diff --git a/.editorconfig b/.editorconfig
new file mode 100644
index 00000000..b78de6e6
--- /dev/null
+++ b/.editorconfig
@@ -0,0 +1,24 @@
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+indent_size = 4
+indent_style = space
+
+[*.{md,yml,yaml,html,css,scss,js,cff}]
+indent_size = 2
+
+# These files are edited and tested upstream in nf-core/modules
+[/modules/nf-core/**]
+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
diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 00000000..050bb120
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,3 @@
+*.config linguist-language=nextflow
+modules/nf-core/** linguist-generated
+subworkflows/nf-core/** linguist-generated
diff --git a/.github/.dockstore.yml b/.github/.dockstore.yml
new file mode 100644
index 00000000..191fabd2
--- /dev/null
+++ b/.github/.dockstore.yml
@@ -0,0 +1,6 @@
+# Dockstore config version, not pipeline version
+version: 1.2
+workflows:
+  - subclass: nfl
+    primaryDescriptorPath: /nextflow.config
+    publish: True
diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
new file mode 100644
index 00000000..3b3e60c9
--- /dev/null
+++ b/.github/CONTRIBUTING.md
@@ -0,0 +1,97 @@
+# sanger-tol/genomeassembly: Contributing Guidelines
+
+Hi there!
+Many thanks for taking an interest in improving sanger-tol/genomeassembly.
+
+We try to manage the required tasks for sanger-tol/genomeassembly 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 sanger-tol/genomeassembly, the standard workflow is as follows:
+
+1. Check that there isn't already an issue about your idea in the [sanger-tol/genomeassembly issues](https://github.com/sanger-tol/genomeassembly/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 [sanger-tol/genomeassembly repository](https://github.com/sanger-tol/genomeassembly) 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
+
+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 sanger-tol/genomeassembly 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 `${task.cpu}` and `${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).
diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml
new file mode 100644
index 00000000..865a5d25
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -0,0 +1,53 @@
+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. 21.10.3)_
+
+        * Hardware _(eg. HPC, Desktop, Cloud)_
+
+        * Executor _(eg. slurm, local, awsbatch)_
+
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter or Charliecloud)_
+
+        * OS _(eg. CentOS Linux, macOS, Linux Mint)_
+
+        * Version of sanger-tol/genomeassembly _(eg. 1.1, 1.5, 1.8.2)_
+
+        "
diff --git a/.github/ISSUE_TEMPLATE/feature_request.yml b/.github/ISSUE_TEMPLATE/feature_request.yml
new file mode 100644
index 00000000..ae7677dc
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/feature_request.yml
@@ -0,0 +1,11 @@
+name: Feature request
+description: Suggest an idea for the sanger-tol/genomeassembly 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
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
new file mode 100644
index 00000000..006842ef
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -0,0 +1,24 @@
+<!--
+# sanger-tol/genomeassembly pull request
+
+Many thanks for contributing to sanger-tol/genomeassembly!
+
+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/sanger-tol/genomeassembly/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/sanger-tol/genomeassembly/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>`).
+- [ ] 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).
diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml
new file mode 100644
index 00000000..5f55544d
--- /dev/null
+++ b/.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 == 'sanger-tol/genomeassembly'
+        run: |
+          { [[ ${{github.event.pull_request.head.repo.full_name }} == sanger-tol/genomeassembly ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]]
+
+      # If the above check failed, post a comment on the PR explaining the failure
+      # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets
+      - name: Post PR comment
+        if: failure()
+        uses: mshick/add-pr-comment@v1
+        with:
+          message: |
+            ## This PR is against the `master` branch :x:
+
+            * Do not close this PR
+            * Click _Edit_ and change the `base` to `dev`
+            * This CI test will remain failed until you push a new commit
+
+            ---
+
+            Hi @${{ 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: ${{ secrets.GITHUB_TOKEN }}
+          allow-repeats: false
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 00000000..62e603b5
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,39 @@
+name: nf-core CI
+# This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
+on:
+  push:
+    branches:
+      - dev
+  pull_request:
+  release:
+    types: [published]
+
+env:
+  NXF_ANSI_LOG: false
+
+jobs:
+  test:
+    name: Run pipeline with test data
+    # Only run on push if this is the nf-core dev branch (merged PRs)
+    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'sanger-tol/genomeassembly') }}"
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        NXF_VER:
+          - "21.10.3"
+          - "latest-everything"
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@v2
+
+      - name: Install Nextflow
+        uses: nf-core/setup-nextflow@v1
+        with:
+          version: "${{ matrix.NXF_VER }}"
+
+      - name: Run pipeline with test data
+        # TODO nf-core: 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
diff --git a/.github/workflows/fix-linting.yml b/.github/workflows/fix-linting.yml
new file mode 100644
index 00000000..08f701c6
--- /dev/null
+++ b/.github/workflows/fix-linting.yml
@@ -0,0 +1,55 @@
+name: Fix linting from a comment
+on:
+  issue_comment:
+    types: [created]
+
+jobs:
+  deploy:
+    # Only run if comment is on a PR with the main repo, and if it contains the magic keywords
+    if: >
+      contains(github.event.comment.html_url, '/pull/') &&
+      contains(github.event.comment.body, '@nf-core-bot fix linting') &&
+      github.repository == 'sanger-tol/genomeassembly'
+    runs-on: ubuntu-latest
+    steps:
+      # Use the @nf-core-bot token to check out so we can push later
+      - uses: actions/checkout@v3
+        with:
+          token: ${{ secrets.nf_core_bot_auth_token }}
+
+      # Action runs on the issue comment, so we don't get the PR by default
+      # Use the gh cli to check out the PR
+      - name: Checkout Pull Request
+        run: gh pr checkout ${{ github.event.issue.number }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.nf_core_bot_auth_token }}
+
+      - uses: actions/setup-node@v2
+
+      - name: Install Prettier
+        run: npm install -g prettier @prettier/plugin-php
+
+      # Check that we actually need to fix something
+      - name: Run 'prettier --check'
+        id: prettier_status
+        run: |
+          if prettier --check ${GITHUB_WORKSPACE}; then
+            echo "::set-output name=result::pass"
+          else
+            echo "::set-output name=result::fail"
+          fi
+
+      - name: Run 'prettier --write'
+        if: steps.prettier_status.outputs.result == 'fail'
+        run: prettier --write ${GITHUB_WORKSPACE}
+
+      - name: Commit & push changes
+        if: steps.prettier_status.outputs.result == 'fail'
+        run: |
+          git config user.email "core@nf-co.re"
+          git config user.name "nf-core-bot"
+          git config push.default upstream
+          git add .
+          git status
+          git commit -m "[automated] Fix linting with Prettier"
+          git push
diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
new file mode 100644
index 00000000..ea434dc2
--- /dev/null
+++ b/.github/workflows/linting.yml
@@ -0,0 +1,106 @@
+name: nf-core linting
+# This workflow is triggered on pushes and PRs to the repository.
+# It runs the `nf-core lint` and markdown lint tests to ensure
+# that the code meets the nf-core guidelines.
+on:
+  push:
+  pull_request:
+  release:
+    types: [published]
+
+jobs:
+  EditorConfig:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: actions/setup-node@v2
+
+      - name: Install editorconfig-checker
+        run: npm install -g editorconfig-checker
+
+      - 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')
