Merge branch 'Buzz_Lightyear' into 'develop'

Buzz lightyear

See merge request !75

.gitlab-ci.yml

@@ -3,15 +3,18 @@ before_script:
   - module load python/3.6.1-2-anaconda
   - pip install --user pytest-pythonpath==0.7.1 pytest-cov==2.5.1
   - module load nextflow/20.01.0
-  - module load singularity/3.0.2
-  - mkdir -p test_data/simple1
-  - mkdir -p test_data/simple2
-  - ln -sfn /project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/* test_data/simple1/
-  - ln -sfn /project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple2/* test_data/simple2/
+  - module load singularity/3.5.3
+  - mkdir -p test_data/cellranger1bcl
+  - mkdir -p test_data/cellranger2bcl
+  - mkdir -p test_data/spaceranger1bcl
+  - ln -sfn /project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/cellranger1bcl/* test_data/cellranger1bcl/
+  - ln -sfn /project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/cellranger2bcl/* test_data/cellranger2bcl/
+  - ln -sfn /project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/spaceranger1bcl/* test_data/spaceranger1bcl/
 
 stages:
   - astrocyte
-  - simple
+  - cellranger
+  - spaceranger
 
 astrocyte_check:
   stage: astrocyte
@@ -24,11 +27,11 @@ astrocyte_check:
     when:
       - always
 
-simple_1FC:
-  stage: simple
+cellranger1bcl:
+  stage: cellranger
   script:
-    - nextflow run workflow/main.nf -profile biohpc,cluster --bcl "test_data/simple1/*.tar.gz" --designFile "test_data/simple1/cellranger-tiny-bcl-simple-1_2_0.csv" --ci true
-    ##- pytest -m simple1
+    - nextflow run workflow/main.nf -profile biohpc,cluster --ranger "cellranger" --bcl "test_data/cellranger1bcl/*.tar.gz" --designFile "test_data/cellranger1bcl/cellranger-tiny-bcl-simple-1_2_0.csv" --ci true
+    ##- pytest -m cellranger1bcl
   artifacts:
     name: "$CI_JOB_NAME"
     when: always
@@ -41,11 +44,28 @@ simple_1FC:
     when:
       - always
 
-simple_2FC:
-  stage: simple
+cellranger2bcl:
+  stage: cellranger
   script:
-    - nextflow run workflow/main.nf -profile biohpc,cluster --bcl "test_data/simple2/*.tar.gz" --designFile "test_data/simple2/cellranger-tiny-bcl-simple-1_2_0.csv" --ci true
-    ##- pytest -m simple2
+    - nextflow run workflow/main.nf -profile biohpc,cluster --ranger "cellranger" --bcl "test_data/cellranger2bcl/*.tar.gz" --designFile "test_data/cellranger2bcl/cellranger-tiny-bcl-simple-1_2_0.csv" --ci true
+    ##- pytest -m cellranger2bcl
+  artifacts:
+    name: "$CI_JOB_NAME"
+    when: always
+    paths:
+      - .nextflow.log
+      - workflow/output/multiqc/run/multiqc_report.html
+    expire_in: 2 days
+  retry:
+    max: 0
+    when:
+      - always
+
+spaceranger1bcl:
+  stage: spaceranger
+  script:
+    - nextflow run workflow/main.nf -profile biohpc,cluster --ranger "spaceranger" --bcl "test_data/spaceranger1bcl/*.tar.gz" --designFile "test_data/spaceranger1bcl/spaceranger-tiny-bcl-simple-1.0.0.csv" --ci true
+    ##- pytest -m spaceranger1bcl
   artifacts:
     name: "$CI_JOB_NAME"
     when: always

CHANGELOG.md

 # v3.0.0
 **UserFacing**
-* 
+* Add flag to select cellranger vs spaceranger
+* Adjust versions to take into account multiple 10x-Ranger softwares
+* Remove countDesign process
+* Spaceranger V1.2.0 update
 
