Merge pull request #16 from IARCbioinfo/dev

Dev

Author: nalcala

.circleci/config.yml

@@ -8,9 +8,13 @@ jobs:
                         - run: cd ~ ; wget -qO- get.nextflow.io | bash ; chmod 755 nextflow ; sudo ln -s ~/nextflow /usr/local/bin/ ; sudo apt-get install graphviz
                         - run: cd ~ && git clone https://github.com/iarcbioinfo/data_test.git
                         - run: echo " docker.runOptions = '-u $(id -u):$(id -g)' " > ~/.nextflow/config
-                        - run: cd ~/project/ ; docker build -t iarcbioinfo/rnaseq-nf .
+                        - run: 
+                                name: docker_build
+                                no_output_timeout: 120m
+                                command: cd ~/project/ ; docker build -t iarcbioinfo/rnaseq-nf .
                         - run: cd ; nextflow run ~/project/RNAseq.nf --help
                         - run: cd ; nextflow run ~/project/RNAseq.nf -with-docker iarcbioinfo/rnaseq-nf --input_folder ~/data_test/BAM/ --output_folder BAM_realigned --ref_folder  ~/data_test/REF --gtf ~/data_test/REF/TP53_small.gtf --bed ~/data_test/BED/TP53_small.bed --cpu 2 --mem 4 -with-dag dag_STAR.png
+                        - run: cd ; nextflow run ~/project/RNAseq.nf -with-docker iarcbioinfo/rnaseq-nf --input_folder data_test/FASTQ/ --fastq_ext fastq.gz --suffix2 null --output_folder BAM_aligned --ref_folder  data_test/REF --gtf data_test/REF/TP53_small.gtf --bed data_test/BED/TP53_small.bed --cpu 2 --mem 4 --sjtrim --ref data_test/REF/17_7572000-7591000.fasta --recalibration --snp_vcf data_test/REF/dbsnp_138.17_7572000-7591000.vcf.gz --indel_vcf data_test/REF/1000G_phase1.indels.17_7572000-7591000.sites.vcf.gz
                         - run: cd ; nextflow run ~/project/RNAseq.nf -with-docker iarcbioinfo/rnaseq-nf --input_folder ~/data_test/BAM/ --output_folder BAM_realigned --ref_folder  ~/data_test/REF --gtf ~/data_test/REF/TP53_small.gtf --bed ~/data_test/BED/TP53_small.bed --cpu 2 --mem 4 -with-dag dag_STAR.html
                         - run: cd ; nextflow run ~/project/RNAseq.nf -with-docker iarcbioinfo/rnaseq-nf --input_folder ~/data_test/BAM/ --output_folder BAM_realigned_sjtrim --ref_folder  ~/data_test/REF --gtf ~/data_test/REF/TP53_small.gtf --bed ~/data_test/BED/TP53_small.bed --cpu 2 --mem 4 --sjtrim --ref ~/data_test/REF/17_7572000-7591000.fasta -with-dag dag_STAR_sjtrim.png
                         - run: cd ; nextflow run ~/project/RNAseq.nf -with-docker iarcbioinfo/rnaseq-nf --input_folder ~/data_test/BAM/ --output_folder BAM_realigned_sjtrim --ref_folder  ~/data_test/REF --gtf ~/data_test/REF/TP53_small.gtf --bed ~/data_test/BED/TP53_small.bed --cpu 2 --mem 4 --sjtrim --ref ~/data_test/REF/17_7572000-7591000.fasta -with-dag dag_STAR_sjtrim.html

Dockerfile

@@ -6,7 +6,7 @@ FROM continuumio/miniconda3:4.7.12
 LABEL base_image="continuumio/miniconda3"
 LABEL version="4.7.12"
 LABEL software="rnaseq-nf"
-LABEL software.version="2.3"
+LABEL software.version="2.4"
 LABEL about.summary="Container image containing all requirements for rnaseq-nf"
 LABEL about.home="http://github.com/IARCbioinfo/RNAseq-nf"
 LABEL about.documentation="http://github.com/IARCbioinfo/RNAseq-nf/README.md"
@@ -19,5 +19,6 @@ MAINTAINER **nalcala** <**alcalan@fellows.iarc.fr**>
 ################## INSTALLATION ######################
 COPY environment.yml /
 RUN apt-get update && apt-get install -y procps && apt-get clean -y
+RUN conda config --set channel_priority strict
 RUN conda env create -n rnaseq-nf -f /environment.yml && conda clean -a
 ENV PATH /opt/conda/envs/rnaseq-nf/bin:$PATH

