Merge pull request #7 from nf-core/dev

v1.1.1: Update pipeline to nfcore 2.5.1

Author: sguizard

.editorconfig

@@ -8,7 +8,7 @@ trim_trailing_whitespace = true
 indent_size = 4
 indent_style = space
 
-[*.{md,yml,yaml,html,css,scss,js}]
+[*.{md,yml,yaml,html,css,scss,js,cff}]
 indent_size = 2
 
 # These files are edited and tested upstream in nf-core/modules

.github/PULL_REQUEST_TEMPLATE.md

@@ -15,8 +15,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/isos
 
 - [ ] This comment contains a description of changes (with reason).
 - [ ] If you've fixed a bug or added code that should be tested, add tests!
-  - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/isoseq/tree/master/.github/CONTRIBUTING.md)
-  - [ ] If necessary, also make a PR on the nf-core/isoseq _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
+- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/isoseq/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/isoseq _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
 - [ ] Make sure your code lints (`nf-core lint`).
 - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.

.github/workflows/ci.yml

@@ -10,7 +10,6 @@ on:
 
 env:
   NXF_ANSI_LOG: false
-  CAPSULE_LOG: none
 
 jobs:
   test:
@@ -20,27 +19,17 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        # Nextflow versions
-        include:
-          # Test pipeline minimum Nextflow version
-          - NXF_VER: "21.10.3"
-            NXF_EDGE: ""
-          # Test latest edge release of Nextflow
-          - NXF_VER: ""
-            NXF_EDGE: "1"
+        NXF_VER:
+          - "21.10.3"
+          - "latest-everything"
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2
 
       - name: Install Nextflow
-        env:
-          NXF_VER: ${{ matrix.NXF_VER }}
-          # Uncomment only if the edge release is more recent than the latest stable release
-          # See https://github.com/nextflow-io/nextflow/issues/2467
-          # NXF_EDGE: ${{ matrix.NXF_EDGE }}
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
+        uses: nf-core/setup-nextflow@v1
+        with:
+          version: "${{ matrix.NXF_VER }}"
 
       - name: Run pipeline with test data (uLTRA)
         run: |

.github/workflows/linting.yml

@@ -35,22 +35,48 @@ jobs:
       - name: Run Prettier --check
         run: prettier --check ${GITHUB_WORKSPACE}
 
+  PythonBlack:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Check code lints with Black
+        uses: psf/black@stable
+
+      # If the above check failed, post a comment on the PR explaining the failure
+      - name: Post PR comment
+        if: failure()
+        uses: mshick/add-pr-comment@v1
+        with:
+          message: |
+            ## Python linting (`black`) is failing
+
+            To keep the code consistent with lots of contributors, we run automated code consistency checks.
+            To fix this CI test, please run:
+
+            * Install [`black`](https://black.readthedocs.io/en/stable/): `pip install black`
+            * Fix formatting errors in your pipeline: `black .`
+
+            Once you push these changes the test should pass, and you can hide this comment :+1:
+
+            We highly recommend setting up Black in your code editor so that this formatting is done automatically on save. Ask about it on Slack for help!
+
+            Thanks again for your contribution!
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          allow-repeats: false
+
   nf-core:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2
 
       - name: Install Nextflow
-        env:
-          CAPSULE_LOG: none
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
+        uses: nf-core/setup-nextflow@v1
 
       - uses: actions/setup-python@v3
         with:
-          python-version: "3.6"
+          python-version: "3.7"
           architecture: "x64"
 
       - name: Install dependencies

CHANGELOG.md

@@ -3,6 +3,24 @@
 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).
 
+## v1.1.1 - White Hawk [26/09/2022]
+
+Update the pipeline to nf-core 2.5.1, update modules, and fix documentation.
+
+### `Added`
+
+### `Fixed`
+
+- Documentation: Correct aligner option documentation
+
+### `Dependencies`
+
+- Update `samplesheet_check` module
+- Update `dumpsoftwareversion` module
+- Update `MultiQC` module
+
+### `Deprecated`
+
 ## v1.1.0 - Black Crow [12/07/2022]
 
 Improves computation time.

