Merge branch '38-add.5prime' into 'develop'

Resolve "Add 3':5' param"

Closes #38

See merge request !60

.gitlab-ci.yml

@@ -22,7 +22,7 @@ stages:
 astrocyte_check:
   stage: astrocyte
   script:
-    - astrocyte_cli check ../cellranger_count
+    - astrocyte_cli check .
   artifacts:
     expire_in: 2 days
   retry:
@@ -40,7 +40,7 @@ simple_1:
       - develop
       - master
   script:
-  - nextflow run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v3s1r500/*.fastq.gz" --designFile "test_data/hu.v3s1r500/design.csv" --genome 'GRCh38-3.0.0' --kitVersion 'three' --version '3.1.0' -with-tower
+  - nextflow -q run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v3s1r500/*.fastq.gz" --designFile "test_data/hu.v3s1r500/design.csv" --genome 'GRCh38-3.0.0' --kitVersion '3GEXv3' --version '3.1.0'
   - pytest -m count310
   artifacts:
     name: "$CI_JOB_NAME"
@@ -65,7 +65,7 @@ simple_2:
       - master
       - tags
   script:
-  - nextflow run workflow/main.nf -profile biohpc,cluster --fastq "test_data/mu.v3s1r500/*.fastq.gz" --designFile "test_data/mu.v3s1r500/design.csv" --genome 'mm10-3.0.0' --kitVersion 'three' --version '3.1.0' -with-tower
+  - nextflow -q run workflow/main.nf -profile biohpc,cluster --fastq "test_data/mu.v3s1r500/*.fastq.gz" --designFile "test_data/mu.v3s1r500/design.csv" --genome 'mm10-3.0.0' --kitVersion '3GEXv3' --version '3.1.0'
   - pytest -m count310
   artifacts:
     name: "$CI_JOB_NAME"
@@ -89,7 +89,7 @@ detailed_1:
     refs:
       - tags
   script:
-  - nextflow run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v3s2r10k/*.fastq.gz" --designFile "test_data/hu.v3s2r10k/design.csv" --genome 'GRCh38-3.0.0' --kitVersion 'auto' --version '3.1.0' -with-tower
+  - nextflow -q run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v3s2r10k/*.fastq.gz" --designFile "test_data/hu.v3s2r10k/design.csv" --genome 'GRCh38-3.0.0' --kitVersion 'auto' --version '3.1.0'
   - pytest -m count310
   artifacts:
     name: "$CI_JOB_NAME"
@@ -114,7 +114,7 @@ detailed_2:
     refs:
       - tags
   script:
-  - nextflow run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v3s2r10k/*.fastq.gz" --designFile "test_data/hu.v3s2r10k/design.csv" --genome 'GRCh38-3.0.0' --kitVersion 'auto' --version '3.0.2' -with-tower
+  - nextflow -q run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v3s2r10k/*.fastq.gz" --designFile "test_data/hu.v3s2r10k/design.csv" --genome 'GRCh38-3.0.0' --kitVersion 'auto' --version '3.0.2'
   - pytest -m count302
   artifacts:
     name: "$CI_JOB_NAME"
@@ -138,7 +138,7 @@ detailed_3:
     refs:
       - tags
   script:
-  - nextflow run workflow/main.nf -profile biohpc,cluster --fastq "test_data/mu.v3s2r10k/*.fastq.gz" --designFile "test_data/mu.v3s2r10k/design.csv" --genome 'mm10-3.0.0' --kitVersion 'three' --version '3.0.1' -with-tower
+  - nextflow -q run workflow/main.nf -profile biohpc,cluster --fastq "test_data/mu.v3s2r10k/*.fastq.gz" --designFile "test_data/mu.v3s2r10k/design.csv" --genome 'mm10-3.0.0' --kitVersion 'three' --version '3.0.1'
   - pytest -m count301
   artifacts:
     name: "$CI_JOB_NAME"
@@ -162,7 +162,7 @@ detailed_4:
     refs:
       - tags
   script:
-  - nextflow run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v2s2r10k/*.fastq.gz" --designFile "test_data/hu.v2s2r10k/design.csv" --genome 'GRCh38-1.2.0' --kitVersion 'two' --version '2.1.1' -with-tower
+  - nextflow -q run workflow/main.nf -profile biohpc,cluster --fastq "test_data/hu.v2s2r10k/*.fastq.gz" --designFile "test_data/hu.v2s2r10k/design.csv" --genome 'GRCh38-1.2.0' --kitVersion 'two' --version '2.1.1'
   - pytest -m count211
   artifacts:
     name: "$CI_JOB_NAME"

CHANGELOG.md

-# v1.2.1 (in development)
+# v2.0.0 (in development)
 **User Facing**
 * Check Design File for spaces in name and file contents
 * Attempt to preven thredding error (which appears to only happen on 256GBv1 nodes)
+* Add option for 5' GEX chemistry
 
 **Background**
 * Add Nextflow Tower integration into CI (GHH's profile)
 * Add new layered config folders, including prepare for awsifying
+* Do not rely on astrocyte for final param settings
 
 *Known Bugs*
+* Running in CLI: to set --fastq path of file/s needs to be in quotes
 
