Merge pull request #813 from drpatelh/updates

Update modules in pipeline

Author: drpatelh

CHANGELOG.md

@@ -3,7 +3,12 @@
 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).
 
-## [Unpublished Version / DEV]
+## [[3.7](https://github.com/nf-core/rnaseq/releases/tag/3.7)] - 2022-04-29
+
+### :warning: Major enhancements
+
+- Updated default STAR version to latest available (`2.7.10a`; see [#808](https://github.com/nf-core/rnaseq/issues/808]))
+- Vanilla Linux Docker container changed from `biocontainers/biocontainers:v1.2.0_cv1` to `ubuntu:20.04` to fix issues observed on GCP (see [#764](https://github.com/nf-core/rnaseq/issues/764]))
 
 ### Enhancements & fixes
 
@@ -13,9 +18,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#799](https://github.com/nf-core/rnaseq/issues/799)] - Issue with using `--retain_unpaired` with the `FASTQC_UMITOOLS_TRIMGALORE:TRIMGALORE` module
 - [[#802](https://github.com/nf-core/rnaseq/issues/802)] - `--bam_csi_index` error generated if `--skip_alignment` specified
 - [[#808](https://github.com/nf-core/rnaseq/issues/808)] - Auto-detect usage of Illumina iGenomes reference
+- [[#814](https://github.com/nf-core/rnaseq/issues/814)] - Use decimal values for `--min_mapped_reads`
 - Updated pipeline template to [nf-core/tools 2.3.2](https://github.com/nf-core/tools/releases/tag/2.3.2)
 
-### Parameters
+### Software dependencies
+
+Note, since the pipeline is now using Nextflow DSL2, each process will be run with its own [Biocontainer](https://biocontainers.pro/#/registry). This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference.
+
+| Dependency  | Old version | New version |
+| ----------- | ----------- | ----------- |
+| `samtools`  | 1.14        | 1.15.1      |
+| `star`      | 2.6.1d      | 2.7.10a     |
+| `stringtie` | 2.1.7       | 2.2.1       |
+
+> **NB:** Dependency has been **updated** if both old and new version information is present.
+> **NB:** Dependency has been **added** if just the new version information is present.
+> **NB:** Dependency has been **removed** if version information isn't present.
 
 ## [[3.6](https://github.com/nf-core/rnaseq/releases/tag/3.6)] - 2022-03-04
 

README.md

@@ -22,6 +22,12 @@ On release, automated continuous integration tests run the pipeline on a [full-s
 
 The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community!
 
+## Online videos
+
+A short talk about the history, current status and functionality on offer in this pipeline was given by Harshil Patel ([@drpatelh](https://github.com/drpatelh)) on [8th February 2022](https://nf-co.re/events/2022/bytesize-32-nf-core-rnaseq) as part of the nf-core/bytesize series.
+
+You can find numerous talks on the [nf-core events page](https://nf-co.re/events) from various topics including writing pipelines/modules in Nextflow DSL2, using nf-core tooling, running nf-core pipelines as well as more generic content like contributing to Github. Please check them out!
+
 ## Pipeline summary
 
 The SRA download functionality has been removed from the pipeline (`>=3.2`) and ported to an independent workflow called [nf-core/fetchngs](https://nf-co.re/fetchngs). You can provide `--nf_core_pipeline rnaseq` when running nf-core/fetchngs to download and auto-create a samplesheet containing publicly available samples that can be accepted directly as input by this pipeline.

assets/multiqc_config.yml

@@ -81,7 +81,7 @@ sp:
     fn: "meta_info.json"
 
   preseq:
-    fn: "*.ccurve.txt"
+    fn: "*.lc_extrap.txt"
 
   samtools/stats:
     fn: "*.stats"

conf/modules.config

@@ -455,7 +455,7 @@ if (!params.skip_alignment) {
 
     if (!params.skip_stringtie) {
         process {
-            withName: 'STRINGTIE' {
+            withName: 'STRINGTIE_STRINGTIE' {
                 ext.args   = [
                     '-v',
                     params.stringtie_ignore_gtf ? '' : '-e'

docs/output.md

@@ -563,7 +563,7 @@ See [dupRadar docs](https://www.bioconductor.org/packages/devel/bioc/vignettes/d
 <summary>Output files</summary>
 