+
+  Prettier:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: actions/setup-node@v2
+
+      - name: Install Prettier
+        run: npm install -g prettier
+
+      - 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
+        uses: nf-core/setup-nextflow@v1
+
+      - uses: actions/setup-python@v3
+        with:
+          python-version: "3.6"
+          architecture: "x64"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install nf-core
+
+      - name: Run nf-core lint
+        env:
+          GITHUB_COMMENTS_URL: ${{ github.event.pull_request.comments_url }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_PR_COMMIT: ${{ github.event.pull_request.head.sha }}
+        run: nf-core -l lint_log.txt lint --dir ${GITHUB_WORKSPACE} --markdown lint_results.md
+
+      - name: Save PR number
+        if: ${{ always() }}
+        run: echo ${{ github.event.pull_request.number }} > PR_number.txt
+
+      - name: Upload linting log file artifact
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: linting-logs
+          path: |
+            lint_log.txt
+            lint_results.md
+            PR_number.txt
diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml
new file mode 100644
index 00000000..04758f61
--- /dev/null
+++ b/.github/workflows/linting_comment.yml
@@ -0,0 +1,28 @@
+name: nf-core linting comment
+# This workflow is triggered after the linting action is complete
+# It posts an automated comment to the PR, even if the PR is coming from a fork
+
+on:
+  workflow_run:
+    workflows: ["nf-core linting"]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download lint results
+        uses: dawidd6/action-download-artifact@v2
+        with:
+          workflow: linting.yml
+          workflow_conclusion: completed
+
+      - name: Get PR number
+        id: pr_number
+        run: echo "::set-output name=pr_number::$(cat linting-logs/PR_number.txt)"
+
+      - name: Post PR comment
+        uses: marocchino/sticky-pull-request-comment@v2
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          number: ${{ steps.pr_number.outputs.pr_number }}
+          path: linting-logs/lint_results.md
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..5124c9ac
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,8 @@
+.nextflow*
+work/
+data/
+results/
+.DS_Store
+testing/
+testing*
+*.pyc
diff --git a/.gitpod.yml b/.gitpod.yml
new file mode 100644
index 00000000..85d95ecc
--- /dev/null
+++ b/.gitpod.yml
@@ -0,0 +1,14 @@
+image: nfcore/gitpod:latest
+
+vscode:
+  extensions: # based on nf-core.nf-core-extensionpack
+    - codezombiech.gitignore # Language support for .gitignore files
+    # - cssho.vscode-svgviewer                 # SVG viewer
+    - esbenp.prettier-vscode # Markdown/CommonMark linting and style checking for Visual Studio Code
+    - eamodio.gitlens # Quickly glimpse into whom, why, and when a line or code block was changed
+    - EditorConfig.EditorConfig # override user/workspace settings with settings found in .editorconfig files
+    - Gruntfuggly.todo-tree # Display TODO and FIXME in a tree view in the activity bar
+    - mechatroner.rainbow-csv # Highlight columns in csv files in different colors
+    # - nextflow.nextflow                      # Nextflow syntax highlighting
+    - oderwat.indent-rainbow # Highlight indentation level
+    - streetsidesoftware.code-spell-checker # Spelling checker for source code
diff --git a/.nf-core.yml b/.nf-core.yml
new file mode 100644
index 00000000..693a794d
--- /dev/null
+++ b/.nf-core.yml
@@ -0,0 +1,15 @@
+repository_type: pipeline
+lint:
+  files_exist:
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-genomeassembly_logo_light.png
+    - docs/images/nf-core-genomeassembly_logo_light.png
+    - docs/images/nf-core-genomeassembly_logo_dark.png
+    - .github/ISSUE_TEMPLATE/config.yml
+    - .github/workflows/awstest.yml
+    - .github/workflows/awsfulltest.yml
+  nextflow_config:
+    - manifest.name
+    - manifest.homePage
+  multiqc_config:
+    - report_comment
diff --git a/.prettierignore b/.prettierignore
new file mode 100644
index 00000000..d0e7ae58
--- /dev/null
+++ b/.prettierignore
@@ -0,0 +1,9 @@
+email_template.html
+.nextflow*
+work/
+data/
+results/
+.DS_Store
+testing/
+testing*
+*.pyc
diff --git a/.prettierrc.yml b/.prettierrc.yml
new file mode 100644
index 00000000..c81f9a76
--- /dev/null
+++ b/.prettierrc.yml
@@ -0,0 +1 @@
+printWidth: 120
diff --git a/CHANGELOG.md b/CHANGELOG.md
new file mode 100644
index 00000000..0f4689c0
--- /dev/null
+++ b/CHANGELOG.md
@@ -0,0 +1,16 @@
+# sanger-tol/genomeassembly: Changelog
+
+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).
+
+## v1.0dev - [date]
+
+Initial release of sanger-tol/genomeassembly, created with the [nf-core](https://nf-co.re/) template.
