Merge pull request #59 from PlantandFoodResearch/dev

Candidate for 0.4.0

.devcontainer/devcontainer.json

@@ -0,0 +1,20 @@
+{
+    "name": "nfcore",
+    "image": "nfcore/gitpod:latest",
+    "remoteUser": "gitpod",
+    "runArgs": ["--privileged"],
+
+    // Configure tool-specific properties.
+    "customizations": {
+        // Configure properties specific to VS Code.
+        "vscode": {
+            // Set *default* container specific settings.json values on container create.
+            "settings": {
+                "python.defaultInterpreterPath": "/opt/conda/bin/python"
+            },
+
+            // Add the IDs of extensions you want installed when the container is created.
+            "extensions": ["ms-python.python", "ms-python.vscode-pylance", "nf-core.nf-core-extensionpack"]
+        }
+    }
+}

.editorconfig

@@ -8,7 +8,7 @@ trim_trailing_whitespace = true
 indent_size = 4
 indent_style = space
 
-[*.{md,yml,yaml,html,css,scss,js,cff}]
+[*.{md,yml,yaml,html,css,scss,js}]
 indent_size = 2
 
 # These files are edited and tested upstream in nf-core/modules
@@ -18,43 +18,34 @@ end_of_line = unset
 insert_final_newline = unset
 trim_trailing_whitespace = unset
 indent_style = unset
-indent_size = unset
-
 [/subworkflows/nf-core/**]
 charset = unset
 end_of_line = unset
 insert_final_newline = unset
 trim_trailing_whitespace = unset
 indent_style = unset
+
+[/assets/email*]
 indent_size = unset
 
-# These files are edited and tested upstream in pfr/modules
-[/modules/pfr/**]
+# ignore python and markdown
+[*.{py,md}]
+indent_style = unset
+
+# These files are edited and tested upstream in gallvp/modules,subworkflows
+[/modules/gallvp/**]
 charset = unset
 end_of_line = unset
 insert_final_newline = unset
 trim_trailing_whitespace = unset
 indent_style = unset
-indent_size = unset
 
-[/subworkflows/pfr/**]
+[/subworkflows/gallvp/**]
 charset = unset
 end_of_line = unset
 insert_final_newline = unset
 trim_trailing_whitespace = unset
 indent_style = unset
-indent_size = unset
-
-[/assets/email*]
-indent_size = unset
-
-# ignore Readme
-[README.md]
-indent_style = unset
-
-# ignore python
-[*.{py}]
-indent_style = unset
 
 # ignore perl
 [*.{pl,pm}]

.gitattributes

@@ -0,0 +1,4 @@
+*.config linguist-language=nextflow
+*.nf.test linguist-language=nextflow
+modules/nf-core/** linguist-generated
+subworkflows/nf-core/** linguist-generated

.github/.dockstore.yml

@@ -0,0 +1,6 @@
+# Dockstore config version, not pipeline version
+version: 1.2
+workflows:
+  - subclass: nfl
+    primaryDescriptorPath: /nextflow.config
+    publish: True

