}"
Channel
.fromPath( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fastq_files }
Channel
.fromPath( params.index )
@@ -18,27 +19,37 @@ Channel
.set { index_files }
process mapping_fastq {
- tag "$reads.baseName"
+ tag "$file_id"
cpus 4
publishDir "results/mapping/quantification/", mode: 'copy'
input:
- file reads from fastq_files
+ set file_id, file(reads) from fastq_files
file index from index_files.toList()
output:
file "*" into count_files
script:
-index_name = (index[0].baseName =~ /(.*)\.\d/)[0][1]
+ index_id = index[0]
+ for (index_file in index) {
+ if (index_file =~ /.*\.1\.bt2/ && !(index_file =~ /.*\.rev\.1\.bt2/)) {
+ index_id = ( index_file =~ /(.*)\.1\.bt2/)[0][1]
+ }
+ }
"""
+ls -l
rsem-calculate-expression --bowtie2 \
--bowtie2-path \$(which bowtie2 | sed 's/bowtie2\$//g') \
--bowtie2-sensitivity-level "very_sensitive" \
--fragment-length-mean ${params.mean} --fragment-length-sd ${params.sd} \
--output-genome-bam -p ${task.cpus} \
-${reads} ${index_name} ${reads.baseName} \
-> ${reads.baseName}_rsem_bowtie2_report.txt
+${reads} ${index_id} ${file_id} \
+2> ${file_id}_rsem_bowtie2_report.txt
+
+if grep -q "Error" ${file_id}_rsem_bowtie2_report.txt; then
+ exit 1
+fi
"""
}
diff --git a/src/nf_modules/RSEM/rsem.nf b/src/nf_modules/RSEM/rsem.nf
deleted file mode 100644
index 54e6ad0cec2305207c274efe6b9187d53439be75..0000000000000000000000000000000000000000
--- a/src/nf_modules/RSEM/rsem.nf
+++ /dev/null
@@ -1,139 +0,0 @@
-/*
-* RSEM :
-* Imputs : fastq files
-* Imputs : fasta files
-* Output : bam files
-*/
-
-/* fasta indexing */
-params.fasta = "$baseDir/data/bam/*.fasta"
-params.annotation = "$baseDir/data/bam/*.gff3"
-
-log.info "fasta files : ${params.fasta}"
-
-Channel
- .fromPath( params.fasta )
- .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
- .set { fasta_file }
-Channel
- .fromPath( params.annotation )
- .ifEmpty { error "Cannot find any annotation files matching: ${params.annotation}" }
- .set { annotation_file }
-
-process index_fasta {
- tag "$fasta.baseName"
- cpus 4
- publishDir "results/mapping/index/", mode: 'copy'
-
- input:
- file fasta from fasta_file
- file annotation from annotation_file
-
- output:
- file "*.index*" into index_files
-
- script:
- def cmd_annotation = "--gff3 ${annotation}"
- if(annotation ==~ /.*\.gtf$/){
- cmd_annotation = "--gtf ${annotation}"
- }
-"""
-rsem-prepare-reference -p ${task.cpus} --bowtie2 \
---bowtie2-path \$(which bowtie2 | sed 's/bowtie2\$//g') \
-${cmd_annotation} ${fasta} ${fasta.baseName}.index > \
-${fasta.baseName}_rsem_bowtie2_report.txt
-"""
-}
-
-
-/*
-* for paired-end data
-*/
-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/quantification/", mode: 'copy'
-
- input:
- set pair_id, file(reads) from fastq_files
- file index from index_files.toList()
-
- output:
- file "*" into counts_files
-
- script:
-index_name = (index[0].baseName =~ /(.*)\.\d/)[0][1]
-"""
-rsem-calculate-expression --bowtie2 \
---bowtie2-path \$(which bowtie2 | sed 's/bowtie2\$//g') \
---bowtie2-sensitivity-level "very_sensitive" \
--output-genome-bam -p ${task.cpus} \
---paired-end ${reads[0]} ${reads[1]} ${index_name} ${pair_id} \
-> ${pair_id}_rsem_bowtie2_report.txt
-"""
-}
-
-
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*.fastq"
-params.index = "$baseDir/data/index/*.index*"
-params.mean = 300
-params.sd = 100
-
-log.info "fastq files : ${params.fastq}"
-log.info "index files : ${params.index}"
-log.info "mean read size: ${params.mean}"
-log.info "sd read size: ${params.sd}"
-
-Channel
- .fromPath( 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: ${params.index}" }
- .set { index_files }
-
-process mapping_fastq {
- tag "$reads.baseName"
- cpus 4
- publishDir "results/mapping/quantification/", mode: 'copy'
-
- input:
- file reads from fastq_files
- file index from index_files.toList()
-
- output:
- file "*" into count_files
-
- script:
-index_name = (index[0].baseName =~ /(.*)\.\d/)[0][1]
-"""
-rsem-calculate-expression --bowtie2 \
---bowtie2-path \$(which bowtie2 | sed 's/bowtie2\$//g') \
---bowtie2-sensitivity-level "very_sensitive" \
---fragment-length-mean ${params.mean} --fragment-length-sd ${params.sd} \
---output-genome-bam -p ${task.cpus} \
-${reads} ${index_name} ${tagname} > ${tagname}_rsem_bowtie2_report.txt
-"""
-}
-
diff --git a/src/nf_modules/RSEM/tests/tests.sh b/src/nf_modules/RSEM/tests.sh
similarity index 54%
rename from src/nf_modules/RSEM/tests/tests.sh
rename to src/nf_modules/RSEM/tests.sh
index f7fcd064b93430badd67899831561121580e4709..7d56b790607b7cc1128262f6439cb2b4d3d012ef 100755
--- a/src/nf_modules/RSEM/tests/tests.sh
+++ b/src/nf_modules/RSEM/tests.sh
@@ -1,17 +1,17 @@
-nextflow src/nf_modules/RSEM/tests/index.nf \
- -c src/nf_modules/RSEM/rsem.config \
+./nextflow src/nf_modules/RSEM/indexing.nf \
+ -c src/nf_modules/RSEM/indexing.config \
-profile docker \
--fasta "data/tiny_dataset/fasta/tiny_v2.fasta" \
--annotation "data/tiny_dataset/annot/tiny.gff"
-nextflow src/nf_modules/RSEM/tests/quantification_single.nf \
- -c src/nf_modules/RSEM/rsem.config \
+./nextflow src/nf_modules/RSEM/quantification_single.nf \
+ -c src/nf_modules/RSEM/quantification_single.config \
-profile docker \
--index "results/mapping/index/tiny_v2.index*" \
--fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
-nextflow src/nf_modules/RSEM/tests/quantification_paired.nf \
- -c src/nf_modules/RSEM/rsem.config \
+./nextflow src/nf_modules/RSEM/quantification_paired.nf \