+
+### `Added`
+
+### `Fixed`
+
+### `Dependencies`
+
+### `Deprecated`
diff --git a/CITATION.cff b/CITATION.cff
new file mode 100644
index 00000000..4533e2f2
--- /dev/null
+++ b/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
diff --git a/CITATIONS.md b/CITATIONS.md
new file mode 100644
index 00000000..b6756d75
--- /dev/null
+++ b/CITATIONS.md
@@ -0,0 +1,35 @@
+# sanger-tol/genomeassembly: Citations
+
+## [nf-core](https://pubmed.ncbi.nlm.nih.gov/32055031/)
+
+> Ewels PA, Peltzer A, Fillinger S, Patel H, Alneberg J, Wilm A, Garcia MU, Di Tommaso P, Nahnsen S. The nf-core framework for community-curated bioinformatics pipelines. Nat Biotechnol. 2020 Mar;38(3):276-278. doi: 10.1038/s41587-020-0439-x. PubMed PMID: 32055031.
+
+## [Nextflow](https://pubmed.ncbi.nlm.nih.gov/28398311/)
+
+> Di Tommaso P, Chatzou M, Floden EW, Barja PP, Palumbo E, Notredame C. Nextflow enables reproducible computational workflows. Nat Biotechnol. 2017 Apr 11;35(4):316-319. doi: 10.1038/nbt.3820. PubMed PMID: 28398311.
+
+## Pipeline tools
+
+- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+
+- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+  > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
+
+## Software packaging/containerisation tools
+
+- [Anaconda](https://anaconda.com)
+
+  > Anaconda Software Distribution. Computer software. Vers. 2-2.4.0. Anaconda, Nov. 2016. Web.
+
+- [Bioconda](https://pubmed.ncbi.nlm.nih.gov/29967506/)
+
+  > Grüning B, Dale R, Sjödin A, Chapman BA, Rowe J, Tomkins-Tinch CH, Valieris R, Köster J; Bioconda Team. Bioconda: sustainable and comprehensive software distribution for the life sciences. Nat Methods. 2018 Jul;15(7):475-476. doi: 10.1038/s41592-018-0046-7. PubMed PMID: 29967506.
+
+- [BioContainers](https://pubmed.ncbi.nlm.nih.gov/28379341/)
+
+  > da Veiga Leprevost F, Grüning B, Aflitos SA, Röst HL, Uszkoreit J, Barsnes H, Vaudel M, Moreno P, Gatto L, Weber J, Bai M, Jimenez RC, Sachsenberg T, Pfeuffer J, Alvarez RV, Griss J, Nesvizhskii AI, Perez-Riverol Y. BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics. 2017 Aug 15;33(16):2580-2582. doi: 10.1093/bioinformatics/btx192. PubMed PMID: 28379341; PubMed Central PMCID: PMC5870671.
+
+- [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241)
+
+- [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/)
+  > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675.
diff --git a/LICENSE b/LICENSE
new file mode 100644
index 00000000..fba963d9
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) @ksenia-krasheninnikova
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
diff --git a/README.md b/README.md
new file mode 100644
index 00000000..ba41319d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,82 @@
+[![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?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/sanger-tol/genomeassembly)
+
+## Introduction
+
+<!-- TODO nf-core: Write a 1-2 sentence summary of what data the pipeline is for and what it does -->
+
+**sanger-tol/genomeassembly** is a bioinformatics best-practice analysis pipeline for .
+
+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!
+
+<!-- TODO nf-core: Add full-sized test dataset and amend the paragraph below if applicable -->
+
+On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources.
+
+## Pipeline summary
+
+<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
+
+1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
+2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+
+## Quick Start
+
+1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=21.10.3`)
+
+2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/) (you can follow [this tutorial](https://singularity-tutorial.github.io/01-installation/)), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(you can use [`Conda`](https://conda.io/miniconda.html) both to install Nextflow itself and also to manage software within pipelines. Please only use it within pipelines as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_.
+
+3. Download the pipeline and test it on a minimal dataset with a single command:
+
+   ```console
+   nextflow run sanger-tol/genomeassembly -profile test,YOURPROFILE --outdir <OUTDIR>
+   ```
+
+   Note that some form of configuration will be needed so that Nextflow knows how to fetch the required software. This is usually done in the form of a config profile (`YOURPROFILE` in the example command above). You can chain multiple config profiles in a comma-separated string.
+
+   > - The pipeline comes with config profiles called `docker`, `singularity`, `podman`, `shifter`, `charliecloud` and `conda` which instruct the pipeline to use the named tool for software management. For example, `-profile test,docker`.