 **Background**
-* 
+* Update scripts to reflect spaceranger or cellranger input
+* Update CI to include simple3 and add simple3 tests for later pytest use (commented out for all simple CI)
+* Add simple3 to test data folder
+* redo channels to include multple rangers
+* Rename simple1 and 2 to cellranger1 and 2 and simple3 to spaceranger1
+* Redo Versioning for rangers to ouput correctly
 
 *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)

README.md

@@ -4,13 +4,13 @@
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.2652611.svg)](https://doi.org/10.5281/zenodo.2652611)
 
-10x Genomics scRNA-Seq (cellranger) mkfastq Pipeline
+10x Genomics scRNA-Seq (cellranger/spaceranger) mkfastq Pipeline
 ==================================================
 
 Introduction
 ------------
 
-This pipeline is a wrapper for the cellranger mkfastq tool from 10x Genomics (which uses Illumina's bcl2fastq). It takes demultiplexes samples from 10x Genomics Single Cell Gene Expression libraries into fastqs.
+This pipeline is a wrapper for the cellranger or spaceranger mkfastq tool from 10x Genomics (which uses Illumina's bcl2fastq). It takes demultiplexes samples from 10x Genomics Single Cell Gene Expression libraries into fastqs.
 
 FastQC is run on the resulting fastq and those reports and bcl2fastq reports are collated with the MultiQC tool.
 
@@ -42,15 +42,19 @@ To Run:
 * Available parameters:
   * **-profile**
     * what environments to run on, available: `biohpc`, `local`, `cluster`, `aws`, `ondemand`, `spot`
-    * eg: **-profile biohpc,cluster** to run on BioHPC in cluster mode
-    * eg: **-profile aws,ondemand** to run on AWS on a on-demand queue
+    * eg: `-profile biohpc,cluster` to run on BioHPC in cluster mode
+    * eg: `-profile aws,ondemand` to run on AWS on a on-demand queue
   * **--name**
     * run name, puts outputs in a directory with this name
-    * eg: **--name 'test'**
+    * eg: `--name 'test'`
+  * **--ranger**
+    * select the 10x ranger being run.
+    * eg: `--ranger 'cellranger'` to run cellranger mkfastq
+    * eg: `--ranger 'spaceranger'` to run spaceranger mkfastq
   * **--bcl**
     * base call files (tarballed [*.tar] +/- gunzipping [*.tar.gz] from a sequencing of 10x single-cell expereiment, supports pigr parallelization)
     * there can be multiple basecall files, but they all will be demultiplexed by the same design file
-    * eg: ```--bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-1_2_0.tar.gz'```
+    * eg: `--bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-1_2_0.tar.gz'`
   * **--designFile**
     * path to design file (csv format) location
     * column 1 = "Lane" (number of lanes to demultiplex, **\*** for all lanes)
@@ -60,16 +64,16 @@ To Run:
     * [Current sample barcode IDs](https://s3-us-west-2.amazonaws.com/10x.files/supp/cell-exp/chromium-shared-sample-indexes-plate.csv)
     * can have repeated "Sample" if there are multiple fastq R1/R2 pairs for the samples
     * can be downloaded [HERE](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_mkfastq/blob/master/docs/design.csv)
-    * eg: ```--designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple/cellranger-tiny-bcl-simple-1_2_0.csv'```
+    * eg: `--designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple/cellranger-tiny-bcl-simple-1_2_0.csv'`
   * **--mask**
     * add a base mask if the sequencing strategy doesn't match the requirements of 10x Genomics
-    * eg: **--mask '--use-bases-mask=Y\*,I8n\*,n\*,Y\*'**
+    * eg: `--mask '--ignore-dual-index --use-bases-mask=Y\*,I8n\*,n\*,Y\*'`
   * **--outDir**
     * optional output directory for run
-    * eg: ```--outDir 'test'```
+    * eg: `--outDir 'test'`
 * FULL EXAMPLE:
   ```
-  nextflow run workflow/main.nf -profile biohpc,cluster --name 'test' --bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-1_2_0.tar.gz' --designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-simple-1_2_0.csv' --outDir 'test'
+  nextflow run workflow/main.nf -profile biohpc,cluster --name 'test' --ranger 'cellranger' --bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-1_2_0.tar.gz' --designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-simple-1_2_0.csv' --outDir 'test'
   ```
 * Design example:
 