.github/CONTRIBUTING.md

@@ -0,0 +1,118 @@
+# plant-food-research-open/genepal: Contributing Guidelines
+
+Hi there!
+Many thanks for taking an interest in improving plant-food-research-open/genepal.
+
+We try to manage the required tasks for plant-food-research-open/genepal using GitHub issues, you probably came to this page when creating one.
+Please use the pre-filled template to save time.
+
+However, don't be put off by this template - other more general issues and suggestions are welcome!
+Contributions to the code are even more welcome ;)
+
+## Contribution workflow
+
+If you'd like to write some code for plant-food-research-open/genepal, the standard workflow is as follows:
+
+1. Check that there isn't already an issue about your idea in the [plant-food-research-open/genepal issues](https://github.com/plant-food-research-open/genepal/issues) to avoid duplicating work. If there isn't one already, please create one so that others know you're working on this
+2. [Fork](https://help.github.com/en/github/getting-started-with-github/fork-a-repo) the [plant-food-research-open/genepal repository](https://github.com/plant-food-research-open/genepal) to your GitHub account
+3. Make the necessary changes / additions within your forked repository following [Pipeline conventions](#pipeline-contribution-conventions)
+4. Use `nf-core schema build` and add any new parameters to the pipeline JSON schema (requires [nf-core tools](https://github.com/nf-core/tools) >= 1.10).
+5. Submit a Pull Request against the `dev` branch and wait for the code to be reviewed and merged
+
+If you're not used to this workflow with git, you can start with some [docs from GitHub](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests) or even their [excellent `git` resources](https://try.github.io/).
+
+## Tests
+
+You have the option to test your changes locally by running the pipeline. For receiving warnings about process selectors and other `debug` information, it is recommended to use the debug profile. Execute all the tests with the following command:
+
+```bash
+nf-test test --profile debug,test,docker --verbose
+```
+
+When you create a pull request with changes, [GitHub Actions](https://github.com/features/actions) will run automatic tests.
+Typically, pull-requests are only fully reviewed when these tests are passing, though of course we can help out before then.
+
+There are typically two types of tests that run:
+
+### Lint tests
+
+`nf-core` has a [set of guidelines](https://nf-co.re/developers/guidelines) which all pipelines must adhere to.
+To enforce these and ensure that all pipelines stay in sync, we have developed a helper tool which runs checks on the pipeline code. This is in the [nf-core/tools repository](https://github.com/nf-core/tools) and once installed can be run locally with the `nf-core lint <pipeline-directory>` command.
+
+If any failures or warnings are encountered, please follow the listed URL for more documentation.
+
+### Pipeline tests
+
+Each `nf-core` pipeline should be set up with a minimal set of test-data.
+`GitHub Actions` then runs the pipeline on this data to ensure that it exits successfully.
+If there are any failures then the automated tests fail.
+These tests are run both with the latest available version of `Nextflow` and also the minimum required version that is stated in the pipeline code.
+
+## Patch
+
+:warning: Only in the unlikely and regretful event of a release happening with a bug.
+
+- On your own fork, make a new branch `patch` based on `upstream/master`.
+- Fix the bug, and bump version (X.Y.Z+1).
+- A PR should be made on `master` from patch to directly this particular bug.
+
+## Pipeline contribution conventions
+
+To make the plant-food-research-open/genepal code and processing logic more understandable for new contributors and to ensure quality, we semi-standardise the way the code and other contributions are written.
+
+### Adding a new step
+
+If you wish to contribute a new step, please use the following coding standards:
+
+1. Define the corresponding input channel into your new process from the expected previous process channel
+2. Write the process block (see below).
+3. Define the output channel if needed (see below).
+4. Add any new parameters to `nextflow.config` with a default (see below).
+5. Add any new parameters to `nextflow_schema.json` with help text (via the `nf-core schema build` tool).
+6. Add sanity checks and validation for all relevant parameters.
+7. Perform local tests to validate that the new code works as expected.
+8. If applicable, add a new test command in `.github/workflow/ci.yml`.
+9. Update MultiQC config `assets/multiqc_config.yml` so relevant suffixes, file name clean up and module plots are in the appropriate order. If applicable, add a [MultiQC](https://https://multiqc.info/) module.
+10. Add a description of the output files and if relevant any appropriate images from the MultiQC report to `docs/output.md`.
+
+### Default values
+
+Parameters should be initialised / defined with default values in `nextflow.config` under the `params` scope.
+
+Once there, use `nf-core schema build` to add to `nextflow_schema.json`.
+
+### Default processes resource requirements
+
+Sensible defaults for process resource requirements (CPUs / memory / time) for a process should be defined in `conf/base.config`. These should generally be specified generic with `withLabel:` selectors so they can be shared across multiple processes/steps of the pipeline. A nf-core standard set of labels that should be followed where possible can be seen in the [nf-core pipeline template](https://github.com/nf-core/tools/blob/master/nf_core/pipeline-template/conf/base.config), which has the default process as a single core-process, and then different levels of multi-core configurations for increasingly large memory requirements defined with standardised labels.
+
+The process resources can be passed on to the tool dynamically within the process with the `${task.cpus}` and `${task.memory}` variables in the `script:` block.
+
+### Naming schemes
+
+Please use the following naming schemes, to make it easy to understand what is going where.
+
+- initial process channel: `ch_output_from_<process>`
+- intermediate and terminal channels: `ch_<previousprocess>_for_<nextprocess>`
+
+### Nextflow version bumping
+
+If you are using a new feature from core Nextflow, you may bump the minimum required version of nextflow in the pipeline with: `nf-core bump-version --nextflow . [min-nf-version]`
+
+### Images and figures
+
+For overview images and other documents we follow the nf-core [style guidelines and examples](https://nf-co.re/developers/design_guidelines).
+
+## GitHub Codespaces
+
+This repo includes a devcontainer configuration which will create a GitHub Codespaces for Nextflow development! This is an online developer environment that runs in your browser, complete with VSCode and a terminal.
+
+To get started:
+
+- Open the repo in [Codespaces](https://github.com/plant-food-research-open/genepal/codespaces)
+- Tools installed
+  - nf-core
+  - Nextflow
+
+Devcontainer specs:
+
+- [DevContainer config](.devcontainer/devcontainer.json)