+ -c src/nf_modules/RSEM/quantification_paired.config \
-profile docker \
--index "results/mapping/index/tiny_v2.index*" \
--fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
diff --git a/src/nf_modules/SAMtools/filter_bams.config b/src/nf_modules/SAMtools/filter_bams.config
new file mode 100644
index 0000000000000000000000000000000000000000..066684006e4a04daef5caf26e45ba74878bb4ebf
--- /dev/null
+++ b/src/nf_modules/SAMtools/filter_bams.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $filter_bam {
+ container = "samtools:1.7"
+ }
+ }
+ }
+ sge {
+ process{
+ $filter_bam {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/SAMtools/tests/filter_bams.nf b/src/nf_modules/SAMtools/filter_bams.nf
similarity index 67%
rename from src/nf_modules/SAMtools/tests/filter_bams.nf
rename to src/nf_modules/SAMtools/filter_bams.nf
index 49021362d7bc97c950042ab163a5224a2eb28d02..0812a19b227049fd05b54f46cbc30b246da73127 100644
--- a/src/nf_modules/SAMtools/tests/filter_bams.nf
+++ b/src/nf_modules/SAMtools/filter_bams.nf
@@ -7,6 +7,7 @@ log.info "bed file : ${params.bed}"
Channel
.fromPath( params.bam )
.ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { bam_files }
Channel
.fromPath( params.bed )
@@ -14,18 +15,18 @@ Channel
.set { bed_files }
process filter_bam {
- tag "$bam.baseName"
+ tag "$file_id"
cpus 4
input:
- file bam from bam_files
+ set file_id, file(bam) from bam_files
file bed from bed_files
output:
- file "*_filtered.bam*" into filtered_bam_files
+ set file_id, "*_filtered.bam*" into filtered_bam_files
script:
"""
-samtools view -@ ${task.cpus} -hb ${bam} -L ${bed} > ${bam.baseName}_filtered.bam
+samtools view -@ ${task.cpus} -hb ${bam} -L ${bed} > ${file_id}_filtered.bam
"""
}
diff --git a/src/nf_modules/SAMtools/index_bams.config b/src/nf_modules/SAMtools/index_bams.config
new file mode 100644
index 0000000000000000000000000000000000000000..3b23601d9566ee96f034d14a798c6c8e08a6870f
--- /dev/null
+++ b/src/nf_modules/SAMtools/index_bams.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $index_bam {
+ container = "samtools:1.7"
+ }
+ }
+ }
+ sge {
+ process{
+ $index_bam {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/SAMtools/tests/index_bams.nf b/src/nf_modules/SAMtools/index_bams.nf
similarity index 63%
rename from src/nf_modules/SAMtools/tests/index_bams.nf
rename to src/nf_modules/SAMtools/index_bams.nf
index bea5441c2c5946a705117c4422581c3e3eea6f02..489b0f4f71f39d1fdc5b7870547e9fd18a29f9af 100644
--- a/src/nf_modules/SAMtools/tests/index_bams.nf
+++ b/src/nf_modules/SAMtools/index_bams.nf
@@ -5,14 +5,18 @@ log.info "bams files : ${params.bam}"
Channel
.fromPath( params.bam )
.ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { bam_files }
process index_bam {
- tag "$bam.baseName"
+ tag "$file_id"
+
input:
- file bam from bam_files
+ set file_id, file(bam) from bam_files
+
output:
- file "*bam*" into indexed_bam_file
+ set file_id, "*.bam*" into indexed_bam_file
+
script:
"""
samtools index ${bam}
diff --git a/src/nf_modules/SAMtools/samtools.config b/src/nf_modules/SAMtools/samtools.config
deleted file mode 100644
index a10e3e578a16a66324e2c6989d054015af03e491..0000000000000000000000000000000000000000
--- a/src/nf_modules/SAMtools/samtools.config
+++ /dev/null
@@ -1,36 +0,0 @@
-profiles {
- docker {
- docker.temp = 'auto'
- docker.enabled = true
- process {
- $sort_bam {
- container = "samtools:1.7"
- }
- $index_bam {
- container = "samtools:1.7"
- }
- $split_bam {
- container = "samtools:1.7"
- }
- $filter_bam {
- container = "samtools:1.7"
- }
- }
- }
- sge {
- process{
- $trimming {
- beforeScript = "module purge; module load SAMtools/1.7"
- }
- $index_bam {
- beforeScript = "module purge; module load SAMtools/1.7"
- }
- $split_bam {
- beforeScript = "module purge; module load SAMtools/1.7"
- }
- $filter_bam {
- beforeScript = "module purge; module load SAMtools/1.7"
- }
- }
- }
-}
diff --git a/src/nf_modules/SAMtools/samtools.nf b/src/nf_modules/SAMtools/samtools.nf
deleted file mode 100644
index f178bb0d706a4b656bf40beca25bf4cea69e9103..0000000000000000000000000000000000000000
--- a/src/nf_modules/SAMtools/samtools.nf
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
-* SAMtools :
-* Imputs : bam files
-* Output : bam files
-*/
-
-/* bams sorting */
-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
- .fromPath( params.bam )
- .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
- .set { bam_files }
-
-process sort_bam {
- tag "$bam.baseName"
- cpus 4
-
- input:
- file bam from bam_files
-
- output:
- file "*_sorted.bam" into sorted_bam_files
-
- script:
-"""
-samtools sort -@ ${task.cpus} -O BAM -o ${bam.baseName}_sorted.bam ${bam}
-"""
-}
-
-/* bams indexing */
-
-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
- .fromPath( params.bam )
- .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
- .set { bam_files }
-
-process index_bam {
- tag "$bam.baseName"
- input:
- file bam from bam_files
- output:
- file "*bam*" into indexed_bam_file
- script:
-"""
-samtools index ${bam}
-"""
-}
-
-
-/* bams spliting */
-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
- .fromPath( params.bam )
- .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
- .set { bam_files }
-
-process split_bam {
- tag "$bam.baseName"
- cpus 2
-
- input:
- file bam from bam_files
-
- output:
- file "*_forward.bam*" into forward_bam_files
- file "*_reverse.bam*" into reverse_bam_files
- script:
-"""
-samtools view -hb -F 0x10 ${bam} > ${bam}_forward.bam &
