diff --git a/README.md b/README.md
index 56f8013b9f27f59938638d738b055a0b11731950..e67ff5c6fa2ec2ad582d8b3b9f6bed26cbdef45e 100755
--- a/README.md
+++ b/README.md
@@ -1,5 +1,9 @@
+|*master*|*develop*|
+|:-:|:-:|
+|[](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count/commits/master)|[](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count/commits/develop)|
+
10x Genomics scRNA-Seq (cellranger) count Pipeline
-========================================
+==================================================
Introduction
------------
@@ -19,13 +23,14 @@ To Run:
* **--fastq**
* path to the fastq location
* R1 and R2 only necessary but can include I2
+ * only fastq's in designFile (see below) are used, not present will be ignored
* eg: **--fastq '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_count/v3s2r100k/\*.fastq.gz'**
* **--designFile**
* path to design file (csv format) location
* column 1 = "Sample"
* column 2 = "fastq_R1"
* column 3 = "fastq_R2"
- * can have repeated "Sample" if there are multiole fastq R1/R2 pairs for the samples
+ * can have repeated "Sample" if there are multiple fastq R1/R2 pairs for the samples
* eg: **--designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_count/v3s2r100k/design.csv'**
* **--genome**
* reference genome
@@ -44,7 +49,7 @@ To Run:
* eg: **--genome 'GRCh38-3.0.0'**
* **--genomeLocationFull**
* path to a custom genome
- * if --genomeLocationFull is used --genome is not necessary and is overwritten
+ * if --genomeLocationFull is used --genome is not necessary and is ignored
* eg. **--genomeLocationFull '/project/apps_database/cellranger/refdata-cellranger-GRCh38-3.0.0'**
* **--expectCells**
* expected number of cells to be detected
@@ -57,11 +62,11 @@ To Run:
* **--forceCells**
* forces filtering of the top number of cells matching this parameter
* 0-10000
- * if --forceCells is used then --expectedCells is not necessary and is overwritten
+ * if --forceCells is used then --expectedCells is not necessary and is ignored
* eg: **--forceCells 10000**
* **--kitVersion**
* the library chemistry version number for the 10x Genomics Gene Expression kit
- * setting to auto will attempt to autodetect from the detected cycle strategy in the fastq's
+ * setting to auto will attempt to autodetect from the detected sequencing strategy in the fastq's
* version numbers are spelled out
* --kitversion is only used if --version (cellranger version) is > 2
* --version (cellranger version) 2.1.1 can only read --kitVersion of two (2)
@@ -69,7 +74,7 @@ To Run:
* *'auto'*
* *'three'*
* *'two'*
- * eg: **--kitVersion 'three'**'
+ * eg: **--kitVersion 'three'**
* **--version**
* cellranger version
* --version (cellranger version) 2.1.1 can only read --kitVersion of two (2)
@@ -91,4 +96,4 @@ To Run:
|---------|------------------------------------|------------------------------------|
| sample1 | pbmc_1k_v2_S1_L001_R1_001.fastq.gz | pbmc_1k_v2_S1_L001_R2_001.fastq.gz |
| sample2 | pbmc_1k_v2_S2_L001_R1_001.fastq.gz | pbmc_1k_v2_S2_L001_R2_001.fastq.gz |
-| sample2 | pbmc_1k_v2_S2_L002_R1_001.fastq.gz | pbmc_1k_v2_S2_L002_R2_001.fastq.gz |
\ No newline at end of file
+| sample2 | pbmc_1k_v2_S2_L002_R1_001.fastq.gz | pbmc_1k_v2_S2_L002_R2_001.fastq.gz |
diff --git a/astrocyte_pkg.yml b/astrocyte_pkg.yml
index 57a83b333141e9056fa00b894bc76e43010ee341..8417664465fb8691f52e97960b6acda0b54594c8 100755
--- a/astrocyte_pkg.yml
+++ b/astrocyte_pkg.yml
@@ -150,16 +150,6 @@ workflow_parameters:
description: |
10x cellranger version.
- - id: feature
- type: select
- default: 'no'
- choices:
- - [ 'no', 'No']
- - [ 'yes', 'Yes']
- required: true
- description: |
- Additional features to count (only used in cellranger version 3+, ignored otherwise).