 # v1.2.0
 **User Facing**

README.md

@@ -77,9 +77,10 @@ To Run:
     * --version (cellranger version) 2.1.1 can only read --kitVersion of two (2)
     * options:
         * *'auto'*
-        * *'three'*
-        * *'two'*
-    * eg: **--kitVersion 'three'**
+        * *'3GEXv3'*
+        * *'3GEXv2'*
+        * *'5GEX'*
+    * eg: **--kitVersion '3GEXv3'**
   * **--version**
     * cellranger version
     * --version (cellranger version) 2.1.1 can only read --kitVersion of two (2)
@@ -94,7 +95,7 @@ To Run:
     * eg: **--outDir 'test'**
 * FULL EXAMPLE:
   ```
-  nextflow run workflow/main.nf --fastq '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_count/hu.v3s2r10k/*.fastq.gz' --designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_count/hu.v3s2r10k/design.csv' --genome 'GRCh38-3.0.0' --kitVersion 'three' --version '3.1.0' --outDir 'test'
+  nextflow run workflow/main.nf --fastq '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_count/hu.v3s2r10k/*.fastq.gz' --designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_count/hu.v3s2r10k/design.csv' --genome 'GRCh38-3.0.0' --kitVersion '3GEXv3' --version '3.1.0' --outDir 'test'
   ```
 * Design example:
 

astrocyte_pkg.yml

@@ -136,8 +136,9 @@ workflow_parameters:
     default: 'auto'
     choices:
       - ['auto', 'Auto Detect']
-      - ['three', '3']
-      - ['two', '2']
+      - ['3GEXv3', '3prime GEX v3 (3prime Gene Expression)']
+      - ['3GEXv2', '3prime GEX v2 (3prime Gene Expression)']
+      - ['5GEX', '5prime GEX Auto (5prime Gene Expression)']
     required: true
     description: |
       10x single cell gene expression chemistry version (only used in cellranger version 3.x).

cleanup.sh

+rm *.out
+rm pipeline_trace*.txt*
+rm report*.html*
+rm timeline*.html*
+rm .nextflow*.log*
+rm -r .nextflow/
+rm -r work/

workflow/conf/biohpc.config

@@ -37,14 +37,17 @@ params {
     'auto' {
       param = 'auto'
     }
-    'one' {
+    '3GEXv1' {
       param = 'SC3Pv1'
     }
-   'two' {
+   '3GEXv2' {
       param = 'SC3Pv2'
     }
-   'three' {
+   '3GEXv3' {
       param = 'SC3Pv3'
     }
+   '5GEX' {
+      param = 'fiveprime'
+    }
   }
-}
\ No newline at end of file
+}

workflow/conf/biohpc_cluster.config → workflow/conf/cluster.config

 process {
   executor = 'slurm'
-  queue = 'super'
+  queue = '32GB'
   clusterOptions = '--hold'
 
   withLabel: checkDesignFile {
     module = ['python/3.6.1-2-anaconda']
-    executor = 'local'
   }
   withLabel: count211 {
     module = ['cellranger/2.1.1']
@@ -25,10 +24,8 @@ process {
   }
   withLabel: versions {
     module = ['python/3.6.1-2-anaconda','pandoc/2.7','multiqc/1.7']
-    executor = 'local'
   }
   withLabel: multiqc {
     module = ['multiqc/1.7']
-    executor = 'local'
   }
-}
\ No newline at end of file
+}

workflow/conf/biohpc_local.config → workflow/conf/local.config

@@ -22,4 +22,4 @@ process {
   withLabel: multiqc {
     module = ['multiqc/1.7']
   }
-}
\ No newline at end of file
+}

workflow/main.nf

@@ -13,16 +13,17 @@ params.name = "run"
 params.fastq = "${baseDir}/../test_data/*.fastq.gz"
 params.designFile = "${baseDir}/../test_data/design.csv"
 params.genome = 'GRCh38-3.0.0'
+params.genomeLocation = '/project/apps_database/cellranger/refdata-cellranger-'
 params.expectCells = 10000
 params.forceCells = 0
-params.kitVersion = 'three'
+params.kitVersion = '3GEXv3'
 params.version = '3.1.0'
 params.astrocyte = false
 params.outDir = "${baseDir}/output"
 params.multiqcConf = "${baseDir}/conf/multiqc_config.yaml"
 params.references = "${baseDir}/../docs/references.md"
 
-if (params.kitVersion == "three" && params.version == '2.1.1') {
+if (params.kitVersion == "3GEXv3" && params.version == '2.1.1') {
   print("Cellranger Version 2.1.1 requires kitVersion 2")
   System.exit(32)	
 }
@@ -338,7 +339,6 @@ metricsSummary = metricsSummary211.mix(metricsSummary301, metricsSummary302, met
 process multiqc {
 
   tag "${name}"
-  queue 'super'
   publishDir "${outDir}/${task.process}/${name}", mode: 'copy'
   module 'multiqc/1.7'
 
@@ -358,4 +358,4 @@ process multiqc {
     multiqc -c ${multiqcConf} .
     """
 
-}
\ No newline at end of file
+}

workflow/nextflow.config

@@ -3,10 +3,10 @@ profiles {
     includeConfig 'conf/biohpc.config'
   }
   local {
-    includeConfig 'conf/biohpc_local.config'
+    includeConfig 'conf/local.config'
   }
   cluster {
-    includeConfig 'conf/biohpc_cluster.config'
+    includeConfig 'conf/cluster.config'
   }
   aws {
     includeConfig 'conf/aws.config'
@@ -38,6 +38,6 @@ manifest {
   homePage = 'https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count'
   description = 'This pipeline is a wrapper for the cellranger count tool from 10x Genomics. It takes fastq files from 10x Genomics Single Cell Gene Expression libraries, performs alignment, filtering, barcode counting, and UMI counting. It uses the Chromium cellular barcodes to generate gene-barcode matrices, determine clusters, and perform gene expression analysis.'
   mainScript = 'main.nf'
-  version = 'v1.2.1_indev'
+  version = 'v2.0.0_indev'
   nextflowVersion = '>=0.31.0'
-}
\ No newline at end of file
+}