-samtools view -hb -f 0x10 ${bam} > ${bam}_reverse.bam
-"""
-}
-
-
-/* bams filtering */
-params.bam = "$baseDir/data/bam/*.bam"
-params.bed = "$baseDir/data/bam/*.bed"
-
-log.info "bams files : ${params.bam}"
-log.info "bed file : ${params.bed}"
-
-Channel
- .fromPath( params.bam )
- .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
- .set { bam_files }
-Channel
- .fromPath( params.bed )
- .ifEmpty { error "Cannot find any bed file matching: ${params.bed}" }
- .set { bed_files }
-
-process filter_bam {
- tag "$bam.baseName"
- cpus 4
-
- input:
- file bam from bam_files
- file bed from bed_files
-
- output:
- file "*_filtered.bam*" into filtered_bam_files
- script:
-"""
-samtools view -@ ${task.cpus} -hb ${bam} -L ${bed} > ${bam.baseName}_filtered.bam
-"""
-}
-
-
diff --git a/src/nf_modules/SAMtools/sort_bams.config b/src/nf_modules/SAMtools/sort_bams.config
new file mode 100644
index 0000000000000000000000000000000000000000..d1a8c503ace81d53fa5ff9cd382a435ac710e0cf
--- /dev/null
+++ b/src/nf_modules/SAMtools/sort_bams.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $sort_bam {
+ container = "samtools:1.7"
+ }
+ }
+ }
+ sge {
+ process{
+ $sort_bam {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/SAMtools/tests/sort_bams.nf b/src/nf_modules/SAMtools/sort_bams.nf
similarity index 53%
rename from src/nf_modules/SAMtools/tests/sort_bams.nf
rename to src/nf_modules/SAMtools/sort_bams.nf
index 79a7590519616f3949aeadb651228666c172d0df..ab5c7e5140989b83eebd25f7b4dbb206520416b6 100644
--- a/src/nf_modules/SAMtools/tests/sort_bams.nf
+++ b/src/nf_modules/SAMtools/sort_bams.nf
@@ -5,21 +5,22 @@ log.info "bams files : ${params.bam}"
Channel
.fromPath( params.bam )
.ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { bam_files }
process sort_bam {
- tag "$bams.baseName"
+ tag "$file_id"
cpus 4
input:
- file bam from bam_files
+ set file_id, file(bam) from bam_files
output:
- file "*_sorted.bam" into sorted_bam_files
+ set file_id, "*_sorted.bam" into sorted_bam_files
script:
"""
-samtools sort -@ ${task.cpus} -O BAM -o ${bam.baseName}_sorted.bam ${bam}
+samtools sort -@ ${task.cpus} -O BAM -o ${file_id}_sorted.bam ${bam}
"""
}
diff --git a/src/nf_modules/SAMtools/split_bams.config b/src/nf_modules/SAMtools/split_bams.config
new file mode 100644
index 0000000000000000000000000000000000000000..28b548efd5177e7457bd642b0c78198f2b48acd9
--- /dev/null
+++ b/src/nf_modules/SAMtools/split_bams.config
@@ -0,0 +1,18 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $split_bam {
+ container = "samtools:1.7"
+ }
+ }
+ }
+ sge {
+ process{
+ $split_bam {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/SAMtools/split_bams.nf b/src/nf_modules/SAMtools/split_bams.nf
new file mode 100644
index 0000000000000000000000000000000000000000..f8ba6a50c7d7aecfb7c9c7b0fff8d4436cf055a4
--- /dev/null
+++ b/src/nf_modules/SAMtools/split_bams.nf
@@ -0,0 +1,27 @@
+params.bam = "$baseDir/data/bam/*.bam"
+
+log.info "bams files : ${params.bam}"
+
+Channel
+ .fromPath( params.bam )
+ .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
+ .set { bam_files }
+
+process split_bam {
+ tag "$file_id"
+ cpus 2
+
+ input:
+ set file_id, file(bam) from bam_files
+
+ output:
+ set file_id, "*_forward.bam*" into forward_bam_files
+ set file_id, "*_reverse.bam*" into reverse_bam_files
+ script:
+"""
+samtools view -hb -F 0x10 ${bam} > ${file_id}_forward.bam &
+samtools view -hb -f 0x10 ${bam} > ${file_id}_reverse.bam
+"""
+}
+
diff --git a/src/nf_modules/SAMtools/tests.sh b/src/nf_modules/SAMtools/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..9b7ac5e47388ea99ecf137ddd6add0b2ad313149
--- /dev/null
+++ b/src/nf_modules/SAMtools/tests.sh
@@ -0,0 +1,20 @@
+./nextflow src/nf_modules/SAMtools/sort_bams.nf \
+ -c src/nf_modules/SAMtools/sort_bams.config \
+ -profile docker \
+ --bam "data/tiny_dataset/map/tiny_v2.bam"
+
+./nextflow src/nf_modules/SAMtools/index_bams.nf \
+ -c src/nf_modules/SAMtools/index_bams.config \
+ -profile docker \
+ --bam "data/tiny_dataset/map/tiny_v2.sort.bam"
+
+./nextflow src/nf_modules/SAMtools/split_bams.nf \
+ -c src/nf_modules/SAMtools/split_bams.config \
+ -profile docker \
+ --bam "data/tiny_dataset/map/tiny_v2.bam"
+
+./nextflow src/nf_modules/SAMtools/filter_bams.nf \
+ -c src/nf_modules/SAMtools/filter_bams.config \
+ -profile docker \
+ --bam "data/tiny_dataset/map/tiny_v2.bam" \
+ --bed "data/tiny_dataset/OLD/2genes.bed"
diff --git a/src/nf_modules/SAMtools/tests/split_bams.nf b/src/nf_modules/SAMtools/tests/split_bams.nf
deleted file mode 100644
index edc20864de3c81dd4fc371d4455a62b53ed8a8f9..0000000000000000000000000000000000000000
--- a/src/nf_modules/SAMtools/tests/split_bams.nf
+++ /dev/null
@@ -1,26 +0,0 @@
-params.bam = "$baseDir/data/bam/*.bam"
-
-log.info "bams files : ${params.bam}"
-
-Channel
- .fromPath( params.bam )
- .ifEmpty { error "Cannot find any bam files matching: ${params.bam}" }
- .set { bam_files }
-
-process split_bam {
- tag "$bam.baseName"
- cpus 2
-
- input:
- file bam from bam_files
-
- output:
- file "*_forward.bam*" into forward_bam_files
- file "*_reverse.bam*" into reverse_bam_files
- script:
-"""
-samtools view -hb -F 0x10 ${bam} > ${bam}_forward.bam &
-samtools view -hb -f 0x10 ${bam} > ${bam}_reverse.bam
-"""
-}
-
diff --git a/src/nf_modules/SAMtools/tests/tests.sh b/src/nf_modules/SAMtools/tests/tests.sh
deleted file mode 100755
index e3e809982cdf68959603f5496e49f02f2493afd6..0000000000000000000000000000000000000000