-
- id: astrocyte
type: select
choices:
diff --git a/docs/index.md b/docs/index.md
index 13cc7d7acfadc63ed5543dac64d6f8725f9faaa6..f03554e1205d0479cf817b898b6e4f49def0554f 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1,5 +1,5 @@
10x Genomics scRNA-Seq (cellranger) count Pipeline
-========================================
+==================================================
Introduction
------------
@@ -24,7 +24,7 @@ To Run:
* column 3 = "fastq_R2"
* can have repeated "Sample" if there are multiole fastq R1/R2 pairs for the samples
* eg: can be downloaded [HERE](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count/blob/8db3e25c13cb1463c2a50e510159c72380ae5826/docs/design.csv)
- * **genome**
+ * **genome**
* Reference species and genome used for alignment and subsequent analysis.
* name of available 10x Gemomics premade reference genomes:
* *'GRCh38-3.0.0'* = Human GRCh38 release 93
@@ -36,30 +36,39 @@ To Run:
* *'hg19_and_mm10-3.0.0'* = Human GRCh37 (hg19) + Mouse GRCm38 (mm19) release 93
* *'hg19_and_mm10-1.2.0'* = Human GRCh37 (hg19) + Mouse GRCm38 (mm19) release 84
* *'ercc92-1.2.0'* = ERCC.92 Spike-In
- * **expect cells**
+ * **expect cells**
* Expected number of recovered cells.
* guides cellranger in it's cutoff for background/low quality cells
* as a guide it doesn't have to be exact
* 0-10000
* if --expextedCells is used then --forceCells is not necessary
* only used if force cells is not entered or set to 0
- * **force cells**
+ * **force cells**
* Force pipeline to use this number of cells, bypassing the cell detection algorithm. Use this if the number of cells estimated by Cell Ranger is not consistent with the barcode rank plot. A value of 0 ignores this option. Any value other than 0 overrides expect-cells.
* 0-10000
* if force cells is used then expected cells is not necessary and is ignored
- * **chemistry version**
+ * **chemistry version**
* 10x single cell gene expression chemistry version (only used in cellranger version 3.x).
* setting to auto will attempt to autodetect from the detected cycle strategy in the fastq's
* chemistry version is only used if cellranger version is > 2.x
* cellranger version 2.1.1 can only read chemistry version less than or equal to two (2)
- * **cellranger version**
+ * **cellranger version**
* 10x cellranger version.
* cellranger version 2.1.1 can only read chemistry version less than or equal to two (2)
* Design example:
-| Sample | fastq_R1 | fastq_R2 |
-|---------|------------------------------------|------------------------------------|
-| sample1 | pbmc_1k_v2_S1_L001_R1_001.fastq.gz | pbmc_1k_v2_S1_L001_R2_001.fastq.gz |
-| sample2 | pbmc_1k_v2_S2_L001_R1_001.fastq.gz | pbmc_1k_v2_S2_L001_R2_001.fastq.gz |
-| sample2 | pbmc_1k_v2_S2_L002_R1_001.fastq.gz | pbmc_1k_v2_S2_L002_R2_001.fastq.gz |
+ | Sample | fastq_R1 | fastq_R2 |
+ |---------|------------------------------------|------------------------------------|
+ | sample1 | pbmc_1k_v2_S1_L001_R1_001.fastq.gz | pbmc_1k_v2_S1_L001_R2_001.fastq.gz |
+ | sample2 | pbmc_1k_v2_S2_L001_R1_001.fastq.gz | pbmc_1k_v2_S2_L001_R2_001.fastq.gz |
+ | sample2 | pbmc_1k_v2_S2_L002_R1_001.fastq.gz | pbmc_1k_v2_S2_L002_R2_001.fastq.gz |
+
+
+
+Credits
+-------
+This worklow is was developed jointly with the [Bioinformatic Core Facility (BICF), Department of Bioinformatics](http://www.utsouthwestern.edu/labs/bioinformatics/)
+
+
+Please cite in publications: Pipeline was developed by BICF from funding provided by **Cancer Prevention and Research Institute of Texas (RP150596)**.
