From 36a3562cea56970e98d892916ca137226792480d Mon Sep 17 00:00:00 2001 From: Xavier Grand <157-xgrand@users.noreply.gitbio.ens-lyon.fr> Date: Wed, 27 Jul 2022 14:16:50 +0200 Subject: [PATCH] Modif idx genome to Channel --- src/RNAseq_XGR.nf | 40 ++++++++++++++++++------------ src/nf_modules/star/main_2.7.8a.nf | 6 ++--- 2 files changed, 27 insertions(+), 19 deletions(-) diff --git a/src/RNAseq_XGR.nf b/src/RNAseq_XGR.nf index 800501f..a5f8ff5 100644 --- a/src/RNAseq_XGR.nf +++ b/src/RNAseq_XGR.nf @@ -20,6 +20,7 @@ Maintainer Xavier Grand <xavier.grand@ens-lyon.fr> def helpMessage() { log.info""" Usage: + Pipeline dedicated to transcriptomic analysis of short-reads paired-ends RNAseq. The typical command for running the pipeline is as follows: nextflow ./src/RNAseq_XGR.nf -c ./src/nextflow.config -profile singularity @@ -63,6 +64,7 @@ params.fastq = "${project}/fastq/*_{1,2}.fq.gz" params.gtf = "" params.fasta = "" params.idx = "" +params.filter_bam = "-F 268 -f 1 -q 10" params.fastp_out = "$params.project/fastp/" params.star_mapping_fastq_out = "$params.project/STAR/" @@ -107,6 +109,10 @@ include { index_with_gtf } from "./nf_modules/star/main_2.7.8a.nf" include { mapping_fastq } from "./nf_modules/star/main_2.7.8a.nf" include { mapping_withindex } from "./nf_modules/star/main_2.7.8a.nf" include { htseq_count } from "./nf_modules/htseq/main.nf" +include { filter_bam } from "./nf_modules/samtools/main.nf" +include { stats_bam } from "./nf_modules/samtools/main.nf" +include { sort_bam } from "./nf_modules/samtools/main.nf" +include { index_bam } from "./nf_modules/samtools/main.nf" /* **************************************************************** @@ -120,20 +126,6 @@ workflow { // fastp fastp(fastq_files) - //########################## QUALITY CHECKS ################### - - // fastqc_rawdata - fastqc_raw(fastq_files) - // fastqc_processed - fastqc_preprocessed(fastp.out.fastq.map { it -> [it [0], it[1]]}) - // multiqc - multiqc( - fastqc_raw.out.report - .mix( - fastqc_preprocessed.out.report - ).collect() - ) - //############ GENOME INDEXATION AND MAPPING ################### if (params.idx == "") { @@ -145,7 +137,7 @@ workflow { index_with_gtf(genome_file, gtf_file.collect()) mapping_fastq(index_with_gtf.out.index.collect(), fastp.out.fastq) - htseq_count(mapping_fastq.out.bam, gtf_file) + } else { idx_genome = "${params.idx}" @@ -153,7 +145,23 @@ workflow { .of( idx_genome ) .set { genome_indexed_input } genome_indexed_input.view() - mapping_withindex(fastp.out.fastq) + mapping_withindex(genome_indexed_input.collect(), fastp.out.fastq) htseq_count(mapping_withindex.out.bam, gtf_file) } + + htseq_count(mapping_fastq.out.bam, gtf_file) + + //########################## QUALITY CHECKS ################### + + // fastqc_rawdata + fastqc_raw(fastq_files) + // fastqc_processed + fastqc_preprocessed(fastp.out.fastq.map { it -> [it [0], it[1]]}) + // multiqc + multiqc( + fastqc_raw.out.report + .mix( + fastqc_preprocessed.out.report + ).collect() + ) } diff --git a/src/nf_modules/star/main_2.7.8a.nf b/src/nf_modules/star/main_2.7.8a.nf index 8e25ccd..91a74dc 100644 --- a/src/nf_modules/star/main_2.7.8a.nf +++ b/src/nf_modules/star/main_2.7.8a.nf @@ -185,7 +185,6 @@ mv ${reads_id}.Aligned.sortedByCoord.out.bam ${reads_id}.bam """ } -params.idx = "" process mapping_withindex { container = "${container_url}" label "big_mem_multi_cpus" @@ -194,6 +193,7 @@ process mapping_withindex { } input: + val(index) tuple val(reads_id), path(reads) output: @@ -210,7 +210,7 @@ if (reads_id instanceof List){ if (reads.size() == 2) """ STAR --runThreadN ${task.cpus} \ ---genomeDir ${params.idx} \ +--genomeDir ${index} \ --readFilesCommand zcat \ --readFilesIn ${reads[0]} ${reads[1]} \ --outFileNamePrefix ${reads_id}. \ @@ -223,7 +223,7 @@ mv ${reads_id}.Aligned.sortedByCoord.out.bam ${reads_id}.bam else """ STAR --runThreadN ${task.cpus} \ ---genomeDir ${params.idx} \ +--genomeDir ${index} \ --readFilesCommand zcat \ --readFilesIn ${reads} \ --outFileNamePrefix ${reads_id}. \ -- GitLab