+   > - Please check [nf-core/configs](https://github.com/nf-core/configs#documentation) to see if a custom config file to run nf-core pipelines already exists for your Institute. If so, you can simply use `-profile <institute>` in your command. This will enable either `docker` or `singularity` and set the appropriate execution settings for your local compute environment.
+   > - If you are using `singularity`, please use the [`nf-core download`](https://nf-co.re/tools/#downloading-pipelines-for-offline-use) command to download images first, before running the pipeline. Setting the [`NXF_SINGULARITY_CACHEDIR` or `singularity.cacheDir`](https://www.nextflow.io/docs/latest/singularity.html?#singularity-docker-hub) Nextflow options enables you to store and re-use the images from a central location for future pipeline runs.
+   > - If you are using `conda`, it is highly recommended to use the [`NXF_CONDA_CACHEDIR` or `conda.cacheDir`](https://www.nextflow.io/docs/latest/conda.html) settings to store the environments in a central location for future pipeline runs.
+
+4. Start running your own analysis!
+
+   <!-- TODO nf-core: Update the example "typical command" below used to run the pipeline -->
+
+   ```console
+   nextflow run sanger-tol/genomeassembly --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
+   ```
+
+## Credits
+
+sanger-tol/genomeassembly was originally written by @ksenia-krasheninnikova.
+
+We thank the following people for their extensive assistance in the development of this pipeline:
+
+<!-- TODO nf-core: If applicable, make list of people who have also contributed -->
+
+## Contributions and Support
+
+If you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).
+
+## Citations
+
+<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
+<!-- If you use  sanger-tol/genomeassembly for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
+
+<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
+
+An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
+
+This pipeline uses code and infrastructure developed and maintained by the [nf-core](https://nf-co.re) community, reused here under the [MIT license](https://github.com/nf-core/tools/blob/master/LICENSE).
+
+> **The nf-core framework for community-curated bioinformatics pipelines.**
+>
+> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.
+>
+> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).
diff --git a/assets/email_template.html b/assets/email_template.html
new file mode 100644
index 00000000..6e3b27b2
--- /dev/null
+++ b/assets/email_template.html
@@ -0,0 +1,53 @@
+<html>
+<head>
+  <meta charset="utf-8">
+  <meta http-equiv="X-UA-Compatible" content="IE=edge">
+  <meta name="viewport" content="width=device-width, initial-scale=1">
+
+  <meta name="description" content="sanger-tol/genomeassembly: ">
+  <title>sanger-tol/genomeassembly Pipeline Report</title>
+</head>
+<body>
+<div style="font-family: Helvetica, Arial, sans-serif; padding: 30px; max-width: 800px; margin: 0 auto;">
+
+<img src="cid:nfcorepipelinelogo">
+
+<h1>sanger-tol/genomeassembly v${version}</h1>
+<h2>Run Name: $runName</h2>
+
+<% if (!success){
+    out << """
+    <div style="color: #a94442; background-color: #f2dede; border-color: #ebccd1; padding: 15px; margin-bottom: 20px; border: 1px solid transparent; border-radius: 4px;">
+        <h4 style="margin-top:0; color: inherit;">sanger-tol/genomeassembly execution completed unsuccessfully!</h4>
+        <p>The exit status of the task that caused the workflow execution to fail was: <code>$exitStatus</code>.</p>
+        <p>The full error message was:</p>
+        <pre style="white-space: pre-wrap; overflow: visible; margin-bottom: 0;">${errorReport}</pre>
+    </div>
+    """
+} else {
+    out << """
+    <div style="color: #3c763d; background-color: #dff0d8; border-color: #d6e9c6; padding: 15px; margin-bottom: 20px; border: 1px solid transparent; border-radius: 4px;">
+        sanger-tol/genomeassembly execution completed successfully!