--- a/src/nf_modules/SAMtools/tests/tests.sh
+++ /dev/null
@@ -1,20 +0,0 @@
-nextflow src/nf_modules/SAMtools/tests/sort_bams.nf \
- -c src/nf_modules/SAMtools/samtools.config \
- -profile docker \
- --bam "data/tiny_dataset/map/tiny_v2.bam"
-
-nextflow src/nf_modules/SAMtools/tests/index_bams.nf \
- -c src/nf_modules/SAMtools/samtools.config \
- -profile docker \
- --bam "data/tiny_dataset/map/tiny_v2.sort.bam"
-
-nextflow src/nf_modules/SAMtools/tests/split_bams.nf \
- -c src/nf_modules/SAMtools/samtools.config \
- -profile docker \
- --bam "data/tiny_dataset/map/tiny_v2.bam"
-
-nextflow src/nf_modules/SAMtools/tests/filter_bams.nf \
- -c src/nf_modules/SAMtools/samtools.config \
- -profile docker \
- --bam "data/tiny_dataset/map/tiny_v2.bam" \
- --bed "data/tiny_dataset/OLD/2genes.bed"
diff --git a/src/nf_modules/SRAtoolkit/fastqdump.config b/src/nf_modules/SRAtoolkit/fastqdump.config
new file mode 100644
index 0000000000000000000000000000000000000000..128a4fef272aeb70993f5b614e0c34f901fc0c60
--- /dev/null
+++ b/src/nf_modules/SRAtoolkit/fastqdump.config
@@ -0,0 +1,25 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $fastq_dump {
+ container = "sratoolkit:2.8.2"
+ }
+ }
+ }
+ sge {
+ process{
+ $fastq_dump {
+ beforeScript = "module purge; module load SRAtoolkit/2.8.2"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'monointeldeb128'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/SRAtoolkit/fastqdump.nf b/src/nf_modules/SRAtoolkit/fastqdump.nf
new file mode 100644
index 0000000000000000000000000000000000000000..3dde59641dfa837398abb1e169704d42a57b9fff
--- /dev/null
+++ b/src/nf_modules/SRAtoolkit/fastqdump.nf
@@ -0,0 +1,47 @@
+/*
+* sra-tools :
+
+*/
+
+/* fastq-dump
+* Imputs : srr list
+* Outputs : fastq files
+*/
+
+params.list_srr = "$baseDir/data/SRR/*.txt"
+
+log.info "downloading list srr : ${params.list_srr}"
+
+Channel
+ .fromPath( params.list_srr )
+ .ifEmpty { error "Cannot find any bam files matching: ${params.list_srr}" }
+ .splitCsv()
+ .map { it -> it[0]}
+ .set { SRR }
+
+//run is the column name containing SRR ids
+
+process fastq_dump {
+ tag "$file_id"
+ publishDir "results/download/fastq/${file_id}/", mode: 'copy'
+
+ input:
+ val file_id from SRR
+
+ output:
+ set file_id, "*.fastq" into fastq
+
+ script:
+"""
+#for test only 10000 reads are downloading with the option -N 10000 -X 20000
+fastq-dump --split-files --defline-seq '@\$ac_\$si/\$ri' --defline-qual "+" -N 10000 -X 20000 ${file_id}
+if [ -f ${file_id}_1.fastq ]
+then
+ mv ${file_id}_1.fastq ${file_id}_R1.fastq
+fi
+if [ -f ${file_id}_2.fastq ]
+then
+ mv ${file_id}_2.fastq ${file_id}_R2.fastq
+fi
+"""
+}
diff --git a/src/nf_modules/SRAtoolkit/list-srr.txt b/src/nf_modules/SRAtoolkit/list-srr.txt
new file mode 100644
index 0000000000000000000000000000000000000000..a58fc103ffe37a56f511aee117b26383b1e3f516
--- /dev/null
+++ b/src/nf_modules/SRAtoolkit/list-srr.txt
@@ -0,0 +1,6 @@
+ERR572281
+ERR572146
+ERR572201
+ERR638114
+ERR638115
+ERR638116
diff --git a/src/nf_modules/SRAtoolkit/tests.sh b/src/nf_modules/SRAtoolkit/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..d8575eb43181382f580699f5afd73f0ed69b9a2c
--- /dev/null
+++ b/src/nf_modules/SRAtoolkit/tests.sh
@@ -0,0 +1,4 @@
+./nextflow src/nf_modules/SRAtoolkit/fastqdump.nf \
+ -c src/nf_modules/SRAtoolkit/fastqdump.config \
+ -profile docker \
+ --list_srr "src/nf_modules/SRAtoolkit/list-srr.txt"
diff --git a/src/nf_modules/UrQt/tests.sh b/src/nf_modules/UrQt/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..96f5845311afe29a8d5043bf7556b3d4331b045b
--- /dev/null
+++ b/src/nf_modules/UrQt/tests.sh
@@ -0,0 +1,9 @@
+./nextflow src/nf_modules/UrQt/trimming_paired.nf \
+ -c src/nf_modules/UrQt/trimming_paired.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
+
+./nextflow src/nf_modules/UrQt/trimming_single.nf \
+ -c src/nf_modules/UrQt/trimming_single.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
diff --git a/src/nf_modules/UrQt/tests/tests.sh b/src/nf_modules/UrQt/tests/tests.sh
deleted file mode 100755
index ebad73150b861322459f118dd63c2e2fd81af1f3..0000000000000000000000000000000000000000
--- a/src/nf_modules/UrQt/tests/tests.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-nextflow src/nf_modules/UrQt/tests/trimming_paired.nf \
- -c src/nf_modules/UrQt/urqt.config \
- -profile docker \
- --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/UrQt/tests/trimming_single.nf \
- -c src/nf_modules/UrQt/urqt.config \
- -profile docker \
- --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
diff --git a/src/nf_modules/UrQt/trimming_paired.config b/src/nf_modules/UrQt/trimming_paired.config
new file mode 100644
index 0000000000000000000000000000000000000000..46a86729f1367966225fcb37c5ef7f11070c7255
--- /dev/null
+++ b/src/nf_modules/UrQt/trimming_paired.config
@@ -0,0 +1,26 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $trimming {
+ container = "urqt:d62c1f8"
+ }
+ }
+ }
+ sge {
+ process{
+ $trimming {
+ beforeScript = "module purge; module load UrQt/d62c1f8"
+ executor = "sge"
+ cpus = 4
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/UrQt/tests/trimming_paired.nf b/src/nf_modules/UrQt/trimming_paired.nf
similarity index 100%
rename from src/nf_modules/UrQt/tests/trimming_paired.nf
rename to src/nf_modules/UrQt/trimming_paired.nf
diff --git a/src/nf_modules/UrQt/trimming_single.config b/src/nf_modules/UrQt/trimming_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..46a86729f1367966225fcb37c5ef7f11070c7255
