Merge pull request #4 from IARCbioinfo/dev

Dev
IARCbioinfo · Aug 4, 2020 · 6697e6d · 6697e6d
2 parents 83de666 + c9291c6
commit 6697e6d
Show file tree

Hide file tree

Showing 5 changed files with 38 additions and 16 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -20,9 +20,10 @@ jobs:
                 - run: cd ~ && git clone -b v2.3 https://github.com/iarcbioinfo/RNAseq-nf.git
                 - run: cd ; nextflow run RNAseq-nf/ -profile docker --input_folder ~/data_test/FASTQ/ --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
                 - run: cd ; nextflow run ~/project/ --help
-                - run: cd ; docker pull trinityctat/starfusion:1.8.1
-                - run: cd ; nextflow run ~/project/ -with-docker trinityctat/starfusion:1.8.1 --input_folder ~/data_test/FASTQ/ --output_folder RNAseq-fusion-out --CTAT_folder ~/data_test/REF/ctat_genome_lib_build_dir_TP53/ --fastq_ext fastq.gz --cpu 2 --mem 4 -with-dag dag.html
-                - run: cd ; nextflow run ~/project/ -with-docker trinityctat/starfusion:1.8.1 --input_folder ~/data_test/FASTQ/ --output_folder RNAseq-fusion-out --CTAT_folder ~/data_test/REF/ctat_genome_lib_build_dir_TP53/ --fastq_ext fastq.gz --cpu 2 --mem 4 -resume -with-dag dag.png
+                - run: cd ; docker pull trinityctat/starfusion:1.9.0
+                - run: cd ; nextflow run ~/project/ -with-docker trinityctat/starfusion:1.9.0 --input_folder ~/data_test/FASTQ/ --output_folder RNAseq-fusion-out --CTAT_folder ~/data_test/REF/ctat_genome_lib_build_dir_TP53/ --fastq_ext fastq.gz --cpu 2 --mem 4 -with-dag dag.html
+                - run: cd ; nextflow run ~/project/ -with-docker trinityctat/starfusion:1.9.0 --input_folder ~/data_test/FASTQ/ --output_folder RNAseq-fusion-out --CTAT_folder ~/data_test/REF/ctat_genome_lib_build_dir_TP53/ --fastq_ext fastq.gz --cpu 2 --mem 4 -resume -with-dag dag.png
+                - run: cd ; echo -e 'SM\tpair1\tpair2\tjunction\nNA06984\tdata_test/FASTQ/NA06984_T_1.fastq.gz\tdata_test/FASTQ/NA06984_T_2.fastq.gz\tnone\nNA06984_2RG\tdata_test/FASTQ/NA06984_T_RG1_1.fastq.gz\tdata_test/FASTQ/NA06984_T_RG1_2.fastq.gz\tnone\nNA06984_2RG\tdata_test/FASTQ/NA06984_T_RG2_1.fastq.gz\tdata_test/FASTQ/NA06984_T_RG2_2.fastq.gz\tnone' > input.txt ; nextflow run ~/project/ -with-docker trinityctat/starfusion:1.9.0 --input_file input.txt --output_folder RNAseq-fusion-out --CTAT_folder ~/data_test/REF/ctat_genome_lib_build_dir_TP53/ --fastq_ext fastq.gz --cpu 2 --mem 4
                 - run: cd ; cp ~/dag.* ~/project/.
                 - add_ssh_keys:
                                 fingerprints:

diff --git a/README.md b/README.md
@@ -36,10 +36,10 @@ In addition, STAR-Fusion requires a [CTAT bundle](https://data.broadinstitute.or
 | --CTAT_folder   |. | Folder with STAR-Fusion bundle (CTAT) |
 
 
-
   * #### Optional
 | Name      | Default value | Description     |
 |-----------|---------------|-----------------|
+| --input_file  | NULL  | Input file (comma-separated) with 4 columns: SM(sample name), pair1 (path to fastq pair 1), pair2 (path to fastq pair 2), and junction (path to junction file) |
 | --output_folder   |   results_fusion | Output folder |
 | --fastq_ext       |   fq.gz    |            Extension of fastq files |
 | --suffix1         |  _1 |   Suffix of 1st element of fastq files pair |
@@ -49,6 +49,7 @@ In addition, STAR-Fusion requires a [CTAT bundle](https://data.broadinstitute.or
 | --cpu             |  2 |         Number of cpu used by bwa mem and sambamba |
 | --mem             |  2 |   Size of memory used for mapping (in GB)|
 
+Note: using the input_file mode allows to specify multiple fastq files for a given sample, that are merged during the alignment phase.
 