README.md

@@ -125,6 +125,24 @@ nextflow run iarcbioinfo/RNAseq-nf -r v2.2 -profile singularity --input_folder f
 ``` 
 To run the pipeline using conda instead of singularity, replace "-profile singularity" by "-profile conda". To run with your own local software installation, just remove "-profile singularity".
 
+### Single-end fastq mode
+Default is adapted to paired-end libraries. To use single-end libraries as input, you must specify the option "--suffix2 null". 
+```bash
+nextflow run iarcbioinfo/RNAseq-nf -r v2.2 -profile singularity --input_folder fastq --ref_folder ref_genome --gtf ref.gtf --bed ref.bed --suffix2 null
+``` 
+If using "--input_file", you must additionally set the values in column "pair2" to "NO_fastq2". For example the following file input.txt:
+
+```
+SM RG pair1 pair2
+sample1		sample1.fq.gz	NO_fastq2
+sample2	RG1	sample2_RG1.fq.gz	NO_fastq2
+sample2	RG2	sample2_RG2.fq.gz	NO_fastq2
+``` 
+can be processed with 
+```bash
+nextflow run iarcbioinfo/RNAseq-nf -r v2.2 -profile singularity --input_file input.txt --ref_folder ref_genome --gtf ref.gtf --bed ref.bed --suffix2 null
+``` 
+
 ### Use hisat2 for mapping
 To use hisat2 instead of STAR for the reads mapping, you must add the ***--hisat2* option**, specify the path to the folder containing the hisat2 index files (genome_tran.1.ht2 to genome_tran.8.ht2), as well as satisfy the requirements above mentionned. For example:
 ```bash

RNAseq.nf

@@ -48,7 +48,7 @@ params.help         = null
 
 log.info "" 
 log.info "--------------------------------------------------------"
-log.info "  RNAseq-nf 2.3.0: alignment, QC, and reads counting workflow for RNA sequencing "
+log.info "  RNAseq-nf 2.4.0: alignment, QC, and reads counting workflow for RNA sequencing "
 log.info "--------------------------------------------------------"
 log.info "Copyright (C) IARC/WHO"
 log.info "This program comes with ABSOLUTELY NO WARRANTY; for details see LICENSE"
@@ -132,6 +132,9 @@ if (params.help) {
   log.info "help           = ${params.help}"
 }
 
+suffix2 = params.suffix2
+if(suffix2=="null" ) suffix2 = null
+
 //multiqc config file
 ch_config_for_multiqc = file(params.multiqc_config)
 
@@ -216,31 +219,19 @@ if(mode=='bam'){
 if(mode=='fastq'){
     println "fastq mode"
 
-    keys1 = file(params.input_folder).listFiles().findAll { it.name ==~ /.*${params.suffix1}.${params.fastq_ext}/ }.collect { it.getName() }
-                                                                                                               .collect { it.replace("${params.suffix1}.${params.fastq_ext}",'') }
-    keys2 = file(params.input_folder).listFiles().findAll { it.name ==~ /.*${params.suffix2}.${params.fastq_ext}/ }.collect { it.getName() }
-                                                                                                               .collect { it.replace("${params.suffix2}.${params.fastq_ext}",'') }
-    if ( !(keys1.containsAll(keys2)) || !(keys2.containsAll(keys1)) ) {println "\n ERROR : There is not at least one fastq without its mate, please check your fastq files."; System.exit(0)}
-
-readPairs0 = Channel.fromFilePairs(params.input_folder +"/*{${params.suffix1},${params.suffix2}}" +'.'+ params.fastq_ext)
+    if(suffix2){
+        println "paired library"
+        readPairs0 = Channel.fromFilePairs(params.input_folder +"/*{${params.suffix1},${params.suffix2}}" +'.'+ params.fastq_ext)
 			      .map { row -> [ row[0] , "" , row[1][0], row[1][1] ] }
-                  .subscribe{ row -> println "${row}" }
-
-// Gather files ending with _1 suffix
-   reads1 = Channel
-    .fromPath( params.input_folder+'/*'+params.suffix1+'.'+params.fastq_ext )
-    .map {  path -> [ path.name.replace("${params.suffix1}.${params.fastq_ext}",""), path ] }
-
-// Gather files ending with _2 suffix
-   reads2 = Channel
-    .fromPath( params.input_folder+'/*'+params.suffix2+'.'+params.fastq_ext )
-    .map {  path -> [ path.name.replace("${params.suffix2}.${params.fastq_ext}",""), path ] }
-
-// Match the pairs on two channels having the same 'key' (name) and emit a new pair containing the expected files
-   reads1
-    .phase(reads2)
-    .map { pair1, pair2 -> [ pair1[0] , "" , pair1[1], pair2[1] ] }
-    .into{ readPairs ; readPairs2}
+                  .view()
+                  .into{ readPairs ; readPairs2}
+    }else{
+        println "single library"
+        readPairs0 = Channel.fromPath(params.input_folder +"/*${params.suffix1}" +'.'+ params.fastq_ext)
+			      .map { row -> [ row.name.replace("${params.suffix1}.${params.fastq_ext}","") , "" , row , file("NO_fastq2") ] }
+                  .view()
+                  .into{ readPairs ; readPairs2}
+    }
 }
 }
 