--- /dev/null
+++ b/src/nf_modules/UrQt/trimming_single.config
@@ -0,0 +1,26 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $trimming {
+ container = "urqt:d62c1f8"
+ }
+ }
+ }
+ sge {
+ process{
+ $trimming {
+ beforeScript = "module purge; module load UrQt/d62c1f8"
+ executor = "sge"
+ cpus = 4
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/UrQt/tests/trimming_single.nf b/src/nf_modules/UrQt/trimming_single.nf
similarity index 59%
rename from src/nf_modules/UrQt/tests/trimming_single.nf
rename to src/nf_modules/UrQt/trimming_single.nf
index 3160f3b6c4cf075a78ec6e7155f2c18559660ad3..5eb1e84c57b26417e6794af8bbbe03dc5377c7c7 100644
--- a/src/nf_modules/UrQt/tests/trimming_single.nf
+++ b/src/nf_modules/UrQt/trimming_single.nf
@@ -5,24 +5,25 @@ log.info "fastq files : ${params.fastq}"
Channel
.fromPath( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fastq_files }
process trimming {
- tag "$reads.baseName"
+ tag "$file_id"
cpus 4
input:
- file reads from fastq_files
+ set file_id, file(reads) from fastq_files
output:
- file "*_trim.fastq.gz" into fastq_files_trim
+ set file_id, "*_trim.fastq.gz" into fastq_files_trim
script:
"""
UrQt --t 20 --m ${task.cpus} --gz \
--in ${reads} \
- --out ${reads.baseName}_trim.fastq.gz \
- > ${reads.baseName}_trimming_report.txt
+ --out ${file_id}_trim.fastq.gz \
+ > ${file_id}_trimming_report.txt
"""
}
diff --git a/src/nf_modules/UrQt/urqt.nf b/src/nf_modules/UrQt/urqt.nf
deleted file mode 100644
index d24033632011796fb1bb3d27185cf62a737444a9..0000000000000000000000000000000000000000
--- a/src/nf_modules/UrQt/urqt.nf
+++ /dev/null
@@ -1,74 +0,0 @@
-/*
-* urqt :
-* Imputs : fastq files
-* Output : fastq files
-*/
-/* quality trimming */
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
- .fromFilePairs( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
-process trimming {
- tag "${reads}"
- cpus 4
- publishDir "results/fastq/trimming/", mode: 'copy'
-
- input:
- set pair_id, file(reads) from fastq_files
-
- output:
- set pair_id, "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
-
- script:
-"""
-UrQt --t 20 --m ${task.cpus} --gz \
---in ${reads[0]} --inpair ${reads[1]} \
---out ${pair_id}_trim_R1.fastq.gz --outpair ${pair_id}_trim_R2.fastq.gz \
-> ${pair_id}_trimming_report.txt
-"""
-}
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
- .fromPath( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
-process trimming {
- tag "$reads.baseName"
- cpus 4
- publishDir "results/fastq/trimming/", mode: 'copy'
-
- input:
- file reads from fastq_files
-
- output:
- file "*_trim.fastq.gz" into fastq_files_trim
-
- script:
-"""
-
-UrQt --t 20 --m ${task.cpus} --gz \
---in ${reads} \
---out ${reads.baseName}_trim.fastq.gz \
-> ${reads.baseName}_trimming_report.txt
-"""
-}
-
diff --git a/src/nf_modules/cutadapt/cutadapt.config b/src/nf_modules/cutadapt/adaptor_removal_paired.config
similarity index 50%
rename from src/nf_modules/cutadapt/cutadapt.config
rename to src/nf_modules/cutadapt/adaptor_removal_paired.config
index 07efa9be0c8808c0cf730fb5d0dcb7ae8d351b3f..aa1a372b694db02c9d290a0dccf3c67e14f1c5f7 100644
--- a/src/nf_modules/cutadapt/cutadapt.config
+++ b/src/nf_modules/cutadapt/adaptor_removal_paired.config
@@ -24,30 +24,3 @@ profiles {
}
}
}
-
-profiles {
- docker {
- docker.temp = 'auto'
- docker.enabled = true
- process {
- $trimming {
- container = "cutadapt:1.14"
- }
- }
- }
- sge {
- process{
- $trimming {
- beforeScript = "module purge; module load cutadapt/1.14"
- executor = "sge"
- cpus = 1
- memory = "5GB"
- time = "6h"
- queueSize = 1000
- pollInterval = '60sec'
- queue = 'h6-E5-2667v4deb128'
- penv = 'openmp8'
- }
- }
- }
-}
diff --git a/src/nf_modules/cutadapt/tests/adaptor_removal_paired.nf b/src/nf_modules/cutadapt/adaptor_removal_paired.nf
similarity index 100%
rename from src/nf_modules/cutadapt/tests/adaptor_removal_paired.nf
rename to src/nf_modules/cutadapt/adaptor_removal_paired.nf
diff --git a/src/nf_modules/cutadapt/adaptor_removal_single.config b/src/nf_modules/cutadapt/adaptor_removal_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..aa1a372b694db02c9d290a0dccf3c67e14f1c5f7
--- /dev/null
+++ b/src/nf_modules/cutadapt/adaptor_removal_single.config
@@ -0,0 +1,26 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $adaptor_removal {
+ container = "cutadapt:1.14"
+ }
+ }
+ }
+ sge {
+ process{
+ $adaptor_removal {
+ beforeScript = "module purge; module load cutadapt/1.14"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/cutadapt/tests/adaptor_removal_single.nf b/src/nf_modules/cutadapt/adaptor_removal_single.nf
similarity index 55%
rename from src/nf_modules/cutadapt/tests/adaptor_removal_single.nf
rename to src/nf_modules/cutadapt/adaptor_removal_single.nf
index dc889a0e26d12e90f4913ee2043f60e6f930df4d..26f3cd7602bf242f718a027bad253ba2fe1e8d8c 100644
--- a/src/nf_modules/cutadapt/tests/adaptor_removal_single.nf
+++ b/src/nf_modules/cutadapt/adaptor_removal_single.nf
@@ -3,22 +3,23 @@ log.info "fastq files : ${params.fastq}"
Channel
.fromPath( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fastq_files }
process adaptor_removal {
- tag "$reads.baseName"
+ tag "$file_id"
input:
- file reads from fastq_files
+ set file_id, file(reads) from fastq_files
output:
- file "*_cut.fastq.gz" into fastq_files_cut
+ set file_id, "*_cut.fastq.gz" into fastq_files_cut
script:
"""
cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT\