astrocyte_pkg.yml

@@ -17,7 +17,7 @@ title: 'BICF CellRanger mkfastq Workflow'
 # A summary of the workflow package in plain text
 description: |
   This is a workflow package for the BICF/Strand Lab CellRanger mkfastq workflow system.
-  It implements 10x CellRanger mkfastq analysis workflow application.
+  It implements 10x CellRanger/SpaceRanger mkfastq analysis workflow application.
 
 # -----------------------------------------------------------------------------
 # DOCUMENTATION
@@ -39,7 +39,7 @@ documentation_files:
 # A list of cluster environment modules that this workflow requires to run.
 # Specify versioned module names to ensure reproducability.
 workflow_modules:
-  - 'singularity/3.0.2'
+  - 'singularity/3.5.3'
 
 # A list of parameters used by the workflow, defining how to present them,
 # options etc in the web interface. For each parameter:
@@ -99,6 +99,16 @@ workflow_parameters:
     description: |
       Ensure configuraton for astrocyte.
 
+  - id: ranger
+    type: select
+    choices:
+      - [ 'CellRanger', 'cellranger' ]
+      - [ 'SpaceRanger', 'spaceranger' ]
+    required: true
+    default: 'CellRanger'
+    description: |
+      CellRanger or SpaceRanger 10x data.
+
 
 # -----------------------------------------------------------------------------
 # SHINY APP CONFIGURATION

docs/index.md

-10x Genomics scRNA-Seq (cellranger) mkfastq Pipeline
+10x Genomics scRNA-Seq mkfastq Pipeline
 ====================================================
 
 Introduction
 ------------
 
-This pipeline is a wrapper for the cellranger mkfastq tool from 10x Genomics (which uses Illumina's bcl2fastq). It takes bcl's and demultiplexes samples from 10x Genomics Single Cell Gene Expression libraries into fastqs.
+This pipeline is a wrapper for the various ranger mkfastq tools from 10x Genomics (which uses Illumina's bcl2fastq). It takes bcl's and demultiplexes samples from 10x Genomics Single Cell Gene Expression libraries into fastqs.
 
 FastQC is run on the resulting fastq and those reports and bcl2fastq reports are collated with the MultiQC tool.
 

docs/references.md

@@ -12,6 +12,9 @@
 4. **cellranger**:
   * 10x Genomics cellranger mkfastq [https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/mkfastq](https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/mkfastq)
 
+6. **spaceranger**:
+  * 10x Genomics spaceranger mkfastq [https://support.10xgenomics.com/spatial-gene-expression/software/pipelines/latest/using/mkfastq](https://support.10xgenomics.com/spatial-gene-expression/software/pipelines/latest/using/mkfastq)
+
 5. **bcl2fastq**:
   * Ilumina's bcl2fastq [https://support.illumina.com/sequencing/sequencing_software/bcl2fastq-conversion-software.html](https://support.illumina.com/sequencing/sequencing_software/bcl2fastq-conversion-software.html)
 
@@ -19,4 +22,4 @@
   * fastqc [https://www.bioinformatics.babraham.ac.uk/projects/fastqc/](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
 7. **MultiQc**:
-  * Ewels P., Magnusson M., Lundin S. and Käller M. 2016. MultiQC: Summarize analysis results for multiple tools and samples in a single report. Bioinformatics 32(19): 3047–3048. doi:[10.1093/bioinformatics/btw354](https://dx.doi.org/10.1093/bioinformatics/btw354)
\ No newline at end of file
+  * Ewels P., Magnusson M., Lundin S. and Käller M. 2016. MultiQC: Summarize analysis results for multiple tools and samples in a single report. Bioinformatics 32(19): 3047–3048. doi:[10.1093/bioinformatics/btw354](https://dx.doi.org/10.1093/bioinformatics/btw354)