+    </div>
+    """
+}
+%>
+
+<p>The workflow was completed at <strong>$dateComplete</strong> (duration: <strong>$duration</strong>)</p>
+<p>The command used to launch the workflow was as follows:</p>
+<pre style="white-space: pre-wrap; overflow: visible; background-color: #ededed; padding: 15px; border-radius: 4px; margin-bottom:30px;">$commandLine</pre>
+
+<h3>Pipeline Configuration:</h3>
+<table style="width:100%; max-width:100%; border-spacing: 0; border-collapse: collapse; border:0; margin-bottom: 30px;">
+    <tbody style="border-bottom: 1px solid #ddd;">
+        <% out << summary.collect{ k,v -> "<tr><th style='text-align:left; padding: 8px 0; line-height: 1.42857143; vertical-align: top; border-top: 1px solid #ddd;'>$k</th><td style='text-align:left; padding: 8px; line-height: 1.42857143; vertical-align: top; border-top: 1px solid #ddd;'><pre style='white-space: pre-wrap; overflow: visible;'>$v</pre></td></tr>" }.join("\n") %>
+    </tbody>
+</table>
+
+<p>sanger-tol/genomeassembly</p>
+<p><a href="https://github.com/sanger-tol/genomeassembly">https://github.com/sanger-tol/genomeassembly</a></p>
+
+</div>
+
+</body>
+</html>
diff --git a/assets/email_template.txt b/assets/email_template.txt
new file mode 100644
index 00000000..3276dd21
--- /dev/null
+++ b/assets/email_template.txt
@@ -0,0 +1,31 @@
+Run Name: $runName
+
+<% if (success){
+    out << "## sanger-tol/genomeassembly execution completed successfully! ##"
+} else {
+    out << """####################################################
+## sanger-tol/genomeassembly execution completed unsuccessfully! ##
+####################################################
+The exit status of the task that caused the workflow execution to fail was: $exitStatus.
+The full error message was:
+
+${errorReport}
+"""
+} %>
+
+
+The workflow was completed at $dateComplete (duration: $duration)
+
+The command used to launch the workflow was as follows:
+
+  $commandLine
+
+
+
+Pipeline Configuration:
+-----------------------
+<% out << summary.collect{ k,v -> " - $k: $v" }.join("\n") %>
+
+--
+sanger-tol/genomeassembly
+https://github.com/sanger-tol/genomeassembly
diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
new file mode 100644
index 00000000..6a0906d5
--- /dev/null
+++ b/assets/multiqc_config.yml
@@ -0,0 +1,10 @@
+report_comment: >
+  This report has been generated by the <a href="https://github.com/sanger-tol/genomeassembly" target="_blank">sanger-tol/genomeassembly</a>
+  analysis pipeline.
+report_section_order:
+  software_versions:
+    order: -1000
+  "sanger-tol-genomeassembly-summary":
+    order: -1001
+
+export_plots: true
diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
new file mode 100644
index 00000000..5f653ab7
--- /dev/null
+++ b/assets/samplesheet.csv
@@ -0,0 +1,3 @@
+sample,fastq_1,fastq_2
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
diff --git a/assets/schema_input.json b/assets/schema_input.json
new file mode 100644
index 00000000..f6d56429
--- /dev/null
+++ b/assets/schema_input.json
@@ -0,0 +1,36 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema",
+    "$id": "https://raw.githubusercontent.com/sanger-tol/genomeassembly/master/assets/schema_input.json",
+    "title": "sanger-tol/genomeassembly pipeline - params.input schema",
+    "description": "Schema for the file provided with params.input",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "sample": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "Sample name must be provided and cannot contain spaces"
+            },
+            "fastq_1": {
+                "type": "string",
+                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
+                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+            },
+            "fastq_2": {
+                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
+                "anyOf": [
+                    {
+                        "type": "string",
+                        "pattern": "^\\S+\\.f(ast)?q\\.gz$"
+                    },
+                    {
+                        "type": "string",
+                        "maxLength": 0
+                    }
+                ]
+            }
+        },
+        "required": ["sample", "fastq_1"]
+    }
+}
diff --git a/assets/sendmail_template.txt b/assets/sendmail_template.txt
new file mode 100644
index 00000000..bb68bbca
--- /dev/null
+++ b/assets/sendmail_template.txt
@@ -0,0 +1,53 @@
+To: $email
+Subject: $subject
+Mime-Version: 1.0
+Content-Type: multipart/related;boundary="nfcoremimeboundary"
+
+--nfcoremimeboundary
+Content-Type: text/html; charset=utf-8
+
+$email_html
+
+--nfcoremimeboundary
+Content-Type: image/png;name="sanger-tol-genomeassembly_logo.png"
+Content-Transfer-Encoding: base64
+Content-ID: <nfcorepipelinelogo>
+Content-Disposition: inline; filename="sanger-tol-genomeassembly_logo_light.png"
+
+<% out << new File("$projectDir/assets/sanger-tol-genomeassembly_logo_light.png").