- -o ${reads.baseName}_cut.fastq.gz \
- ${reads} > ${reads.baseName}_report.txt
+ -o ${file_id}_cut.fastq.gz \
+ ${reads} > ${file_id}_report.txt
"""
}
diff --git a/src/nf_modules/cutadapt/cutadapt.nf b/src/nf_modules/cutadapt/cutadapt.nf
deleted file mode 100644
index 204a9e5a5e34ecef5b47e1892bc0ac9e0f6a1760..0000000000000000000000000000000000000000
--- a/src/nf_modules/cutadapt/cutadapt.nf
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
-* cutadapt :
-* Imputs : fastq files
-* Output : fastq files
-*/
-
-/* Illumina adaptor removal */
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
- .fromFilePairs( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
-process adaptor_removal {
- tag "$pair_id"
- publishDir "results/fastq/adaptor_removal/", mode: 'copy'
-
- input:
- set pair_id, file(reads) from fastq_files
-
- output:
- set pair_id, "*_cut_R{1,2}.fastq.gz" into fastq_files_cut
-
- script:
- """
- cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT -A AGATCGGAAGAG -G CTCTTCCGATCT \
- -o ${pair_id}_cut_R1.fastq.gz -p ${pair_id}_cut_R2.fastq.gz \
- ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
- """
-}
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
- .fromPath( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
-process adaptor_removal {
- tag "$reads.baseName"
- publishDir "results/fastq/adaptor_removal/", mode: 'copy'
-
- input:
- file reads from fastq_files
-
- output:
- file "*_cut.fastq.gz" into fastq_files_cut
-
- script:
- """
- cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT\
- -o ${reads.baseName}_cut.fastq.gz \
- ${reads} > ${reads.baseName}_report.txt
- """
-}
-
-/* quality trimming */
-
-/*
-* for paired-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
- .fromFilePairs( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
-process trimming {
- tag "$pair_id"
- publishDir "results/fastq/trimming/", mode: 'copy'
-
- input:
- set pair_id, file(reads) from fastq_files
-
- output:
- set pair_id, "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
-
- script:
- """
- cutadapt -q 20,20 \
- -o ${pair_id}_trim_R1.fastq.gz -p ${pair_id}_trim_R2.fastq.gz \
- ${reads[0]} ${reads[1]} > ${pair_id}_report.txt
- """
-}
-
-/*
-* for single-end data
-*/
-
-params.fastq = "$baseDir/data/fastq/*.fastq"
-
-log.info "fastq files : ${params.fastq}"
-
-Channel
- .fromPath( params.fastq )
- .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
- .set { fastq_files }
-
-process trimming {
- tag "$reads.baseName"
- publishDir "results/fastq/trimming/", mode: 'copy'
-
- input:
- file reads from fastq_files
-
- output:
- file "*_trim.fastq.gz" into fastq_files_trim
-
- script:
- """
- cutadapt -q 20,20 \
- -o ${reads.baseName}_trim.fastq.gz \
- ${reads} > ${reads.baseName}_report.txt
- """
-}
-
diff --git a/src/nf_modules/cutadapt/tests.sh b/src/nf_modules/cutadapt/tests.sh
new file mode 100755
index 0000000000000000000000000000000000000000..75089624c4c790df6f4153b2b52048dbfd2d61ad
--- /dev/null
+++ b/src/nf_modules/cutadapt/tests.sh
@@ -0,0 +1,19 @@
+./nextflow src/nf_modules/cutadapt/adaptor_removal_paired.nf \
+ -c src/nf_modules/cutadapt/adaptor_removal_paired.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
+
+./nextflow src/nf_modules/cutadapt/adaptor_removal_single.nf \
+ -c src/nf_modules/cutadapt/adaptor_removal_single.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
+
+./nextflow src/nf_modules/cutadapt/trimming_paired.nf \
+ -c src/nf_modules/cutadapt/trimming_paired.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
+
+./nextflow src/nf_modules/cutadapt/trimming_single.nf \
+ -c src/nf_modules/cutadapt/trimming_single.config \
+ -profile docker \
+ --fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
diff --git a/src/nf_modules/cutadapt/tests/tests.sh b/src/nf_modules/cutadapt/tests/tests.sh
deleted file mode 100755
index a684410cf8234c3b5172679ea9de8198decf02e8..0000000000000000000000000000000000000000
--- a/src/nf_modules/cutadapt/tests/tests.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-nextflow src/nf_modules/cutadapt/tests/adaptor_removal_paired.nf \
- -c src/nf_modules/cutadapt/cutadapt.config \
- -profile docker \
- --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/cutadapt/tests/adaptor_removal_single.nf \
- -c src/nf_modules/cutadapt/cutadapt.config \
- -profile docker \
- --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/cutadapt/tests/trimming_paired.nf \
- -c src/nf_modules/cutadapt/cutadapt.config \
- -profile docker \
- --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/cutadapt/tests/trimming_single.nf \
- -c src/nf_modules/cutadapt/cutadapt.config \
- -profile docker \
- --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
diff --git a/src/nf_modules/cutadapt/trimming_paired.config b/src/nf_modules/cutadapt/trimming_paired.config
new file mode 100644
index 0000000000000000000000000000000000000000..be03e9d728f08bf863f6909e4673f3c0bef810be
--- /dev/null
+++ b/src/nf_modules/cutadapt/trimming_paired.config
@@ -0,0 +1,26 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $trimming {
+ container = "cutadapt:1.14"
+ }
+ }
+ }
+ sge {
+ process{
+ $trimming {
+ beforeScript = "module purge; module load cutadapt/1.14"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/cutadapt/tests/trimming_paired.nf b/src/nf_modules/cutadapt/trimming_paired.nf
similarity index 100%
rename from src/nf_modules/cutadapt/tests/trimming_paired.nf