   * #### Flags
 
@@ -59,10 +60,11 @@ Flags are special parameters without value.
 | --junctions | Option to use STAR junction files already generated |
 | --help    | Display help |
 
+Note: when the --junctions option is not used, the junction column of the input file is ignored.
 
 ## Usage
   ```
-  nextflow run iarcbioinfo/RNAseq-fusion-nf -r v1.0 -profile singularity  --input_folder input --CTAT_folder CTAT --output_folder output
+  nextflow run iarcbioinfo/RNAseq-fusion-nf -r v1.1 -profile singularity  --input_folder input --CTAT_folder CTAT --output_folder output
   ```
 
 To run the pipeline without singularity just remove "-profile singularity"; you can also directly download a singularity image at https://data.broadinstitute.org/Trinity/CTAT_SINGULARITY/STAR-Fusion/ using the command `singularity pull https://data.broadinstitute.org/Trinity/CTAT_SINGULARITY/STAR-Fusion/star-fusion.v1.9.0.simg`. Alternatively, one can run the pipeline using a docker container (-profile docker) the conda receipe containing all required dependencies (-profile conda).
@@ -83,7 +85,7 @@ To run the pipeline without singularity just remove "-profile singularity"; you
 
   | Name      | Email | Description     |
   |-----------|---------------|-----------------|
-  | Nicolas Alcala    |  alcalan@fellows.iarc.fr | Developer to contact for support |
+  | Nicolas Alcala    |  [email protected] | Developer to contact for support |
 
 ## References
 Haas, B. J., Dobin, A., Li, B., Stransky, N., Pochet, N., & Regev, A. (2019). Accuracy assessment of fusion transcript detection via read-mapping and de novo fusion transcript assembly-based methods. Genome biology, 20(1), 213.

diff --git a/environment.yml b/environment.yml
@@ -4,5 +4,5 @@ channels:
   - conda-forge
   - defaults
 dependencies:
-  - star-fusion=1.8.1
+  - star-fusion=1.9.0
   - python=3.6
diff --git a/nextflow.config b/nextflow.config
@@ -13,12 +13,12 @@ profiles {
 	}
   docker { 
     docker.enabled = true 
-    process.container = 'trinityctat/starfusion:1.8.1'
+    process.container = 'trinityctat/starfusion:1.9.0'
   }
   singularity { 
     singularity.enabled = true 
     singularity.autoMounts = true
-    process.container = 'docker://trinityctat/starfusion:1.8.1'
+    process.container = 'docker://trinityctat/starfusion:1.9.0'
     pullTimeout = "200 min"
   }
 }

diff --git a/rnaseq-fusion.nf b/rnaseq-fusion.nf
@@ -17,6 +17,7 @@
 
 params.CTAT_folder = '.'
 params.input_folder = '.'
+params.input_file   = null
 params.output_folder= "results_fusion"
 params.mem  = 2
 params.cpu  = 2
@@ -31,7 +32,7 @@ params.help = null
 
 log.info ""
 log.info "--------------------------------------------------------"
-log.info "  rnaseq-fusion-nf v1.0: nextflow pipeline to run STAR-fusion "
+log.info "  rnaseq-fusion-nf v1.1: nextflow pipeline to run STAR-fusion "
 log.info "--------------------------------------------------------"
 log.info "Copyright (C) IARC/WHO"
 log.info "This program comes with ABSOLUTELY NO WARRANTY; for details see LICENSE"
@@ -42,16 +43,19 @@ log.info ""
 