+    bytes.
+    encodeBase64().
+    toString().
+    tokenize( '\n' )*.
+    toList()*.
+    collate( 76 )*.
+    collect { it.join() }.
+    flatten().
+    join( '\n' ) %>
+
+<%
+if (mqcFile){
+def mqcFileObj = new File("$mqcFile")
+if (mqcFileObj.length() < mqcMaxSize){
+out << """
+--nfcoremimeboundary
+Content-Type: text/html; name=\"multiqc_report\"
+Content-Transfer-Encoding: base64
+Content-ID: <mqcreport>
+Content-Disposition: attachment; filename=\"${mqcFileObj.getName()}\"
+
+${mqcFileObj.
+    bytes.
+    encodeBase64().
+    toString().
+    tokenize( '\n' )*.
+    toList()*.
+    collate( 76 )*.
+    collect { it.join() }.
+    flatten().
+    join( '\n' )}
+"""
+}}
+%>
+
+--nfcoremimeboundary--
diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py
new file mode 100755
index 00000000..09044815
--- /dev/null
+++ b/bin/check_samplesheet.py
@@ -0,0 +1,256 @@
+#!/usr/bin/env python
+
+
+"""Provide a command line tool to validate and transform tabular samplesheets."""
+
+
+import argparse
+import csv
+import logging
+import sys
+from collections import Counter
+from pathlib import Path
+
+logger = logging.getLogger()
+
+
+class RowChecker:
+    """
+    Define a service that can validate and transform each given row.
+
+    Attributes:
+        modified (list): A list of dicts, where each dict corresponds to a previously
+            validated and transformed row. The order of rows is maintained.
+
+    """
+
+    VALID_FORMATS = (
+        ".fq.gz",
+        ".fastq.gz",
+    )
+
+    def __init__(
+        self,
+        sample_col="sample",
+        first_col="fastq_1",
+        second_col="fastq_2",
+        single_col="single_end",
+        **kwargs,
+    ):
+        """
+        Initialize the row checker with the expected column names.
+
+        Args:
+            sample_col (str): The name of the column that contains the sample name
+                (default "sample").
+            first_col (str): The name of the column that contains the first (or only)
+                FASTQ file path (default "fastq_1").
+            second_col (str): The name of the column that contains the second (if any)
+                FASTQ file path (default "fastq_2").
+            single_col (str): The name of the new column that will be inserted and
+                records whether the sample contains single- or paired-end sequencing
+                reads (default "single_end").
+
+        """
+        super().__init__(**kwargs)
+        self._sample_col = sample_col
+        self._first_col = first_col
+        self._second_col = second_col
+        self._single_col = single_col
+        self._seen = set()
+        self.modified = []
+
+    def validate_and_transform(self, row):
+        """
+        Perform all validations on the given row and insert the read pairing status.
+
+        Args:
+            row (dict): A mapping from column headers (keys) to elements of that row
+                (values).
+
+        """
+        self._validate_sample(row)
+        self._validate_first(row)
+        self._validate_second(row)
+        self._validate_pair(row)
+        self._seen.add((row[self._sample_col], row[self._first_col]))
+        self.modified.append(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."
+        # Sanitize samples slightly.
+        row[self._sample_col] = row[self._sample_col].replace(" ", "_")
+
+    def _validate_first(self, row):
+        """Assert that the first FASTQ entry is non-empty and has the right format."""
+        assert len(row[self._first_col]) > 0, "At least the first FASTQ file is required."
+        self._validate_fastq_format(row[self._first_col])
+
+    def _validate_second(self, row):
+        """Assert that the second FASTQ entry has the right format if it exists."""
+        if len(row[self._second_col]) > 0:
+            self._validate_fastq_format(row[self._second_col])
+
+    def _validate_pair(self, row):
+        """Assert that read pairs have the same file extension. Report pair status."""
