diff --git a/.gitignore b/.gitignore
index 712b98cf9f5267ff9fc6896f7def336e52514f40..f153fc296faef39fd8ce3be544fdf32b414a32c5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -306,7 +306,7 @@ $RECYCLE.BIN/
/output/*
pipeline_trace*.txt*
.nextflow*.log*
-report.html*
+report*.html*
timeline*.html*
*~
diff --git a/astrocyte_pkg.yml b/astrocyte_pkg.yml
index a27056d44d172e22051b5c258439c42c0e08f617..e96cb4e5a55717bed78238ee74c712b4f27826ac 100755
--- a/astrocyte_pkg.yml
+++ b/astrocyte_pkg.yml
@@ -137,7 +137,7 @@ workflow_parameters:
- [ 'two', '2']
required: true
description: |
- 10x single cell gene expression chemistry version (only used in cellranger version 2.x).
+ 10x single cell gene expression chemistry version (only used in cellranger version 3.x).
- id: version
type: select
@@ -151,10 +151,11 @@ workflow_parameters:
10x cellranger version.
- id: astrocyte
- type: string
- default: 'true'
+ type: select
+ choices:
+ - [ 'true', 'true' ]
required: true
- regex: 'true'
+ default: 'true'
description: |
Ensure configuraton for astrocyte.
diff --git a/docs/design.csv b/docs/design.csv
new file mode 100755
index 0000000000000000000000000000000000000000..df082a46726ff6b863ff945de21cf1bad419028f
--- /dev/null
+++ b/docs/design.csv
@@ -0,0 +1,4 @@
+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
diff --git a/docs/index.md b/docs/index.md
index 654bef8befdc01d28ebb410ae0fbf775d3c10dfb..13cc7d7acfadc63ed5543dac64d6f8725f9faaa6 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1,3 +1,65 @@
-# Astrocyte CellRanger 10x Workflow Package
+10x Genomics scRNA-Seq (cellranger) count Pipeline
+========================================
-## Workflow SOP
+Introduction
+------------
+
+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.
+
+The pipeline uses Nextflow, a bioinformatics workflow tool.
+
+To Run:
+-------
+
+* Workflow parameters:
+ * **fastq**
+ * Pairs (read1 and read2) of fastq.gz files from a sequencing of 10x single-cell expereiment. Index fastq not required.
+ * REQUIRED
+ * R1 and R2 only necessary
+ * **design file**
+ * A design file listing sample, corresponding read1 filename, corresponding read2 filename. There can be multiple rows with the same sample name, if there are multiple fastq's for that sample.
+ * REQUIRED
+ * 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
+ * eg: can be downloaded [HERE](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count/blob/8db3e25c13cb1463c2a50e510159c72380ae5826/docs/design.csv)
+ * **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
+ * *'GRCh38-1.2.0'* = Human GRCh38 release 84
+ * *'hg19-3.0.0'* = Human GRCh37 (hg19) release 87
+ * *'hg19-1.2.0'* = Human GRCh37 (hg19) release 84
+ * *'mm10-3.0.0'* = Human GRCm38 (mm10) release 93
+ * *'mm10-3.0.0'* = Human GRCm38 (mm10) release 84
+ * *'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**
+ * 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 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**
+ * 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**
+ * 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 |
diff --git a/workflow/main.nf b/workflow/main.nf
index ec068ca61a42f82f99c9587c48e64e75ae89f0a1..82d30dfbfb02aae0ba5cbaadac9fb0a8b9302ccc 100755
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -14,16 +14,12 @@ params.forceCells = 0
params.kitVersion = 'three'
params.version = '3.0.2'
-params.astrocyte = 'false'
+params.astrocyte = false
params.outDir = "$baseDir/output"
// Assign variables if astrocyte
-if (params.astrocyte == 'false') {
- params.genomes = []
- params.genomeLocation = params.genome ? params.genomes[ params.genome ].loc ?: false : false
- params.chemistry = []
- params.chemistryParam = params.kitVersion ? params.chemistry[ params.kitVersion ].param ?: false : false
-} else if (params.astrocyte == 'true') {
+if (params.astrocyte) {
+ print("Running under astrocyte")
params.genomeLocation = '/project/apps_database/cellranger/refdata-cellranger-'
if (params.kitVersion == "one") {
params.chemistryParam ='SC3Pv1'
@@ -34,6 +30,12 @@ if (params.astrocyte == 'false') {
} else {
params.chemistryParam = 'auto'
}
+} else {
+ params.genomes = []
+ params.genomeLocation = params.genome ? params.genomes[ params.genome ].loc ?: false : false
+ params.chemistry = []
+ params.chemistryParam = params.kitVersion ? params.chemistry[ params.kitVersion ].param ?: false : false
+
}
params.genomeLocationFull = params.genomeLocation+params.genome