 if (params.help) {
     log.info "--------------------------------------------------------"
-    log.info "  USAGE nextflow run rnaseq-fusion-nf --input_folder fastq/ --CTAT_folder GRCh38_CTAT/                                                 "
+    log.info "  USAGE            "
     log.info "--------------------------------------------------------"
     log.info ""
-    log.info "nextflow run iarcbioinfo/rnaseq-transcript-nf [-with-docker] [OPTIONS]"
+    log.info "nextflow run IARCbioinfo/RNAseq-fusion-nf --input_folder fastq/ --CTAT_folder GRCh38_CTAT/  [-with-docker] [OPTIONS]"
     log.info ""
     log.info "Mandatory arguments:"
     log.info '    --input_folder    FOLDER                  Folder containing fastq files and STAR junction files.'
     log.info '    --CTAT_folder     FOLDER                  Folder with STAR-Fusion bundle (CTAT).'
     log.info ""
     log.info "Optional arguments:"
+    log.info '    --input_file      STRING                  Input file (comma-separated) with 4 columns:'
+    log.info '                                              SM(sample name), pair1 (path to fastq pair 1), '
+    log.info '                                              pair2 (path to fastq pair 2), and junction (path to junction file).'
     log.info '    --output_folder   STRING                  Output folder (default: results_fusion).'
     log.info '    --fastq_ext       STRING                  Extension of fastq files (default: fq.gz).'
     log.info '    --suffix1         STRING                  Suffix of 1st element of fastq files pair (default: _1).'
@@ -62,12 +66,13 @@ if (params.help) {
     log.info '    --mem             INTEGER                 Size of memory used for mapping (in GB) (default: 2).' 
     log.info ""
     log.info "Flags:"
-    log.info "--junctions          Option to use STAR junction files (default: null)."
+    log.info "    --junctions                               Option to use STAR junction files (default: null)."
     log.info ""
     exit 0
 } else {
 /* Software information */
    log.info "input_folder    = ${params.input_folder}"
+   log.info "input_file      = ${params.input_file}"
    log.info "cpu             = ${params.cpu}"
    log.info "mem             = ${params.mem}"
    log.info "output_folder   = ${params.output_folder}"
@@ -83,6 +88,13 @@ if (params.help) {
 
 
 // Gather paired fastq files
+if(params.input_file){
+input_triplet = Channel.fromPath("${params.input_file}")
+			       .splitCsv(header: true, sep: '\t', strip: true)
+			       .map { row -> [row.SM , file(row.pair1), file(row.pair2), file(row.junction) ] }
+                   .groupTuple(by: 0)
+                   .map { row -> [row[0] , row[1], row[2], row[3][0] ] }
+}else{
    readPairs = Channel.fromFilePairs(params.input_folder +"/*{${params.suffix1},${params.suffix2}}" +'.'+ params.fastq_ext)
                       .map {  row -> [ row[0], row[1][0], row[1][1] ] }
 
@@ -103,9 +115,9 @@ if (params.help) {
    }else{
 	println "Do not gather STAR junction files; STAR will be used for alignment"
  	input_triplet = readPairs.map { pairs -> [ pairs[0],pairs[1], pairs[2], 'NO_FILE' ] }
+    }
 }
 
-
 process STAR_Fusion {
 	cpus params.cpu
 	memory params.mem+'G'
@@ -127,7 +139,14 @@ process STAR_Fusion {
 	}else{
 	        SF_junction=" "
 	}
+    input_txt="${file_tag}\t${pair1[0]}\t${pair2[0]}"
+    if(pair1 instanceof List) {
+        for( i = 1; i < pair1.size(); i++){
+	        input_txt=input_txt+"\n${file_tag}\t${pair1[i]}\t${pair2[i]}"
+        }
+    }
     '''
-	!{params.starfusion_path} --genome_lib_dir $PWD/!{CTAT_folder} !{SF_junction} --left_fq !{pair1} --right_fq !{pair2} --output_dir . --FusionInspector validate --denovo_reconstruct --examine_coding_effect --CPU !{params.cpu}
+    echo '!{input_txt}' > input.txt
+	!{params.starfusion_path} --genome_lib_dir $PWD/!{CTAT_folder} !{SF_junction} --samples_file input.txt --output_dir . --FusionInspector validate --denovo_reconstruct --examine_coding_effect --CPU !{params.cpu}
     '''
-}
+}