Merge branch 'cellranger-4.0.0_ref-2020A' into 'develop'

Cellranger 4.0.0 ref 2020 a

See merge request !73

CHANGELOG.md

+# v2.2.0-indev
+**UserFacing**
+* Update cellranger to version 4.0.0
+
+**Background**
+* Add runtime info
+* Make standard (profile) be biohpc AND cluster
+
+*Known Bugs*
+* cellranger mkfastq will not accept spaces in path for run param even if quoted, issue raised on 10XGenomics/cellranger github issue [#31](https://github.com/10XGenomics/cellranger/issues/31)
+    * note: 10x doesn't check github issues, emailed instead
+    * note: pipeline checks for spaces and exits prematurely if found
+* If multiple flowcells (tar'd) files are inputted then there will be multiple fastq's by the same name, currently dealing with that name conflict is not tractable
+    * note: if multiple bcl files are detected then cellranger_count design file is not created
+* If too many (or too large) .tar(.gz) bcl files are placed in one run, aws runs appears to fail possibly due to timeout on staging
+
 # v2.1.5
 **UserFacing**
 * Check Design File for spaces in name and file contents

workflow/main.nf

@@ -32,7 +32,7 @@ bclCount = Channel
   .count()
 
 // Define regular variables
-pipelineVersion = "2.1.5"
+pipelineVersion = "2.2.0-indev"
 name = params.name
 designLocation = Channel
   .fromPath(params.designFile)
@@ -85,8 +85,26 @@ process trackStart {
 }
 
 
-process checkDesignFile {
+log.info """\
+================================
+BICF cellranger_mkfastq Pipeline
+================================
+Run name        : ${params.name}
+bcl             : ${params.bcl}
+Design File     : ${params.designFile}
+Output Directory: ${params.outDir}
+--------------------------------
+Nextflow Version: ${workflow.nextflow.version}
+Pipeline Version: ${pipelineVersion}
+Session ID      : ${workflow.sessionId}
+--------------------------------
+Astrocyte       : ${params.astrocyte}
+CI              : ${params.ci}
+Development     : ${params.dev}
+--------------------------------
+"""
 
+process checkDesignFile {
   tag "${name}"
   module 'python/3.6.1-2-anaconda'
 
@@ -115,14 +133,12 @@ process checkDesignFile {
     echo "${workflow.nextflow.version}" > version_nextflow.txt
     echo "${pipelineVersion}" > version_pipeline.txt
     """
-
 }
 /* nextflow workflow manifest version calls that aren't compatible with Asrcocyte
     echo "${workflow.manifest.version}" > version_pipeline.txt
 */
 
 process untarBCL {  
-
   tag "${tar.simpleName}"
   module 'pigz/2.4'
 
@@ -148,11 +164,10 @@ process untarBCL {
 
 
 process mkfastq {
-
   tag "${bcl.simpleName}"
   publishDir "${outDir}/${task.process}", mode: 'copy', pattern: "{*/outs/**/*.fastq.gz}"
   queue '128GB,256GB,256GBv1,384GB'
-  module 'cellranger/3.1.0:bcl2fastq/2.19.1'
+  module 'cellranger/4.0.0:bcl2fastq/2.19.1'
 
   input:
     file versions_cellrangerScript
@@ -173,21 +188,18 @@ process mkfastq {
     hostname
     ulimit -u 16384
     ulimit -a
-    cellranger mkfastq --id=mkfastq_${bcl.simpleName} --run=${bcl} --csv=${design} --ignore-dual-index ${mask}
+    cellranger mkfastq --id=mkfastq_${bcl.simpleName} --run=${bcl} --csv=${design} ${mask}
     mkdir fq
     mkdir "fq/${bcl.simpleName}"
     find . -name "*.fastq.gz" -exec cp {} fq/${bcl.simpleName}/ \\;
     bash versions_cellranger.sh > version_cellranger.txt
     bash versions_bcl2fastq.sh > version_bcl2fastq.txt
     """
-
 }
 
 
 if (bclCount.value == 1) {
-
   process countDesign {
-
     tag "${name}"
     publishDir "${outDir}/${task.process}/${name}", mode: 'copy'
 
@@ -205,14 +217,11 @@ if (bclCount.value == 1) {
       ulimit -a
       bash countDesign.sh
       """
-
   }
-
 }
 
 
 process fastqc {
-
   tag "${bcl}"
   module 'fastqc/0.11.5:parallel'
 
@@ -235,12 +244,10 @@ process fastqc {
     bash fastqc.sh
     bash versions_fastqc.sh > version_fastqc.txt
     """
-
 }
 
 
 process versions {
-
   tag "${name}"
   module 'python/3.6.1-2-anaconda:cellranger/3.1.0:bcl2fastq/2.19.1:fastqc/0.11.5:pandoc/2.7'
 
@@ -266,12 +273,10 @@ process versions {
     python3 generate_versions.py -f version_*.txt -o versions
     python3 generate_references.py -r ${references} -o references
     """
-
 }
 
 
 process multiqc {
-
   tag "${name}"
   publishDir "${outDir}/${task.process}/${name}", mode: 'copy', pattern: "{multiqc*}"
   module 'multiqc/1.7'
@@ -293,5 +298,4 @@ process multiqc {
     #export LANG=C.UTF-8
     multiqc -c ${multiqcConf} .
     """
-
 }

workflow/nextflow.config

 profiles {
   standard {
     includeConfig 'configs/biohpc.config'
+    includeConfig 'configs/cluster.config'
   }
   biohpc {
     includeConfig 'configs/biohpc.config'
@@ -47,6 +48,6 @@ manifest {
   homePage = 'https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_mkfastq'
   description = 'This pipeline is a wrapper for the cellranger mkfastq tool from 10x Genomics (which uses Illuminas bcl2fastq). It takes bcls and demultiplexes samples from 10x Genomics Single Cell Gene Expression libraries into fastqs.'
   mainScript = 'main.nf'
-  version = '2.1.5'
+  version = '2.2.0-indev'
   nextflowVersion = '>=0.31.0'
 }

workflow/scripts/generate_references.py

-#!/usr/bin/env python
+#!/usr/bin/env python3
 #generate_references.py
 #*
 #* --------------------------------------------------------------------------