@@ -262,10 +253,17 @@ process fastqc_pretrim {
 	shell:
 	basename1=pair1.name.replace(".${params.fastq_ext}","") //baseName.split("\\.")[0]
 	basename2=pair2.name.replace(".${params.fastq_ext}","") //baseName.split("\\.")[0]
+    if(suffix2){
+        pairs="${pair1} ${pair2}"
+    }else{
+        pairs="${pair1}"
+    }
     '''
-	fastqc -t !{task.cpus} !{pair1} !{pair2}
+	fastqc -t !{task.cpus} !{pairs}
 	mv !{basename1}_fastqc.zip !{file_tag}!{params.suffix1}!{rg}_pretrim_fastqc.zip
-	mv !{basename2}_fastqc.zip !{file_tag}!{params.suffix2}!{rg}_pretrim_fastqc.zip 
+	if [ ! -L NO_fastq2 ]
+        then mv !{basename2}_fastqc.zip !{file_tag}!{params.suffix2}!{rg}_pretrim_fastqc.zip 
+    fi 
     '''
 }
 
@@ -281,7 +279,7 @@ if(params.cutadapt!=null){
 
         output:
         set val(file_tag), val(rg) , file("${file_tag}${rg}*val_1.fq.gz"), file("${file_tag}${rg}*val_2.fq.gz")  into readPairs3
-	    file("*_val_*_fastqc.zip") into fastqc_postpairs
+	    file("*_fastqc.zip") into fastqc_postpairs
 	    file("*trimming_report.txt") into trimming_reports
 
 	    publishDir "${params.output_folder}/QC/adapter_trimming", mode: 'copy', pattern: '{*report.txt,*fastqc.zip}'
@@ -290,8 +288,19 @@ if(params.cutadapt!=null){
 	    cpu_tg = params.cpu_trim -1
 	    cpu_tg2 = cpu_tg.div(3.5)
 	    cpu_tg3 = Math.round(Math.ceil(cpu_tg2))
+        if(suffix2){
+            pairs="${pair1} ${pair2}"
+            opts="--paired "
+        }else{
+            pairs="${pair1}"
+            opts=" "
+        }
         '''
-	    trim_galore --paired --fastqc --gzip --basename !{file_tag}!{rg} -j !{cpu_tg3} !{pair1} !{pair2}
+	    trim_galore !{opts} --fastqc --gzip --basename !{file_tag}!{rg} -j !{cpu_tg3} !{pairs}
+        if [ ! -L NO_fastq2 ]
+            mv !{file_tag}!{rg}_trimmed.fq.gz !{file_tag}!{rg}_val_1.fq.gz
+            then touch !{file_tag}!{rg}_val_2.fq.gz 
+        fi 
         '''
 	}
 }else{
@@ -337,23 +346,32 @@ process alignment {
       sort_threads = params.cpu.intdiv(2) - 1
       sort_mem     = params.mem.intdiv(4)
       input_f1="${pair1[0]}"
-      input_f2="${pair2[0]}"
       rgtmp="${rg[0]}"
       if(rgtmp=="") rgtmp="${file_tag}"
       rgline="ID:${rgtmp} SM:${file_tag} ${params.RG}"
       for( p1tmp in pair1.drop(1) ){
-	input_f1=input_f1+",${p1tmp}"
-      }
-      for( p2tmp in pair2.drop(1) ){
-        input_f2=input_f2+",${p2tmp}"
+	    input_f1=input_f1+",${p1tmp}"
       }
       for( rgtmp in rg.drop(1) ){
-	if(rgtmp=="") rgtmp="${file_tag}"
+	    if(rgtmp=="") rgtmp="${file_tag}"
         rgline=rgline+" , ID:${rgtmp} SM:${file_tag} ${params.RG}"
       }
-      MQ=""
+      if(suffix2){
+        input_f2="${pair2[0]}"
+        for( p2tmp in pair2.drop(1) ){
+            input_f2=input_f2+",${p2tmp}"
+        }
+        pairs="${input_f1} ${input_f2}"
+      }else{
+        pairs="${input_f1}"
+      }
       '''
-      STAR --outSAMattrRGline !{rgline} --outSAMmapqUnique !{params.STAR_mapqUnique} --chimSegmentMin 12 --chimJunctionOverhangMin 12 --chimSegmentReadGapMax 3 --alignSJDBoverhangMin 10 --alignMatesGapMax 100000 --alignIntronMax 100000 --alignSJstitchMismatchNmax 5 -1 5 5 --outSAMstrandField intronMotif --chimMultimapScoreRange 10 --chimMultimapNmax 10 --chimNonchimScoreDropMin 10 --peOverlapNbasesMin 12 --peOverlapMMp 0.1 --chimOutJunctionFormat 1 --twopassMode Basic --outReadsUnmapped None --runThreadN !{align_threads} --genomeDir . --sjdbGTFfile !{gtf} --readFilesCommand zcat --readFilesIn !{input_f1} !{input_f2} --outStd SAM | samblaster --addMateTags | sambamba view -S -f bam -l 0 /dev/stdin | sambamba sort -t !{sort_threads} -m !{sort_mem}G --tmpdir=!{file_tag}_tmp -o !{file_tag}.bam /dev/stdin
+      STAR --outSAMattrRGline !{rgline} --outSAMmapqUnique !{params.STAR_mapqUnique} --chimSegmentMin 12 --chimJunctionOverhangMin 12 \
+           --chimSegmentReadGapMax 3 --alignSJDBoverhangMin 10 --alignMatesGapMax 100000 --alignIntronMax 100000 \
+           --alignSJstitchMismatchNmax 5 -1 5 5 --outSAMstrandField intronMotif --chimMultimapScoreRange 10 --chimMultimapNmax 10 \
+           --chimNonchimScoreDropMin 10 --peOverlapNbasesMin 12 --peOverlapMMp 0.1 --chimOutJunctionFormat 1 --twopassMode Basic \
+           --outReadsUnmapped None --runThreadN !{align_threads} --genomeDir . --sjdbGTFfile !{gtf} --readFilesCommand zcat \
+           --readFilesIn !{pairs} --outStd SAM | samblaster --addMateTags | sambamba view -S -f bam -l 0 /dev/stdin | sambamba sort -t !{sort_threads} -m !{sort_mem}G --tmpdir=!{file_tag}_tmp -o !{file_tag}.bam /dev/stdin
       mv Chimeric.out.junction STAR.!{file_tag}.Chimeric.SJ.out.junction
       mv SJ.out.tab STAR.!{file_tag}.SJ.out.tab
       mv Log.final.out STAR.!{file_tag}.Log.final.out