workflow/configs/aws.config

@@ -16,7 +16,11 @@ process {
   withName:checkDesignFile {
     cpus = 4
   }
-  withName:mkfastq {
+  withName:cellranger_mkfastq {
+    cpus = 6
+    memory = '2 GB'
+  }
+  withName:spaceranger_mkfastq {
     cpus = 6
     memory = '2 GB'
   }

workflow/configs/cluster.config

@@ -12,11 +12,11 @@ process {
   withName:untarBCL {
     queue = 'super'
   }
-  withName:mkfastq {
+  withName:cellranger_mkfastq {
     queue = '128GB,256GB,256GBv1,384GB'
   }
-  withName:countDesign {
-    executor = 'local'
+  withName:spaceranger_mkfastq {
+    queue = '128GB,256GB,256GBv1,384GB'
   }
   withName:fastqc {
     queue = 'super'

workflow/configs/multiqc_config.yaml

@@ -5,12 +5,12 @@ custom_logo_title: 'Bioinformatics Core Facility'
 
 report_header_info:
     - Contact E-mail: 'bicf@utsouthwestern.edu'
-    - Application Type: 'cellranger_mkfastq'
+    - Application Type: '10x-ranger_mkfastq'
     - Department: 'Bioinformatic Core Facility, Department of Bioinformatics'
 
 
 # Title to use for the report.
-title: BICF CellRanger MKfastq Analysis Report
+title: BICF 10x-Ranger MKfastq Analysis Report
 
 report_comment: >
   This report has been generated by the <a href="https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_mkfastq"

workflow/main.nf

@@ -18,6 +18,7 @@ main.nf
 
 // Define input variables
 params.name = "run"
+params.ranger = "cellranger"
 params.bcl = "${baseDir}/../test_data/simple1/*.tar.gz"
 params.designFile = "${baseDir}/../test_data/single1/cellranger-tiny-bcl-simple-1_2_0.csv"
 params.mask = ""
@@ -34,6 +35,7 @@ bclCount = Channel
 // Define regular variables
 pipelineVersion = "3.0.0_indev"
 name = params.name
+ranger = params.ranger
 designLocation = Channel
   .fromPath(params.designFile)
   .ifEmpty { exit 1, "design file not found: ${params.designFile}" }
@@ -43,13 +45,13 @@ outDir = params.outDir
 // Define script files
 check_designScript = Channel.fromPath("$baseDir/scripts/check_design.py")
 untarBCLScript = Channel.fromPath("$baseDir/scripts/untarBCL.sh")
-countDesignScript = Channel.fromPath("$baseDir/scripts/countDesign.sh")
 fastqcScript = Channel.fromPath("$baseDir/scripts/fastqc.sh")
 versionsScript = Channel.fromPath("$baseDir/scripts/generate_versions.py")
 referencesScript = Channel.fromPath("$baseDir/scripts/generate_references.py")
 versions_pythonScript = Channel.fromPath("$baseDir/scripts/versions_python.sh")
 //versions_pigzScript = Channel.fromPath("$baseDir/scripts/versions_pigz.sh")
 versions_cellrangerScript = Channel.fromPath("$baseDir/scripts/versions_cellranger.sh")
+versions_spacerangerScript = Channel.fromPath("$baseDir/scripts/versions_spaceranger.sh")
 versions_bcl2fastqScript = Channel.fromPath("$baseDir/scripts/versions_bcl2fastq.sh")
 versions_fastqcScript = Channel.fromPath("$baseDir/scripts/versions_fastqc.sh")
 
