v1.0.1

CHANGELOG.md

@@ -3,6 +3,21 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.0.1 - []
+
+### `Fixed`
+
+- [#4](https://github.com/nf-core/marsseq/issues/4) - Fix AWS testing with s3 bucket
+- missing zenodo in `lib/`
+- added credit and provided short MARS-seq description
+
+## v1.0.0 - [21-06-2023]
+
+### `Dependencies`
+
+- Bump minimal Nextflow version to 23.04.0
+- sync with template 2.8
+
 ## v1.0dev - [date]
 
 Initial release of nf-core/marsseq, created with the [nf-core](https://nf-co.re/) template.

README.md

@@ -12,8 +12,7 @@
 
 ## Introduction
 
-**nf-core/marsseq** is a bioinformatics pipeline for MARS-seq v2.0 preprocessing pipeline. As an additional work we have developed custom set of scripts to run velocity inference using `StarSolo`.
-We do so by converting the raw reads into 10X v2 format.
+**nf-core/marsseq** is a bioinformatics single-cell preprocessing pipeline for MARS-seq v2.0 experiments. MARS-seq is a plate-based technique that can be combined with FACS in order to study rare populations of cells. On top of the pre-existing pipeline, we have developed an RNA velocity workflow that can be used to study cell dynamics using `StarSolo`. We do so by converting the raw FASTQ reads into 10X v2 format.
 
 ![Workflow](docs/images/workflow.png)
 

bin/demultiplex.pl

@@ -1,4 +1,6 @@
 #!/usr/bin/env perl
+# Adapted source code from
+# https://tanaylab.github.io/old_resources/pages/672.html
 use strict;
 
 if ($#ARGV == 0 and $ARGV[0] eq "--version") {

bin/extract_labels.pl

@@ -1,4 +1,6 @@
 #!/usr/bin/env perl
+# Adapted source code from
+# https://tanaylab.github.io/old_resources/pages/672.html
 use strict;
 
 if ($#ARGV == 0 and $ARGV[0] eq "--version") {

bin/qc_align.r

@@ -1,4 +1,6 @@
 #!/usr/bin/env Rscript
+# Adapted source code from
+# https://tanaylab.github.io/old_resources/pages/672.html
 
 args = commandArgs(trailingOnly = TRUE)
 

bin/qc_batch.r

@@ -1,4 +1,6 @@
 #!/usr/bin/env Rscript
+# Adapted source code from
+# https://tanaylab.github.io/old_resources/pages/672.html
 suppressMessages(library(MASS))
 suppressMessages(library(gplots))
 suppressMessages(library(zoo))

bin/qc_report.r

@@ -1,4 +1,6 @@
 #!/usr/bin/env Rscript
+# Adapted source code from
+# https://tanaylab.github.io/old_resources/pages/672.html
 suppressMessages(library(gplots))
 
 get_stats_per_seq_batch = function(seq_batch) {

lib/WorkflowMain.groovy

@@ -11,9 +11,8 @@ class WorkflowMain {
     //
     public static String citation(workflow) {
         return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" +
-            // TODO nf-core: Add Zenodo DOI for pipeline after first release
-            //"* The pipeline\n" +
-            //"  https://doi.org/10.5281/zenodo.XXXXXXX\n\n" +
+            "* The pipeline\n" +
+            "  https://doi.org/10.5281/zenodo.8063539\n\n" +
             "* The nf-core framework\n" +
             "  https://doi.org/10.1038/s41587-020-0439-x\n\n" +
             "* Software dependencies\n" +

modules/local/prepare/main.nf

@@ -17,16 +17,19 @@ process PREPARE {
         'biocontainers/mulled-v2-0bcca2890a3ab7be29a83e813a02d340d6f54660:4cb478c6e57df2ef85ea5f8eae6d717c017962cd-0' }"
 
     input:
-    tuple val(meta), path(reads)
+    path(amp_batches)
+    path(seq_batches)
+    path(well_cells)
     path(gtf)
     path(ercc_regions)
+    tuple val(meta), path(reads)
 
     output:
-    path "amp_batches.txt"      , emit: amp_batches
-    path "gene_intervals.txt"   , emit: gene_intervals
-    path "seq_batches.txt"      , emit: seq_batches
-    path "wells_cells.txt"      , emit: wells_cells
-    path "versions.yml"         , emit: versions
+    path "amp_batches.txt"   , emit: amp_batches
+    path "gene_intervals.txt", emit: gene_intervals
+    path "seq_batches.txt"   , emit: seq_batches
+    path "wells_cells.txt"   , emit: wells_cells
+    path "versions.yml"      , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -35,9 +38,9 @@ process PREPARE {
     """
     prepare_pipeline.py \\
         --batch ${meta.id} \\
-        --amp_batches ${meta.amp_batches} \\
-        --seq_batches ${meta.seq_batches} \\
-        --well_cells ${meta.well_cells} \\
+        --amp_batches $amp_batches \\
+        --seq_batches $seq_batches \\
+        --well_cells $well_cells \\
         --gtf $gtf \\
         --output .
     cat $ercc_regions >> gene_intervals.txt

nextflow.config

@@ -226,7 +226,7 @@ manifest {
     description     = """MARS-seq v2 preprocessing pipeline"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '1.0.0'
+    version         = '1.0.0dev'
     doi             = ''
 }
 

subworkflows/local/prepare_pipeline.nf

@@ -8,20 +8,30 @@ include { FASTP_SPLIT } from '../../modules/local/fastp/split/main'
 
 workflow PREPARE_PIPELINE {
     take:
-    batches       // channel: [ val(meta), [ reads ] ]
+    amp_batches   // channel: amp_batch
+    seq_batches   // channel: seq_batch
+    well_cells    // channel: well_cells
     gtf           // channel: gtf
     ercc_regions  // channel: ercc_regions
+    reads         // channel: [ val(meta), [ reads ] ]
 
     main:
     ch_reads = Channel.empty()
     ch_versions = Channel.empty()
 
     // convert XLS metadata into txt format
-    PREPARE ( batches, gtf, ercc_regions )
+    PREPARE (
+        amp_batches,
+        seq_batches,
+        well_cells,
+        gtf,
+        ercc_regions,
+        reads
+    )
     ch_versions = ch_versions.mix(PREPARE.out.versions)
 
     // split fastq reads by predefined number of reads per fastq file
-    ch_reads = FASTP_SPLIT ( batches ).reads
+    ch_reads = FASTP_SPLIT ( reads ).reads
     ch_versions = ch_versions.mix(FASTP_SPLIT.out.versions)
 
     // verify that split was performed correctly

workflows/marsseq.nf

@@ -98,7 +98,14 @@ workflow MARSSEQ {
     )
     ch_versions = ch_versions.mix(FASTQC.out.versions)
 
-    PREPARE_PIPELINE ( INPUT_CHECK.out.reads, ch_gtf, ch_ercc_regions )
+    PREPARE_PIPELINE (
+        INPUT_CHECK.out.reads.map { it[0].amp_batches },
+        INPUT_CHECK.out.reads.map { it[0].seq_batches },
+        INPUT_CHECK.out.reads.map { it[0].well_cells },
+        ch_gtf,
+        ch_ercc_regions,
+        INPUT_CHECK.out.reads
+    )
     ch_versions = ch_versions.mix(PREPARE_PIPELINE.out.versions)
 
     LABEL_READS (