rename to src/nf_modules/cutadapt/trimming_paired.nf
diff --git a/src/nf_modules/cutadapt/trimming_single.config b/src/nf_modules/cutadapt/trimming_single.config
new file mode 100644
index 0000000000000000000000000000000000000000..be03e9d728f08bf863f6909e4673f3c0bef810be
--- /dev/null
+++ b/src/nf_modules/cutadapt/trimming_single.config
@@ -0,0 +1,26 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $trimming {
+ container = "cutadapt:1.14"
+ }
+ }
+ }
+ sge {
+ process{
+ $trimming {
+ beforeScript = "module purge; module load cutadapt/1.14"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/cutadapt/tests/trimming_single.nf b/src/nf_modules/cutadapt/trimming_single.nf
similarity index 52%
rename from src/nf_modules/cutadapt/tests/trimming_single.nf
rename to src/nf_modules/cutadapt/trimming_single.nf
index c2dd2627da7d3b989b556c479ca86a43897e4898..9b3764dbed4dd51bfb361b56b4f5fc737b18c270 100644
--- a/src/nf_modules/cutadapt/tests/trimming_single.nf
+++ b/src/nf_modules/cutadapt/trimming_single.nf
@@ -3,22 +3,23 @@ log.info "fastq files : ${params.fastq}"
Channel
.fromPath( params.fastq )
.ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
.set { fastq_files }
process trimming {
- tag "$reads.baseName"
+ tag "$file_id"
input:
- file reads from fastq_files
+ set file_id, file(reads) from fastq_files
output:
- file "*_trim.fastq.gz" into fastq_files_cut
+ set file_id, "*_trim.fastq.gz" into fastq_files_cut
script:
"""
cutadapt -q 20,20 \
- -o ${reads.baseName}_trim.fastq.gz \
- ${reads} > ${reads.baseName}_report.txt
+ -o ${file_id}_trim.fastq.gz \
+ ${reads} > ${file_id}_report.txt
"""
}
diff --git a/src/sge_modules b/src/sge_modules
index 03a80f96cfe966f0ac855f0ac12a0b39b9ca2064..1d6cfb91449b187b05a3a78df9a06ff3baaf5558 160000
--- a/src/sge_modules
+++ b/src/sge_modules
@@ -1 +1 @@
-Subproject commit 03a80f96cfe966f0ac855f0ac12a0b39b9ca2064
+Subproject commit 1d6cfb91449b187b05a3a78df9a06ff3baaf5558
diff --git a/src/training_dataset.config b/src/training_dataset.config
new file mode 100644
index 0000000000000000000000000000000000000000..00a471c6c4a356b9fd843e7185b6c440ea37bfcb
--- /dev/null
+++ b/src/training_dataset.config
@@ -0,0 +1,94 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $build_synthetic_bed {
+ container = "bedtools:2.25.0"
+ }
+ $fasta_from_bed {
+ container = "bedtools:2.25.0"
+ }
+ $index_fasta {
+ container = "bowtie2:2.3.4.1"
+ }
+ $mapping_fastq_paired {
+ container = "bowtie2:2.3.4.1"
+ }
+ $bam_2_fastq_paired {
+ container = "samtools:1.7"
+ }
+ $sort_bam_paired {
+ container = "samtools:1.7"
+ }
+ $index_bam_paired {
+ container = "samtools:1.7"
+ }
+ $mapping_fastq_single {
+ container = "bowtie2:2.3.4.1"
+ }
+ $bam_2_fastq_single {
+ container = "samtools:1.7"
+ }
+ $sort_bam_single {
+ container = "samtools:1.7"
+ }
+ $index_bam_single {
+ container = "samtools:1.7"
+ }
+ }
+ }
+ sge {
+ process{
+ $build_synthetic_bed {
+ beforeScript = "module purge; module load BEDtools/2.25.0"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ $fasta_from_bed {
+ beforeScript = "module purge; module load BEDtools/2.25.0"
+ executor = "sge"
+ cpus = 1
+ memory = "5GB"
+ time = "6h"
+ queueSize = 1000
+ pollInterval = '60sec'
+ queue = 'h6-E5-2667v4deb128'
+ penv = 'openmp8'
+ }
+ $index_fasta {
+ beforeScript = "module purge; module load Bowtie2/2.3.4.1"
+ }
+ $mapping_fastq_paired {
+ beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie2/2.3.4.1"
+ }
+ $bam_2_fastq_paired {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ $sort_bam_paired {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ $index_bam_paired {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ $mapping_fastq_single {
+ beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie2/2.3.4.1"
+ }
+ $bam_2_fastq_single {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ $sort_bam_single {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ $index_bam_single {
+ beforeScript = "module purge; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/training_dataset.nf b/src/training_dataset.nf
new file mode 100644
index 0000000000000000000000000000000000000000..c6f48e882a82eaa7437a409c7500c7045224893e
--- /dev/null
+++ b/src/training_dataset.nf
@@ -0,0 +1,308 @@
+/*
+small pipeline to build a training dataset from whole genome data
+
+input:
+- fasta
+- fastq
+- chromosome
+- start position
+- stop position
+
+output:
+- sort fasta
+- sort fastq
+
+example for paired-end data:
+./nextflow src/training_dataset.nf -c src/training_dataset.config --fasta "data/genome.fa" --fastq_paired "data/*_R{1,2}.fastq.gz" --chromosome "X" --start 5305683 --stop 5333928 -resume
+
+example for single-end data:
+./nextflow src/training_dataset.nf -c src/training_dataset.config --fasta "data/genome.fa" --fastq_single "data/*_R1.fastq.gz" --chromosome "X" --start 5305683 --stop 5333928 -resume
+
+*/
+
+params.fastq_paired = ""
+params.fastq_single = ""
+
+log.info "fasta files : ${params.fasta}"
+log.info "fastq paired files : ${params.fastq_paired}"
+log.info "fastq single files : ${params.fastq_single}"
+log.info "chromosome : ${params.chromosome}"
+log.info "start position : ${params.start}"
+log.info "stop position : ${params.stop}"
+
+
+Channel
+ .fromPath( params.fasta )
+ .ifEmpty { error "Cannot find any index files matching: ${params.fasta}" }
+ .set { fasta_file }
+
+
+process build_synthetic_bed {
+ tag "${chromosome}:${start}-${stop}"
+ cpus 4
+
+ input:
+ val chromosome from params.chromosome