@@ -74,6 +76,7 @@ process trackStart {
       "sessionId": "${workflow.sessionId}", \
       "pipeline": "cellranger_mkfastq", \
       "pipelineVersion": "${pipelineVersion}", \
+      "10x-ranger": ${params.ranger}, \
       "start": "${workflow.start}", \
       "astrocyte": ${params.astrocyte}, \
       "status": "started", \
@@ -90,6 +93,7 @@ log.info """\
 BICF cellranger_mkfastq Pipeline
 ================================
 Run name        : ${params.name}
+Ranger          : ${params.ranger}
 bcl             : ${params.bcl}
 Design File     : ${params.designFile}
 Output Directory: ${params.outDir}
@@ -163,7 +167,12 @@ process untarBCL {
 }
 
 
-process mkfastq {
+versions_bcl2fastqScript.into { versions_bcl2fastqScriptCell; versions_bcl2fastqScriptSpace }
+bclPaths.into { bclPathsCell; bclPathsSpace }
+designPaths.into { designPathsCell; designPathsSpace }
+
+
+process cellranger_mkfastq {
   tag "${bcl.simpleName}"
   publishDir "${outDir}/${task.process}", mode: 'copy', pattern: "{*/outs/**/*.fastq.gz}"
   queue '128GB,256GB,256GBv1,384GB'
@@ -171,17 +180,20 @@ process mkfastq {
 
   input:
     file versions_cellrangerScript
-    file versions_bcl2fastqScript
-    each file(bcl) from bclPaths.collect()
-    file design from designPaths
+    file versions_bcl2fastqScriptCell
+    each file(bcl) from bclPathsCell.collect()
+    file design from designPathsCell
 
   output:
-    file("fq/${bcl.simpleName}/*.fastq.gz") into fastqPaths
-    val "${bcl.simpleName}" into bclName
+    file("fq/${bcl.simpleName}/*.fastq.gz") into fastqPathsCell
+    val "${bcl.simpleName}" into bclNameCell
     file("**/outs/**/*.fastq.gz") into cellrangerCount mode flatten
-    file("**/outs/fastq_path/Stats/*") into bqcPaths
-    file("version_cellranger.txt") into version_cellranger
-    file("version_bcl2fastq.txt") into version_bcl2fastq
+    file("**/outs/fastq_path/Stats/*") into bqcPathsCell
+    file("version_Cellranger.txt") into version_cellranger
+    file("version_bcl2fastq.txt") into version_bcl2fastqCell
+
+  when:
+    ranger == "cellranger"
 
   script:
     """
@@ -192,35 +204,76 @@ process mkfastq {
     mkdir fq
     mkdir "fq/${bcl.simpleName}"
     find . -name "*.fastq.gz" -exec cp {} fq/${bcl.simpleName}/ \\;
-    bash versions_cellranger.sh > version_cellranger.txt
+    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'
+process spaceranger_mkfastq {
+  tag "${bcl.simpleName}"
+  publishDir "${outDir}/${task.process}", mode: 'copy', pattern: "{*/outs/**/*.fastq.gz}"
+  queue '128GB,256GB,256GBv1,384GB'
+  module 'spaceranger/1.2.0:bcl2fastq/2.19.1'
 
-    input:
-      file countDesignScript
-      file fastqs from cellrangerCount.collect()
-      file design from designCount
+  input:
+    file versions_spacerangerScript
+    file versions_bcl2fastqScriptSpace
+    each file(bcl) from bclPathsSpace.collect()
+    file design from designPathsSpace
+
+  output:
+    file("fq/${bcl.simpleName}/*.fastq.gz") into fastqPathsSpace
+    val "${bcl.simpleName}" into bclNameSpace
+    file("**/outs/**/*.fastq.gz") into spacerangerCount mode flatten
+    file("**/outs/fastq_path/Stats/*") into bqcPathsSpace
+    file("version_Spaceranger.txt") into version_spaceranger
+    file("version_bcl2fastq.txt") into version_bcl2fastqSpace
 
-    output:
-      file("Cellranger_Count_Design.csv") into CountDesign
+  when:
+    ranger == "spaceranger"
 