diff --git a/workflow/conf/biohpc.config b/workflow/conf/biohpc.config
index e69f0507b028c493d49bbbada40e051034dc0ac7..6f19408ac80f7855559ccf159dd22afd9241e80b 100755
--- a/workflow/conf/biohpc.config
+++ b/workflow/conf/biohpc.config
@@ -2,20 +2,19 @@ process {
executor = 'slurm'
queue='super'
- // Process specific configuration
- $checkDesignFile {
+ withLabel: checkDesignFile {
module = ['python/3.6.1-2-anaconda']
executor = 'local'
}
- $count211 {
+ withLabel: count211 {
module = ['cellranger/2.1.1']
queue = '128GB,256GB,256GBv1,384GB'
}
- $count301 {
+ withLabel: count301 {
module = ['cellranger/3.0.1']
queue = '128GB,256GB,256GBv1,384GB'
}
- $count302 {
+ withLabel: count302 {
module = ['cellranger/3.0.2']
queue = '128GB,256GB,256GBv1,384GB'
}
diff --git a/workflow/main.nf b/workflow/main.nf
index 3649ddfcc70460d5142e3c39cc3b803396c4fe25..43933ba559205017eec4bb3f8ceb701e460dd95d 100755
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -105,7 +105,7 @@ chemistryParam302 = chemistryParam
process count211 {
queue '128GB,256GB,256GBv1,384GB'
- tag "count211-$sample"
+ tag "$sample"
publishDir "$outDir/${task.process}", mode: 'copy'
@@ -143,7 +143,7 @@ process count211 {
process count301 {
queue '128GB,256GB,256GBv1,384GB'
- tag "count301-$sample"
+ tag "$sample"
publishDir "$outDir/${task.process}", mode: 'copy'
@@ -182,13 +182,13 @@ process count301 {
process count302 {
queue '128GB,256GB,256GBv1,384GB'
- tag "count302-$sample"
+ tag "$sample"
publishDir "$outDir/${task.process}", mode: 'copy'
input:
- set sample, file("${sample}_S1_L00?_R1_001.fastq.gz"), file("${sample}_S1_L00?_R2_001.fastq.gz") from samples302
+ set sample, file("${sample}_S?_L001_R1_001.fastq.gz"), file("${sample}_S?_L001_R2_001.fastq.gz") from samples302
file ref from refLocation302.first()
expectCells302
forceCells302
@@ -217,4 +217,4 @@ process count302 {
cellranger count --id="$sample" --transcriptome="./$ref" --fastqs=. --sample="$sample" --force-cells=$forceCells302 --chemistry="$chemistryParam302"
"""
}
-}
\ No newline at end of file
+}
diff --git a/workflow/main.test.nf b/workflow/main.test.nf
deleted file mode 100644
index 581f1777764f5d67b7dc352d17bb9b3e2e350065..0000000000000000000000000000000000000000
--- a/workflow/main.test.nf
+++ /dev/null
@@ -1,89 +0,0 @@
-#!/usr/bin/env nextflow
-
-// Path to an input file, or a pattern for multiple inputs
-// Note - $baseDir is the location of this workflow file main.nf
-
-// Define Input variables
-params.fastq = "$baseDir/../test_data/*.fastq.gz"
-params.designFile = "$baseDir/../test_data/design.csv"
-params.genome = 'GRCh38-3.0.0'
-params.genomes = []
-params.genomeLocation = params.genome ? params.genomes[ params.genome ].loc ?: false : false
-params.expectCells = 10000
-params.forceCells = 0
-params.kitVersion = '3'
-params.chemistry = []
-params.chemistryParam = params.kitVersion ? params.chemistry[ params.kitVersion ].param ?: false : false
-params.version = '3.0.2'
-params.feature = 'yes'
-params.outDir = "$baseDir/output"
-
-// Define regular variables
-designLocation = Channel
- .fromPath(params.designFile)
- .ifEmpty { exit 1, "design file not found: ${params.designFile}" }
-fastqList = Channel
- .fromPath(params.fastq)
- .flatten()
- .map { file -> [ file.getFileName().toString(), file.toString() ].join("\t") }
- .collectFile(name: 'fileList.tsv', newLine: true)
-refLocation = Channel
- .fromPath(params.genomeLocation+params.genome)
- .ifEmpty { exit 1, "referene not found: ${params.genome}" }
-expectCells = params.expectCells
-forceCells = params.forceCells
-chemistryParam = params.chemistryParam
-version = params.version
-feature = params.feature
-featurechk = feature
-outDir = params.outDir
-
-process checkDesignFile {
-
- publishDir "$outDir/${task.process}", mode: 'copy'
-
- input:
-
- file designLocation
- file fastqList
- featurechk
-
- output:
-
- file("*.checked.csv") into designPaths
-
- script:
-
- """
- python3 $baseDir/scripts/check_design.test.py -d $designLocation -f $fastqList -t "$featurechk"
- """
-}
-
-// Parse design file
-samples = designPaths
- .splitCsv (sep: ',', header: true)
- .map { row -> [ row.Sample, file(row.fastq_R1), file(row.fastq_R2) ] }
- .groupTuple()
- //.subscribe { println it }
-
-// Duplicate variables
-samples.into {
- samples211
- samples301
- samples302
-}
-refLocation.into {
- refLocation211
- refLocation301
- refLocation302
-}
-expectCells211 = expectCells
-expectCells301 = expectCells
-expectCells302 = expectCells
-forceCells211 = forceCells
-forceCells301 = forceCells
-forceCells302 = forceCells
-chemistryParam301 = chemistryParam
-chemistryParam302 = chemistryParam
-feature301 = feature
-feature302 = feature
diff --git a/workflow/scripts/check_design.test.py b/workflow/scripts/check_design.test.py
deleted file mode 100755
index e08f08a2573c9a32c88ce3bdbc3860e5bd179446..0000000000000000000000000000000000000000
--- a/workflow/scripts/check_design.test.py
+++ /dev/null
@@ -1,139 +0,0 @@
-#!/usr/bin/env python3
-
-'''Check if design file is correctly formatted and matches files list.'''
