From 4d8776b97b7737e0fcf58c8ed09f2d5d7c393882 Mon Sep 17 00:00:00 2001
From: Laurent Modolo <laurent.modolo@ens-lyon.fr>
Date: Tue, 5 Jun 2018 13:28:06 +0200
Subject: [PATCH] RSEM: fix dockerfile and add nf and test files
---
src/nf_modules/RSEM/1.3.0/Dockerfile | 4 +-
src/nf_modules/RSEM/rsem.config | 24 +++
src/nf_modules/RSEM/rsem.nf | 139 ++++++++++++++++++
src/nf_modules/RSEM/tests/index.nf | 40 +++++
.../RSEM/tests/quantification_paired.nf | 40 +++++
.../RSEM/tests/quantification_single.nf | 44 ++++++
src/nf_modules/RSEM/tests/tests.sh | 18 +++
7 files changed, 308 insertions(+), 1 deletion(-)
create mode 100644 src/nf_modules/RSEM/rsem.config
create mode 100644 src/nf_modules/RSEM/rsem.nf
create mode 100644 src/nf_modules/RSEM/tests/index.nf
create mode 100644 src/nf_modules/RSEM/tests/quantification_paired.nf
create mode 100644 src/nf_modules/RSEM/tests/quantification_single.nf
create mode 100644 src/nf_modules/RSEM/tests/tests.sh
diff --git a/src/nf_modules/RSEM/1.3.0/Dockerfile b/src/nf_modules/RSEM/1.3.0/Dockerfile
index 14d4757..1ccdaa7 100644
--- a/src/nf_modules/RSEM/1.3.0/Dockerfile
+++ b/src/nf_modules/RSEM/1.3.0/Dockerfile
@@ -3,11 +3,13 @@ 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* \
build-essential=12.4* \
ca-certificates=20180409 \
zlib1g-dev=1:1.2.11* \
- bowtie2=${BOWTIE2_VERSION}*
+ bowtie2=${BOWTIE2_VERSION}* \
+ samtools=${SAMTOOLS_VERSION}*
RUN apt-get update && \
apt-get install -y --no-install-recommends ${PACKAGES} && \
diff --git a/src/nf_modules/RSEM/rsem.config b/src/nf_modules/RSEM/rsem.config
new file mode 100644
index 0000000..3209b6b
--- /dev/null
+++ b/src/nf_modules/RSEM/rsem.config
@@ -0,0 +1,24 @@
+profiles {
+ docker {
+ docker.temp = 'auto'
+ docker.enabled = true
+ process {
+ $index_fasta {
+ container = "rsem:1.3.0"
+ }
+ $mapping_fastq {
+ container = "rsem:1.3.0"
+ }
+ }
+ }
+ sge {
+ process{
+ $index_fasta {
+ beforeScript = "module purge; module load RSEM/1.3.0; module load SAMtools/1.7"
+ }
+ $mapping_fastq {
+ beforeScript = "module purge; module load RSEM/1.3.0; module load SAMtools/1.7"
+ }
+ }
+ }
+}
diff --git a/src/nf_modules/RSEM/rsem.nf b/src/nf_modules/RSEM/rsem.nf
new file mode 100644
index 0000000..54e6ad0
--- /dev/null
+++ b/src/nf_modules/RSEM/rsem.nf
@@ -0,0 +1,139 @@
+/*
+* RSEM :
+* Imputs : fastq files
+* Imputs : fasta files
+* Output : bam files
+*/
+
+/* fasta indexing */
+params.fasta = "$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} > ${tagname}_rsem_bowtie2_report.txt
+"""
+}
+
diff --git a/src/nf_modules/RSEM/tests/index.nf b/src/nf_modules/RSEM/tests/index.nf
new file mode 100644
index 0000000..0f5473a
--- /dev/null
+++ b/src/nf_modules/RSEM/tests/index.nf
@@ -0,0 +1,40 @@
+params.fasta = "$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
+"""
+}
+
+
diff --git a/src/nf_modules/RSEM/tests/quantification_paired.nf b/src/nf_modules/RSEM/tests/quantification_paired.nf
new file mode 100644
index 0000000..75ae42f
--- /dev/null
+++ b/src/nf_modules/RSEM/tests/quantification_paired.nf
@@ -0,0 +1,40 @@
+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} \
+> ${pair_id}_rsem_bowtie2_report.txt
+"""
+}
+
+
diff --git a/src/nf_modules/RSEM/tests/quantification_single.nf b/src/nf_modules/RSEM/tests/quantification_single.nf
new file mode 100644
index 0000000..0fd26f0
--- /dev/null
+++ b/src/nf_modules/RSEM/tests/quantification_single.nf
@@ -0,0 +1,44 @@
+params.fastq = "$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} ${reads.baseName} \
+> ${reads.baseName}_rsem_bowtie2_report.txt
+"""
+}
+
diff --git a/src/nf_modules/RSEM/tests/tests.sh b/src/nf_modules/RSEM/tests/tests.sh
new file mode 100644
index 0000000..f7fcd06
--- /dev/null
+++ b/src/nf_modules/RSEM/tests/tests.sh
@@ -0,0 +1,18 @@
+nextflow src/nf_modules/RSEM/tests/index.nf \
+ -c src/nf_modules/RSEM/rsem.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 \
+ -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 \
+ -profile docker \
+ --index "results/mapping/index/tiny_v2.index*" \
+ --fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
+
--
GitLab