Singularity/Singularity.v2.4

@@ -0,0 +1,9 @@
+From:iarcbioinfo/rnaseq-nf:v2.4
+Bootstrap:docker
+
+%labels
+    MAINTAINER **alcalan** <**alcalan@fellows.iarc.fr**>
+    DESCRIPTION Container image containing all requirements for pipeline RNAseq-nf
+    VERSION 2.4
+
+

dag_STAR.html

@@ -199,15 +199,15 @@
 { data: { source: 'p26', target: 'p46', label: 'align_out' } },
 { data: { source: 'p26', target: 'p28', label: 'SJ_out' } },
 { data: { source: 'p26', target: 'p27', label: 'SJ_out_others' } },
-{ data: { source: 'p29', target: 'p40', label: 'recal_bam_files4quant' } },
-{ data: { source: 'p29', target: 'p32', label: 'recal_bam4QCsplittmp' } },
 { data: { source: 'p29', target: 'p31', label: 'recal_bam_files4QC' } },
+{ data: { source: 'p29', target: 'p32', label: 'recal_bam4QCsplittmp' } },
+{ data: { source: 'p29', target: 'p40', label: 'recal_bam_files4quant' } },
 { data: { source: 'p30', target: 'p31', label: 'bed' } },
 { data: { source: 'p31', target: 'p49', label: 'rseqc_files' } },
 { data: { source: 'p31', target: 'p48', label: 'rseqc_clip_files' } },
 { data: { source: 'p31', target: 'p50', label: 'rseqc_jsat_files' } },
-{ data: { source: 'p32', target: 'p34', label: 'recal_bam_files4QCsplit0' } },
 { data: { source: 'p32', target: 'p33', label: 'simple' } },
+{ data: { source: 'p32', target: 'p34', label: 'recal_bam_files4QCsplit0' } },
 { data: { source: 'p34', target: 'p36', label: 'recal_bam_files4QCsplit' } },
 { data: { source: 'p34', target: 'p37', label: 'recal_bam_files4QCsplit4test' } },
 { data: { source: 'p35', target: 'p36', label: 'bed' } },