-
-import argparse
-import logging
-import pandas as pd
-
-EPILOG = '''
-For more details:
- %(prog)s --help
-'''
-
-# SETTINGS
-
-logger = logging.getLogger(__name__)
-logger.addHandler(logging.NullHandler())
-logger.propagate = False
-logger.setLevel(logging.INFO)
-
-
-def get_args():
- '''Define arguments.'''
-
- parser = argparse.ArgumentParser(
- description=__doc__, epilog=EPILOG,
- formatter_class=argparse.RawDescriptionHelpFormatter)
-
- parser.add_argument('-d', '--design',
- help="The design file to run QC (tsv format).",
- required=True )
-
- parser.add_argument('-f', '--fastq',
- help="File with list of fastq files (tsv format).",
- required=True )
-
- parser.add_argument('-t', '--feature',
- help="Additional features to count?",
- required=True )
-
- args = parser.parse_args()
- return args
-
-
-def check_design_headers_n(design):
- '''Check if design file conforms to sequencing type.'''
-
- # Default headers
- design_template = [
- 'Sample',
- 'fastq_R1',
- 'fastq_R2']
-
- design_headers = list(design.columns.values)
-
- # Check if headers
- logger.info("Running header check.")
-
- missing_headers = set(design_template) - set(design_headers)
-
- if len(missing_headers) > 0:
- logger.error('Missing column headers: %s', list(missing_headers))
- raise Exception("Missing column headers: %s" % list(missing_headers))
-
- return design
-
-def check_design_headers_y(design):
- '''Check if design file conforms to sequencing type.'''
-
- # Default headers
- design_template = [
- 'Sample',
- 'fastq_R1',
- 'fastq_R2',
- 'library_type']
-
- design_headers = list(design.columns.values)
-
- # Check if headers
- logger.info("Running header check.")
-
- missing_headers = set(design_template) - set(design_headers)
-
- if len(missing_headers) > 0:
- logger.error('Missing column headers: %s', list(missing_headers))
- raise Exception("Missing column headers: %s" % list(missing_headers))
-
- return design
-
-def check_files(design, fastq):
- '''Check if design file has the files found.'''
-
- logger.info("Running file check.")
-
- files = list(design['fastq_R1']) + list(design['fastq_R2'])
-
- files_found = fastq['name']
-
- missing_files = set(files) - set(files_found)
-
- if len(missing_files) > 0:
- logger.error('Missing files from design file: %s', list(missing_files))
- raise Exception("Missing files from design file: %s" %
- list(missing_files))
- else:
- file_dict = fastq.set_index('name').T.to_dict()
-
- design['fastq_R1'] = design['fastq_R1'].apply(lambda x: file_dict[x]['path'])
- design['fastq_R2'] = design['fastq_R2'].apply(lambda x: file_dict[x]['path'])
-
- return design
-
-
-def main():
- args = get_args()
- design = args.design
-
- # Create a file handler
- handler = logging.FileHandler('design.log')
- logger.addHandler(handler)
-
- # Read files as dataframes
- design_df = pd.read_csv(args.design, sep=',')
- fastq_df = pd.read_csv(args.fastq, sep='\t', names=['name', 'path'])
-
- # Check design file
- if args.feature == 'no':
- new_design_df = check_design_headers_n(design_df)
- else:
- new_design_df = check_design_headers_y(design_df)
- #new_design_df[['sample']].to_csv('library.checked.csv', header=True, sep=',', index=False)
-
- check_files(design_df, fastq_df)
- new_design_df.drop('library_type', 1).to_csv('design.checked.csv', header=True, sep=',', index=False)
-
-
-
-if __name__ == '__main__':
- main()