+ val start from params.start
+ val stop from params.stop
+
+ output:
+ file "*.bed" into bed_files
+
+ script:
+"""
+echo "${chromosome}\t${start}\t${stop}" > synthetic.bed
+"""
+}
+
+process fasta_from_bed {
+ tag "${fasta.baseName}"
+ cpus 4
+ publishDir "results/training/fasta/", mode: 'copy'
+
+ input:
+ file fasta from fasta_file
+ file bed from bed_files
+ val chromosome from params.chromosome
+
+ output:
+ file "*.fasta" into fasta_files_extracted
+
+ script:
+"""
+bedtools getfasta \
+-fi ${fasta} -bed ${bed} -fo s${fasta.baseName}.fasta
+"""
+}
+
+process index_fasta {
+ tag "$fasta.baseName"
+ cpus 4
+ publishDir "results/training/mapping/index/", mode: 'copy'
+
+ input:
+ file fasta from fasta_files_extracted
+
+ output:
+ file "*.index*" into index_files
+ file "*_report.txt" into indexing_report
+
+ script:
+"""
+bowtie2-build --threads ${task.cpus} ${fasta} ${fasta.baseName}.index &> ${fasta.baseName}_bowtie2_report.txt
+
+if grep -q "Error" ${fasta.baseName}_bowtie2_report.txt; then
+ exit 1
+fi
+"""
+}
+
+if ( params.fastq_paired != "" ) {
+ Channel
+ .fromFilePairs( params.fastq_paired )
+ .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq_paired}" }
+ .set { fastq_files_paired }
+
+ process mapping_fastq_paired {
+ tag "$pair_id"
+ cpus 4
+
+ input:
+ set pair_id, file(reads) from fastq_files_paired
+ file index from index_files.collect()
+
+ output:
+ set pair_id, "*.bam" into bam_files_paired
+ file "*_report.txt" into mapping_report
+
+ script:
+ index_id = index[0]
+ for (index_file in index) {
+ if (index_file =~ /.*\.1\.bt2/ && !(index_file =~ /.*\.rev\.1\.bt2/)) {
+ index_id = ( index_file =~ /(.*)\.1\.bt2/)[0][1]
+ }
+ }
+ """
+ bowtie2 --very-sensitive -p ${task.cpus} -x ${index_id} \
+ -1 ${reads[0]} -2 ${reads[1]} 2> \
+ ${pair_id}_bowtie2_report.txt | \
+ samtools view -Sb - > ${pair_id}.bam
+
+ if grep -q "Error" ${pair_id}_bowtie2_report.txt; then
+ exit 1
+ fi
+ """
+ }
+
+ bam_files_paired.into{ bam_files_paired_fa; bam_files_paired_ba}
+
+ process bam_2_fastq_paired {
+ tag "$file_id"
+ publishDir "results/training/fastq/", mode: 'copy'
+
+ input:
+ set file_id, file(bam) from bam_files_paired_fa
+
+ output:
+ set file_id, "*.fastq" into fastq_files_extracted
+ script:
+ """
+ samtools fastq -1 s${file_id}_R1.fastq -2 s${file_id}_R2.fastq -F 0x4 ${bam}
+ """
+ }
+
+ process filter_bam_paired {
+ tag "$file_id"
+ cpus 4
+
+ input:
+ set file_id, file(bam) from bam_files_paired_ba
+ file bed from bed_files
+
+ output:
+ set file_id, "*.bam" into filtered_bam_files_paired
+ script:
+ """
+ samtools view -@ ${task.cpus} -hb ${bam} -F 0x4 > f${file_id}.bam
+ """
+ }
+
+ process sort_bam_paired {
+ tag "$file_id"
+ publishDir "results/training/bams/", mode: 'copy'
+ cpus 4
+
+ input:
+ set file_id, file(bam) from filtered_bam_files_paired
+
+ output:
+ set file_id, "*.bam" into sorted_bam_files_paired
+
+ script:
+ """
+ samtools sort -@ ${task.cpus} -O BAM -o s${file_id}.bam ${bam}
+ """
+ }
+
+ process index_bam_paired {
+ tag "$file_id"
+ publishDir "results/training/bams/", mode: 'copy'
+
+ input:
+ set file_id, file(bam) from sorted_bam_files_paired
+
+ output:
+ set file_id, "*.bam*" into indexed_bam_file_paired
+
+ script:
+ """
+ samtools index ${bam}
+ """
+ }
+}
+
+
+if ( params.fastq_single != "" ) {
+ Channel
+ .fromPath( params.fastq_single )
+ .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq_single}" }
+ .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
+ .set { fastq_files_single }
+
+ process mapping_fastq_single {
+ tag "$file_id"
+ cpus 4
+
+ input:
+ set file_id, file(reads) from fastq_files_single
+ file index from index_files.collect()
+
+ output:
+ set file_id, "*.bam" into bam_files_single
+ file "*_report.txt" into mapping_report
+
+ script:
+ index_id = index[0]
+ for (index_file in index) {
+ if (index_file =~ /.*\.1\.bt2/ && !(index_file =~ /.*\.rev\.1\.bt2/)) {
+ index_id = ( index_file =~ /(.*)\.1\.bt2/)[0][1]
+ }
+ }
+ """
+ bowtie2 --very-sensitive -p ${task.cpus} -x ${index_id} \
+ -U ${reads} 2> \
+ ${file_id}_bowtie2_report.txt | \
+ samtools view -Sb - > ${file_id}.bam
+
+ if grep -q "Error" ${file_id}_bowtie2_report.txt; then
+ exit 1
+ fi
+ """
+ }
+
+ bam_files_single.into{ bam_files_single_fa; bam_files_single_ba}
+
+ process bam_2_fastq_single {
+ tag "$file_id"
+
+ input:
+ set file_id, file(bam) from bam_files_single_fa
+
+ output:
+ set file_id, "*.fastq" into fastq_files_extracted
+ script:
+ """
+ samtools fastq -0 s${file_id}.fastq -F 0x4 ${bam}
+ """
+ }
+
+ process filter_bam_single {
+ tag "$file_id"
+ cpus 4
+
+ input:
+ set file_id, file(bam) from bam_files_single_ba
+ file bed from bed_files
+
+ output:
+ set file_id, "*.bam" into filtered_bam_files_single
+ script:
+ """
+ samtools view -@ ${task.cpus} -hb ${bam} -F 0x4 > f${file_id}.bam
+ """
+ }
+
+ process sort_bam_single {
+ tag "$file_id"
+ publishDir "results/training/bams/", mode: 'copy'
+ cpus 4
+
+ input:
+ set file_id, file(bam) from filtered_bam_files_single
+
+ output:
+ set file_id, "*.bam" into sorted_bam_files_single
+
+ script:
+ """
+ samtools sort -@ ${task.cpus} -O BAM -o s${file_id}.bam ${bam}
+ """
+ }
+
+ process index_bam_single {
+ tag "$file_id"
+ publishDir "results/training/bams/", mode: 'copy'
+
+ input:
+ set file_id, file(bam) from sorted_bam_files_single
+
+ output:
+ set file_id, "*.bam*" into indexed_bam_file_single
+
+ script:
+ """
+ samtools index ${bam}
+ """
+ }
+}
+