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,54 @@
+name: Bug report
+description: Report something that is broken or incorrect
+labels: bug
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: command_used
+    attributes:
+      label: Command used and terminal output
+      description: Steps to reproduce the behaviour. Please paste the command you used
+        to launch the pipeline and the output from your terminal.
+      render: console
+      placeholder: "$ nextflow run ...
+
+
+        Some output where something broke
+
+        "
+  - type: textarea
+    id: files
+    attributes:
+      label: Relevant files
+      description: "Please drag and drop the relevant files here. Create a `.zip` archive
+        if the extension is not allowed.
+
+        Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
+        in the directory where you launched the pipeline)_ as well as custom Nextflow
+        configuration files.
+
+        "
+  - type: textarea
+    id: system
+    attributes:
+      label: System information
+      description: "* Nextflow version _(eg. 23.04.0)_
+
+        * Hardware _(eg. HPC, Desktop, Cloud)_
+
+        * Executor _(eg. slurm, local, awsbatch)_
+
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
+        or Apptainer)_
+
+        * OS _(eg. CentOS Linux, macOS, Linux Mint)_
+
+        * Version of plant-food-research-open/genepal _(eg. 1.1, 1.5, 1.8.2)_
+
+        "

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,11 @@
+name: Feature request
+description: Suggest an idea for the plant-food-research-open/genepal pipeline
+labels: enhancement
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of feature
+      description: Please describe your suggestion for a new feature. It might help to describe a problem or use case, plus any alternatives that you have considered.
+    validations:
+      required: true

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,25 @@
+<!--
+# plant-food-research-open/genepal pull request
+
+Many thanks for contributing to plant-food-research-open/genepal!
+
+Please fill in the appropriate checklist below (delete whatever is not relevant).
+These are the most common things requested on pull requests (PRs).
+
+Remember that PRs should be made against the dev branch, unless you're preparing a pipeline release.
+
+Learn more about contributing: [CONTRIBUTING.md](https://github.com/plant-food-research-open/genepal/tree/master/.github/CONTRIBUTING.md)
+-->
+
+## PR checklist
+
+- [ ] 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/plant-food-research-open/genepal/tree/master/.github/CONTRIBUTING.md)
+- [ ] Make sure your code lints (`nf-core lint`).
+- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
+- [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir <OUTDIR>`).
+- [ ] Usage Documentation in `docs/usage.md` is updated.
+- [ ] Output Documentation in `docs/output.md` is updated.
+- [ ] `CHANGELOG.md` is updated.
+- [ ] `README.md` is updated (including new tool citations and authors/contributors).

.github/contributors.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+
+module_authors=$(find ./modules -name meta.yml | xargs -I {} grep -A20 'authors:' {} | grep '\- ' | tr -d '"' | tr '[:upper:]' '[:lower:]' | awk '{print $2}')
+workflow_authors=$(find ./subworkflows -name meta.yml | xargs -I {} grep -A20 'authors:' {} | grep '\- ' | tr -d '"' | tr '[:upper:]' '[:lower:]' | awk '{print $2}')
+echo -e "${module_authors}\n${workflow_authors}" | sort -V | uniq -c | sort -k1,1 -r | awk '{print $2}' | sed -n 's|@\(.*\)|<a href="https://github.com/\1"><img src="https://github.com/\1.png" width="50" height="50"></a>|p'

.github/workflows/branch.yml

@@ -0,0 +1,44 @@
+name: nf-core branch protection
+# This workflow is triggered on PRs to master branch on the repository
+# It fails when someone tries to make a PR against the nf-core `master` branch instead of `dev`
+on:
+  pull_request_target:
+    branches: [master]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      # PRs to the nf-core repo master branch are only ok if coming from the nf-core repo `dev` or any `patch` branches
+      - name: Check PRs
+        if: github.repository == 'Plant-Food-Research-Open/genepal'
+        run: |
+          { [[ ${{github.event.pull_request.head.repo.full_name }} == Plant-Food-Research-Open/genepal ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]]
+
+      # If the above check failed, post a comment on the PR explaining the failure
+      # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets
+      - name: Post PR comment
+        if: failure()
+        uses: mshick/add-pr-comment@b8f338c590a895d50bcbfa6c5859251edc8952fc # v2
+        with:
+          message: |
+            ## This PR is against the `master` branch :x:
+
+            * Do not close this PR
+            * Click _Edit_ and change the `base` to `dev`
+            * This CI test will remain failed until you push a new commit
+
+            ---
+
+            Hi @${{ github.event.pull_request.user.login }},
+
+            It looks like this pull-request is has been made against the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `master` branch.
+            The `master` branch on nf-core repositories should always contain code from the latest release.
+            Because of this, PRs to `master` are only allowed if they come from the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `dev` branch.
+
+            You do not need to close this PR, you can change the target branch to `dev` by clicking the _"Edit"_ button at the top of this page.
+            Note that even after this, the test will continue to show as failing until you push a new commit.
+
+            Thanks again for your contribution!
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          allow-repeats: false