-    script:
-      """
-      hostname
-      ulimit -a
-      bash countDesign.sh
-      """
-  }
+  script:
+    """
+    hostname
+    ulimit -u 16384
+    ulimit -a
+    spaceranger 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_spaceranger.sh > version_Spaceranger.txt
+    bash versions_bcl2fastq.sh > version_bcl2fastq.txt
+    """
 }
 
 
+Channel
+  .empty()
+  .mix(fastqPathsCell,fastqPathsSpace)
+  .set { fastqPaths }
+Channel
+  .empty()
+  .mix(bclNameCell,bclNameSpace)
+  .set { bclName }
+Channel
+  .empty()
+  .mix(cellrangerCount,spacerangerCount)
+  .set { rangerCount }
+Channel
+  .empty()
+  .mix(bqcPathsCell,bqcPathsSpace)
+  .set { bqcPaths }
+Channel
+  .empty()
+  .mix(version_cellranger,version_spaceranger)
+  .set { version_ranger }
+Channel
+  .empty()
+  .mix(version_bcl2fastqCell,version_bcl2fastqSpace)
+  .set { version_bcl2fastq }
+
+
 process fastqc {
   tag "${bcl}"
   module 'fastqc/0.11.5:parallel'
@@ -249,7 +302,7 @@ process fastqc {
 
 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'
+  module 'python/3.6.1-2-anaconda:pandoc/2.7'
 
   input:
   file versionsScript
@@ -258,7 +311,7 @@ process versions {
   file version_nextflow
   file version_python
   //file version_pigz
-  file version_cellranger
+  file version_ranger
   file version_bcl2fastq
   file version_fastqc
   file references

workflow/scripts/generate_versions.py

@@ -25,12 +25,12 @@ logger.addHandler(logging.NullHandler())
 logger.propagate = False
 logger.setLevel(logging.INFO)
 
+
 SOFTWARE_REGEX = {
     'Pipeline': ['version_pipeline.txt', r"(\S+)"],
     'Nextflow': ['version_nextflow.txt', r"(\S+)"],
     'python': ['version_python.txt', r"(\S+)"],
     #'pigz': ['version_pigz.txt', r"(\S+)"],
-    'cellranger': ['version_cellranger.txt', r"(\S+)"],
     'bcl2fastq': ['version_bcl2fastq.txt', r"(\S+)"],
     'fastqc': ['version_fastqc.txt', r"(\S+)"],
 }
@@ -56,6 +56,18 @@ def get_args():
     return args
 
 
+def rangerType(files):
+    '''Determine Type of Ranger being used'''
+
+    for fname in files:
+            ranger = re.findall("version_(.*)ranger.txt", fname)
+            if not ranger: continue
+            ranger_type = ranger[0]+"ranger"
+            SOFTWARE_REGEX[ranger_type] = [fname, r"(\S+)"]
+
+    return ranger_type
+
+
 def check_files(files):
     '''Check if version files are found.'''
 
@@ -77,12 +89,14 @@ def main():
 
     out_filename = output + '_mqc.yaml'
 
+    ranger_type = rangerType(files)
+
     results = OrderedDict()
     results['Pipeline'] = '<span style="color:#999999;\">N/A</span>'
     results['Nextflow'] = '<span style="color:#999999;\">N/A</span>'
     results['python'] = '<span style="color:#999999;\">N/A</span>'
     #results['pigz'] = '<span style="color:#999999;\">N/A</span>'
-    results['cellranger'] = '<span style="color:#999999;\">N/A</span>'
+    results[ranger_type] = '<span style="color:#999999;\">N/A</span>'
     results['bcl2fastq'] = '<span style="color:#999999;\">N/A</span>'
     results['fastqc'] = '<span style="color:#999999;\">N/A</span>'
 

workflow/scripts/versions_cellranger.sh

@@ -6,4 +6,4 @@
 #* --------------------------------------------------------------------------
 #*
 