 - `<ALIGNER>/preseq/`
-  - `*.ccurve.txt`: Preseq expected future yield file.
+  - `*.lc_extrap.txt`: Preseq expected future yield file.
 - `<ALIGNER>/preseq/log/`
   - `*.command.log`: Standard error output from command.
 

modules.json

@@ -13,10 +13,10 @@
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
             "custom/getchromsizes": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "213403187932dbbdd936a04474cc8cd8abae7a08"
             },
             "fastqc": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "49b18b1639f4f7104187058866a8fab33332bdfe"
             },
             "gffread": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
@@ -25,7 +25,7 @@
                 "git_sha": "9aadd9a6d3f5964476582319b3a1c54a3e3fe7c9"
             },
             "hisat2/align": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773"
             },
             "hisat2/build": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
@@ -34,19 +34,19 @@
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
             "picard/markduplicates": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "49b18b1639f4f7104187058866a8fab33332bdfe"
             },
             "preseq/lcextrap": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "7111e571cc5b6069de4673cd6165af680f17b4d7"
             },
             "qualimap/rnaseq": {
                 "git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046"
             },
             "rsem/calculateexpression": {
-                "git_sha": "f0800157544a82ae222931764483331a81812012"
+                "git_sha": "1b5d3f5ac2ae61ee35dece20a2aeb8018b6438ce"
             },
             "rsem/preparereference": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "1b5d3f5ac2ae61ee35dece20a2aeb8018b6438ce"
             },
             "rseqc/bamstat": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
@@ -79,25 +79,25 @@
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
             "samtools/flagstat": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773"
             },
             "samtools/idxstats": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773"
             },
             "samtools/index": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773"
             },
             "samtools/sort": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773"
             },
             "samtools/stats": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773"
             },
             "sortmerna": {
                 "git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046"
             },
             "stringtie/stringtie": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                "git_sha": "6d88f2da8cc5d586456e801b535cc4213e0fa2f7"
             },
             "subread/featurecounts": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"

modules/local/star_align.nf

@@ -39,8 +39,8 @@ process STAR_ALIGN {
     def prefix = task.ext.prefix ?: "${meta.id}"
 
     // Note: 2.7X indices incompatible with AWS iGenomes so use older STAR version
-    conda_str = "bioconda::star=2.7.9a bioconda::samtools=1.13 conda-forge::gawk=5.1.0"
-    container_id = 'mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:a7908dfb0485a80ca94e4d17b0ac991532e4e989-0'
+    conda_str = "bioconda::star=2.7.10a bioconda::samtools=1.15.1 conda-forge::gawk=5.1.0"
+    container_id = 'mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0'
     if (is_aws_igenome) {
         conda_str = "bioconda::star=2.6.1d bioconda::samtools=1.10 conda-forge::gawk=5.1.0"
         container_id = 'mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0'

modules/local/star_genomegenerate.nf

@@ -24,8 +24,8 @@ process STAR_GENOMEGENERATE {
     def args_list = args.tokenize()
 
     // Note: 2.7X indices incompatible with AWS iGenomes so use older STAR version
-    conda_str = "bioconda::star=2.7.9a bioconda::samtools=1.13 conda-forge::gawk=5.1.0"
-    container_id = 'mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:a7908dfb0485a80ca94e4d17b0ac991532e4e989-0'
+    conda_str = "bioconda::star=2.7.10a bioconda::samtools=1.15.1 conda-forge::gawk=5.1.0"
+    container_id = 'mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0'
     if (is_aws_igenome) {
         conda_str = "bioconda::star=2.6.1d bioconda::samtools=1.10 conda-forge::gawk=5.1.0"
         container_id = 'mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0'