1st attempt to create module :(

Author: borgessbarbara

.devcontainer/devcontainer.json

@@ -1,28 +1,20 @@
 {
     "name": "nfcore",
-    "image": "nfcore/gitpod:dev",
+    "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",
-                "python.linting.enabled": true
+                "python.defaultInterpreterPath": "/opt/conda/bin/python"
             },
 
             // Add the IDs of extensions you want installed when the container is created.
-            "extensions": ["nf-core.nf-core-extensionpack"]
-        }
-    },
-    "features": {
-        "ghcr.io/devcontainers/features/github-cli:1.0.11": {
-            "digest": "sha256:464564228ccdd6028f01f8a62a3cfbaf76e9ba7953b29ac0e53ba2c262604312"
-        },
-        "ghcr.io/devcontainers/features/docker-in-docker:2.9.2": {
-            "digest": "sha256:9074d8eaf4585ab1498c81a8762078992725614fc7a9cfafe799aa22717a6bbf"
+            "extensions": ["ms-python.python", "ms-python.vscode-pylance", "nf-core.nf-core-extensionpack"]
         }
     }
 }

.gitattributes

@@ -1 +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 +1,123 @@
+# `nf-core/transcriptclean`: Contributing Guidelines
+
+Hi there!
+Many thanks for taking an interest in improving nf-core/transcriptclean.
+
+We try to manage the required tasks for nf-core/transcriptclean 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 ;)
+
+> [!NOTE]
+> If you need help using or modifying nf-core/transcriptclean then the best place to ask is on the nf-core Slack [#transcriptclean](https://nfcore.slack.com/channels/transcriptclean) channel ([join our Slack here](https://nf-co.re/join/slack)).
+
+## Contribution workflow
+
+If you'd like to write some code for nf-core/transcriptclean, the standard workflow is as follows:
+
+1. Check that there isn't already an issue about your idea in the [nf-core/transcriptclean issues](https://github.com/nf-core/transcriptclean/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 [nf-core/transcriptclean repository](https://github.com/nf-core/transcriptclean) to your GitHub account
+3. Make the necessary changes / additions within your forked repository following [Pipeline conventions](#pipeline-contribution-conventions)
+4. Use `nf-core pipelines 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 pipelines 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/main` or `upstream/master`.
+- Fix the bug, and bump version (X.Y.Z+1).
+- Open a pull-request from `patch` to `main`/`master` with the changes.
+
+## Getting help
+
+For further information/help, please consult the [nf-core/transcriptclean documentation](https://nf-co.re/transcriptclean/usage) and don't hesitate to get in touch on the nf-core Slack [#transcriptclean](https://nfcore.slack.com/channels/transcriptclean) channel ([join our Slack here](https://nf-co.re/join/slack)).
+
+## Pipeline contribution conventions
+
+To make the `nf-core/transcriptclean` 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 pipelines 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 in the `tests` directory.
+
+### Default values
+
+Parameters should be initialised / defined with default values within the `params` scope in `nextflow.config`.
+
+Once there, use `nf-core pipelines 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/main/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 pipelines 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/nf-core/transcriptclean/codespaces)
+- Tools installed
+  - nf-core
+  - Nextflow
+
+Devcontainer specs:
+
+- [DevContainer config](.devcontainer/devcontainer.json)

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,49 @@
+name: Bug report
+description: Report something that is broken or incorrect
+labels: bug
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Before you post this issue, please check the documentation:
+
+        - [nf-core website: troubleshooting](https://nf-co.re/usage/troubleshooting)
+        - [nf-core/transcriptclean pipeline documentation](https://nf-co.re/transcriptclean/usage)
+  - 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 nf-core/transcriptclean _(eg. 1.1, 1.5, 1.8.2)_

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,7 @@
+contact_links:
+  - name: Join nf-core
+    url: https://nf-co.re/join
+    about: Please join the nf-core community here
+  - name: "Slack #transcriptclean channel"
+    url: https://nfcore.slack.com/channels/transcriptclean
+    about: Discussion about the nf-core/transcriptclean pipeline

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,11 @@
+name: Feature request
+description: Suggest an idea for the nf-core/transcriptclean 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 +1,26 @@
+<!--
+# nf-core/transcriptclean pull request
+
+Many thanks for contributing to nf-core/transcriptclean!
+
+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/nf-core/transcriptclean/tree/main/.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/nf-core/transcriptclean/tree/main/.github/CONTRIBUTING.md)
+- [ ] If necessary, also make a PR on the nf-core/transcriptclean _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
+- [ ] Make sure your code lints (`nf-core pipelines 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/actions/get-shards/action.yml

@@ -0,0 +1,69 @@
+name: "Get number of shards"
+description: "Get the number of nf-test shards for the current CI job"
+inputs:
+  max_shards:
+    description: "Maximum number of shards allowed"
+    required: true
+  paths:
+    description: "Component paths to test"
+    required: false
+  tags:
+    description: "Tags to pass as argument for nf-test --tag parameter"
+    required: false
+outputs:
+  shard:
+    description: "Array of shard numbers"
+    value: ${{ steps.shards.outputs.shard }}
+  total_shards:
+    description: "Total number of shards"
+    value: ${{ steps.shards.outputs.total_shards }}
+runs:
+  using: "composite"
+  steps:
+    - name: Install nf-test
+      uses: nf-core/setup-nf-test@v1
+      with:
+        version: ${{ env.NFT_VER }}
+    - name: Get number of shards
+      id: shards
+      shell: bash
+      run: |
+        # Run nf-test with dynamic parameter
+        nftest_output=$(nf-test test \
+          --profile +docker \
+          $(if [ -n "${{ inputs.tags }}" ]; then echo "--tag ${{ inputs.tags }}"; fi) \
+          --dry-run \
+          --ci \
+          --changed-since HEAD^) || {
+            echo "nf-test command failed with exit code $?"
+            echo "Full output: $nftest_output"
+            exit 1
+        }
+        echo "nf-test dry-run output: $nftest_output"
+
+        # Default values for shard and total_shards
+        shard="[]"
+        total_shards=0
+
+        # Check if there are related tests
+        if echo "$nftest_output" | grep -q 'No tests to execute'; then
+          echo "No related tests found."
+        else
+          # Extract the number of related tests
+          number_of_shards=$(echo "$nftest_output" | sed -n 's|.*Executed \([0-9]*\) tests.*|\1|p')
+          if [[ -n "$number_of_shards" && "$number_of_shards" -gt 0 ]]; then
+            shards_to_run=$(( $number_of_shards < ${{ inputs.max_shards }} ? $number_of_shards : ${{ inputs.max_shards }} ))
+            shard=$(seq 1 "$shards_to_run" | jq -R . | jq -c -s .)
+            total_shards="$shards_to_run"
+          else
+            echo "Unexpected output format. Falling back to default values."
+          fi
+        fi
+
+        # Write to GitHub Actions outputs
+        echo "shard=$shard" >> $GITHUB_OUTPUT
+        echo "total_shards=$total_shards" >> $GITHUB_OUTPUT
+
+        # Debugging output
+        echo "Final shard array: $shard"
+        echo "Total number of shards: $total_shards"