CITATION.cff

@@ -0,0 +1,56 @@
+cff-version: 1.2.0
+message: "If you use `nf-core tools` in your work, please cite the `nf-core` publication"
+authors:
+  - family-names: Ewels
+    given-names: Philip
+  - family-names: Peltzer
+    given-names: Alexander
+  - family-names: Fillinger
+    given-names: Sven
+  - family-names: Patel
+    given-names: Harshil
+  - family-names: Alneberg
+    given-names: Johannes
+  - family-names: Wilm
+    given-names: Andreas
+  - family-names: Ulysse Garcia
+    given-names: Maxime
+  - family-names: Di Tommaso
+    given-names: Paolo
+  - family-names: Nahnsen
+    given-names: Sven
+title: "The nf-core framework for community-curated bioinformatics pipelines."
+version: 2.4.1
+doi: 10.1038/s41587-020-0439-x
+date-released: 2022-05-16
+url: https://github.com/nf-core/tools
+prefered-citation:
+  type: article
+  authors:
+    - family-names: Ewels
+      given-names: Philip
+    - family-names: Peltzer
+      given-names: Alexander
+    - family-names: Fillinger
+      given-names: Sven
+    - family-names: Patel
+      given-names: Harshil
+    - family-names: Alneberg
+      given-names: Johannes
+    - family-names: Wilm
+      given-names: Andreas
+    - family-names: Ulysse Garcia
+      given-names: Maxime
+    - family-names: Di Tommaso
+      given-names: Paolo
+    - family-names: Nahnsen
+      given-names: Sven
+  doi: 10.1038/s41587-020-0439-x
+  journal: nature biotechnology
+  start: 276
+  end: 278
+  title: "The nf-core framework for community-curated bioinformatics pipelines."
+  issue: 3
+  volume: 38
+  year: 2020
+  url: https://dx.doi.org/10.1038/s41587-020-0439-x

README.md

@@ -1,19 +1,14 @@
 # ![nf-core/isoseq](docs/images/nf-core-isoseq_logo_light.png#gh-light-mode-only) ![nf-core/isoseq](docs/images/nf-core-isoseq_logo_dark.png#gh-dark-mode-only)
 
-[![GitHub Actions CI Status](https://github.com/nf-core/isoseq/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/isoseq/actions?query=workflow%3A%22nf-core+CI%22)
-[![GitHub Actions Linting Status](https://github.com/nf-core/isoseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/isoseq/actions?query=workflow%3A%22nf-core+linting%22)
-[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?logo=Amazon%20AWS)](https://nf-co.re/isoseq/results)
-[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8)](https://doi.org/10.5281/zenodo.XXXXXXX)
+[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/isoseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
 
 [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A521.10.3-23aa62.svg)](https://www.nextflow.io/)
-[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?logo=anaconda)](https://docs.conda.io/en/latest/)
-[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?logo=docker)](https://www.docker.com/)
-[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg)](https://sylabs.io/docs/)
+[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
+[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)
+[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)
 [![Launch on Nextflow Tower](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Nextflow%20Tower-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/isoseq)
 
-[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23isoseq-4A154B?logo=slack)](https://nfcore.slack.com/channels/isoseq)
-[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?logo=twitter)](https://twitter.com/nf_core)
-[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?logo=youtube)](https://www.youtube.com/c/nf-core)
+[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23isoseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/isoseq)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)
 
 ## Introduction
 
@@ -54,7 +49,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 3. Download the pipeline and test it on a minimal dataset with a single command:
 
-   ```console
+   ```bash
    nextflow run nf-core/isoseq -profile test,YOURPROFILE --outdir <OUTDIR>
    ```
 
@@ -67,7 +62,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 4. Start running your own analysis!
 
-   ```console
+   ```bash
    nextflow run nf-core/isoseq --input samplesheet.csv --outdir <OUTDIR> --genome <GENOME NAME (e.g. GRCh37)> --primers <PRIMER FASTA> -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
    ```
 

assets/email_template.txt

@@ -6,7 +6,6 @@
                                         `._,._,'
   nf-core/isoseq v${version}
 ----------------------------------------------------
-
 Run Name: $runName
 
 <% if (success){

bin/check_samplesheet.py

@@ -11,7 +11,6 @@
 from collections import Counter
 from pathlib import Path
 
-
 logger = logging.getLogger()
 