-cellranger mkfastq --version | grep 'cellranger mkfastq ' | sed 's/.*(\(.*\))/\1/'
\ No newline at end of file
+cellranger mkfastq --version | grep 'cellranger mkfastq ' | sed 's/.*-\(.*\))/\1/'

workflow/scripts/countDesign.sh → workflow/scripts/versions_spaceranger.sh

 #!/bin/bash
-#countDesign.sh
+#versions_spaceranger.sh
 #*
 #* --------------------------------------------------------------------------
 #* Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_mkfastq/blob/develop/LICENSE)
 #* --------------------------------------------------------------------------
 #*
 
-fastqs=($(ls *.fastq.gz))
-design=$(ls *.csv)
-sample=$(cat ${design} | tail -n +2 | cut -d ',' -f2)
-
-echo "Sample,fastq_R1,fastq_R2" > Cellranger_Count_Design.csv;
-
-for i in ${sample};
-do
-  for j in $(seq 1 ${#fastqs[@]});
-  do
-    if [[ ${fastqs[${j}-1]} == *_I* ]]; then
-      continue
-    elif [[ ${fastqs[${j}-1]} == *${i}* && ${fastqs[${j}]} == *${i}* ]]; then
-      echo "${i},${fastqs[${j}-1]},${fastqs[${j}]}" >> Cellranger_Count_Design.csv
-    fi
-  done
-done
+spaceranger mkfastq --version | grep 'spaceranger mkfastq ' | sed 's/.*-\(.*\))/\1/'

workflow/tests/test_mkfastq.py

@@ -12,13 +12,17 @@ from io import StringIO
 import os
 
 test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
-		'/../output/mkfastq/'
+		'/../output/'
 
-@pytest.mark.simple1
-def test_simple1_mkfastq():
-    assert os.path.exists(os.path.join(test_output_path, 'cellranger-tiny-bcl-1_2_0', 'outs'))
+@pytest.mark.cellranger1bcl
+def test_cellranger1bcl_mkfastq():
+    assert os.path.exists(os.path.join(test_output_path, 'mkfastq', 'cellranger-tiny-bcl-1_2_0', 'outs'))
 
-@pytest.mark.simple2
-def test_simple2_mkfastq():
-    assert os.path.exists(os.path.join(test_output_path, 'cellranger-tiny-bcl-1_2_0-1', 'outs'))
-    assert os.path.exists(os.path.join(test_output_path, 'cellranger-tiny-bcl-1_2_0-2', 'outs'))
\ No newline at end of file
+@pytest.mark.cellranger2bcl
+def test_cellranger2bcl_mkfastq():
+    assert os.path.exists(os.path.join(test_output_path, 'mkfastq', 'cellranger-tiny-bcl-1_2_0-1', 'outs'))
+    assert os.path.exists(os.path.join(test_output_path, 'mkfastq', 'cellranger-tiny-bcl-1_2_0-2', 'outs'))
+
+@pytest.mark.spaceranger1bcl
+def test_spaceranger1bcl_mkfastq():
+    assert os.path.exists(os.path.join(test_output_path, 'spaceranger_mkfastq', 'mkfastq_spaceranger-tiny-bcl-1', 'outs'))

workflow/tests/test_multiqc.py

@@ -14,10 +14,14 @@ import os
 test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
                 '/../output/multiqc/run/'
 
-@pytest.mark.simple1
-def test_simple1_multiqc():
+@pytest.mark.cellranger1bcl
+def test_cellranger1bcl_multiqc():
     assert os.path.exists(os.path.join(test_output_path, 'multiqc_report.html'))
 
-@pytest.mark.simple2
-def test_simple2_multiqc():
-    assert os.path.exists(os.path.join(test_output_path, 'multiqc_report.html'))
\ No newline at end of file
+@pytest.mark.cellranger2bcl
+def test_cellranger2bcl_multiqc():
+    assert os.path.exists(os.path.join(test_output_path, 'multiqc_report.html'))
+
+@pytest.mark.spaceranger1bcl
+def test_spaceranger1bcl_multiqc():
+    assert os.path.exists(os.path.join(test_output_path, 'multiqc_report.html'))