Docs, CI, copyright update

.github/workflows/ci.yml

@@ -1,5 +1,5 @@
 name: nf-core CI
-# This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
+
 on:
   push:
     branches:
@@ -18,14 +18,16 @@ concurrency:
 jobs:
   test:
     name: Run pipeline with test data
-    # Only run on push if this is the nf-core dev branch (merged PRs)
-    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'sanger-tol/readmapping') }}"
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         NXF_VER:
           - "22.10.1"
           - "latest-everything"
+        short_aligner:
+          - bwamem2
+          - minimap2
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v3
@@ -36,8 +38,5 @@ jobs:
           version: "${{ matrix.NXF_VER }}"
 
       - name: Run pipeline with test data
-        # You can customise CI pipeline run tests as required
-        # For example: adding multiple test runs with different parameters
-        # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results --short_aligner ${{ matrix.short_aligner }}

.github/workflows/linting.yml

@@ -19,7 +19,7 @@ jobs:
       - uses: actions/setup-node@v3
 
       - name: Install editorconfig-checker
-        run: npm install -g editorconfig-checker
+        run: npm install -g editorconfig-checker@3.0.2
 
       - name: Run ECLint check
         run: editorconfig-checker -exclude README.md $(find .* -type f | grep -v '.git\|.py\|.md\|json\|yml\|yaml\|html\|css\|work\|.nextflow\|build\|nf_core.egg-info\|log.txt\|Makefile')

LICENSE

@@ -1,6 +1,8 @@
 MIT License
 
-Copyright (c) @priyanka-surana
+Copyright (c) 2022-2024 Genome Research Ltd.
+except `bin/filter_five_end.pl`:
+Copyright (c) 2017 Arima Genomics, Inc.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

assets/schema_input.json

@@ -22,7 +22,7 @@
             "datafile": {
                 "format": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Data file for reads cannot contain spaces and must have extension 'cram', 'bam', '.fq.gz' or '.fastq.gz'",
+                "errorMessage": "Data file for reads cannot contain spaces and must have extension 'cram', 'bam', '.fq.gz' or '.fastq.gz'. Note that FASTQ inputs should be interleaved if paired-end.",
                 "meta": ["datafile"]
             },
             "library": {

docs/usage.md

@@ -42,7 +42,7 @@ sample1_T5,pacbio,pacbio2.bam,pacbio2
 | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `sample`   | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (\_).                                                 |
 | `datatype` | Type of sequencing data. Must be one of `hic`, `Illumina`, `pacbio`, or `ont`.                                                                                                                                                        |
-| `datafile` | Full path to read data file. Must be `bam`, `cram`, `fastq.gz` or `fq.gz` for `Illumina` and `HiC`. Must be `bam`, `fastq.gz` or `fq.gz` for `pacbio`. Must be `fastq.gz` or `fq.gz` for `ont`.                                       |
+| `datafile` | Data file for reads cannot contain spaces and must have extension 'cram', 'bam', '.fq.gz' or '.fastq.gz'. Note that FASTQ inputs should be interleaved if paired-end.                                                                 |
 | `library`  | (Optional) The library value is a unique identifier which is assigned to read group (`@RG`) ID. If the library name is not specified, the pipeline will auto-create library name using the data filename provided in the samplesheet. |
 
 An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.