 
@@ -79,11 +78,13 @@ def validate_and_transform(self, row):
 
     def _validate_sample(self, row):
         """Assert that the sample name exists and convert spaces to underscores."""
-        assert len(row[self._sample_col]) > 0, "Sample input is required."
+        if len(row[self._sample_col]) <= 0:
+            raise AssertionError("Sample input is required.")
         # Sanitize samples slightly.
         row[self._sample_col] = row[self._sample_col].replace(" ", "_")
 
     def _validate_first(self, row):
+
         """Assert that the BAM entry is non-empty and has the right format."""
         assert len(row[self._first_col]) > 0, "The BAM file is required."
         self._validate_format(row[self._first_col])
@@ -152,7 +153,7 @@ def sniff_format(handle):
     handle.seek(0)
     sniffer = csv.Sniffer()
     if not sniffer.has_header(peek):
-        logger.critical(f"The given sample sheet does not appear to contain a header.")
+        logger.critical("The given sample sheet does not appear to contain a header.")
         sys.exit(1)
     dialect = sniffer.sniff(peek)
     return dialect
@@ -191,7 +192,8 @@ def check_samplesheet(file_in, file_out):
 
         # Validate the existence of the expected header columns.
         if not required_columns.issubset(reader.fieldnames):
-            logger.critical(f"The sample sheet **must** contain the column headers: {', '.join(required_columns)}.")
+            req_cols = ", ".join(required_columns)
+            logger.critical(f"The sample sheet **must** contain these column headers: {req_cols}.")
             sys.exit(1)
 
         # Validate each row.

conf/base.config

@@ -24,6 +24,11 @@ process {
     //        If possible, it would be nice to keep the same label naming convention when
     //        adding in your local modules too.
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
+    withLabel:process_single {
+        cpus   = { check_max( 1                  , 'cpus'    ) }
+        memory = { check_max( 6.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 4.h  * task.attempt, 'time'    ) }
+    }
     withLabel:process_low {
         cpus   = { check_max( 2     * task.attempt, 'cpus'    ) }
         memory = { check_max( 12.GB * task.attempt, 'memory'  ) }

docs/usage.md

@@ -12,7 +12,7 @@ This pipeline has been designed to analyse several samples or sequencing runs at
 
 You will need to create a samplesheet with information about the samples you would like to analyze before running the pipeline. Use `--input` parameter to specify its location.
 
-```console
+```bash
 --input '[path to samplesheet file]'
 ```
 
@@ -66,24 +66,24 @@ The reference genome annotation in `GTF` format is required if `uLTRA` aligner i
 Two aligners are available. The `uLTRA` aligner helps to detect small exons with the help of reference genome. However if no annotation is available for your genome you can use minimap2.
 
 ```console
---fasta '[ultra,minimap2]'
+--aligner '[ultra,minimap2]'
 ```
 
 ## Running the pipeline
 
 The typical command for running the pipeline is as follows:
 
-```console
+```bash
 nextflow run nf-core/isoseq --input samplesheet.csv --outdir <OUTDIR> --primers primers.fasta --fasta Gallus_gallus.GRCg6a.dna.toplevel.fasta -profile singularity
 ```
 
 This will launch the pipeline with the `singularity` configuration profile. See below for more information about profiles.
 
 Note that the pipeline will create the following files in your working directory:
 
-```console
+```bash
 work                # Directory containing the nextflow working files
-<OUTIDR>            # Finished results in specified location (defined with --outdir, default = 'results')
+<OUTDIR>            # Finished results in specified location (defined with --outdir)
 .nextflow_log       # Log file from Nextflow
 # Other nextflow hidden files, eg. history of pipeline runs and old logs.
 ```
@@ -92,7 +92,7 @@ work                # Directory containing the nextflow working files
 
 When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline:
 
-```console
+```bash
 nextflow pull nf-core/isoseq
 ```
 
@@ -268,6 +268,6 @@ Some HPC setups also allow you to run nextflow within a cluster job submitted yo
 In some cases, the Nextflow Java virtual machines can start to request a large amount of memory.
 We recommend adding the following line to your environment to limit this (typically in `~/.bashrc` or `~./bash_profile`):
 
-```console
+```bash
 NXF_OPTS='-Xms1g -Xmx4g'
 ```

lib/WorkflowIsoseq.groovy

@@ -10,6 +10,7 @@ class WorkflowIsoseq {
     public static void initialise(params, log) {
         genomeExistsError(params, log)
 
+
         if (!params.fasta) {
             log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file."
             System.exit(1)
@@ -41,9 +42,7 @@ class WorkflowIsoseq {
         yaml_file_text        += "data: |\n"
         yaml_file_text        += "${summary_section}"
         return yaml_file_text
-    }
-
-    //
+    }//
     // Exit pipeline if incorrect --genome key provided
     //
     private static void genomeExistsError(params, log) {