+        if row[self._first_col] and row[self._second_col]:
+            row[self._single_col] = False
+            assert (
+                Path(row[self._first_col]).suffixes[-2:] == Path(row[self._second_col]).suffixes[-2:]
+            ), "FASTQ pairs must have the same file extensions."
+        else:
+            row[self._single_col] = True
+
+    def _validate_fastq_format(self, filename):
+        """Assert that a given filename has one of the expected FASTQ extensions."""
+        assert any(filename.endswith(extension) for extension in self.VALID_FORMATS), (
+            f"The FASTQ file has an unrecognized extension: {filename}\n"
+            f"It should be one of: {', '.join(self.VALID_FORMATS)}"
+        )
+
+    def validate_unique_samples(self):
+        """
+        Assert that the combination of sample name and FASTQ filename is unique.
+
+        In addition to the validation, also rename all samples to have a suffix of _T{n}, where n is the
+        number of times the same sample exist, but with different FASTQ files, e.g., multiple runs per experiment.
+
+        """
+        assert len(self._seen) == len(self.modified), "The pair of sample name and FASTQ must be unique."
+        seen = Counter()
+        for row in self.modified:
+            sample = row[self._sample_col]
+            seen[sample] += 1
+            row[self._sample_col] = f"{sample}_T{seen[sample]}"
+
+
+def read_head(handle, num_lines=10):
+    """Read the specified number of lines from the current position in the file."""
+    lines = []
+    for idx, line in enumerate(handle):
+        if idx == num_lines:
+            break
+        lines.append(line)
+    return "".join(lines)
+
+
+def sniff_format(handle):
+    """
+    Detect the tabular format.
+
+    Args:
+        handle (text file): A handle to a `text file`_ object. The read position is
+        expected to be at the beginning (index 0).
+
+    Returns:
+        csv.Dialect: The detected tabular format.
+
+    .. _text file:
+        https://docs.python.org/3/glossary.html#term-text-file
+
+    """
+    peek = read_head(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.")
+        sys.exit(1)
+    dialect = sniffer.sniff(peek)
+    return dialect
+
+
+def check_samplesheet(file_in, file_out):
+    """
+    Check that the tabular samplesheet has the structure expected by nf-core pipelines.
+
+    Validate the general shape of the table, expected columns, and each row. Also add
+    an additional column which records whether one or two FASTQ reads were found.
+
+    Args:
+        file_in (pathlib.Path): The given tabular samplesheet. The format can be either
+            CSV, TSV, or any other format automatically recognized by ``csv.Sniffer``.
+        file_out (pathlib.Path): Where the validated and transformed samplesheet should
+            be created; always in CSV format.
+
+    Example:
+        This function checks that the samplesheet follows the following structure,
+        see also the `viral recon samplesheet`_::
+
+            sample,fastq_1,fastq_2
+            SAMPLE_PE,SAMPLE_PE_RUN1_1.fastq.gz,SAMPLE_PE_RUN1_2.fastq.gz
+            SAMPLE_PE,SAMPLE_PE_RUN2_1.fastq.gz,SAMPLE_PE_RUN2_2.fastq.gz
+            SAMPLE_SE,SAMPLE_SE_RUN1_1.fastq.gz,
+
+    .. _viral recon samplesheet:
+        https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv
+
+    """
+    required_columns = {"sample", "fastq_1", "fastq_2"}
+    # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`.
+    with file_in.open(newline="") as in_handle:
+        reader = csv.DictReader(in_handle, dialect=sniff_format(in_handle))
+        # 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)}.")
+            sys.exit(1)
+        # Validate each row.
+        checker = RowChecker()
+        for i, row in enumerate(reader):
+            try:
+                checker.validate_and_transform(row)
+            except AssertionError as error:
+                logger.critical(f"{str(error)} On line {i + 2}.")
+                sys.exit(1)
+        checker.validate_unique_samples()
+    header = list(reader.fieldnames)
+    header.insert(1, "single_end")
+    # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`.
+    with file_out.open(mode="w", newline="") as out_handle:
+        writer = csv.DictWriter(out_handle, header, delimiter=",")
+        writer.writeheader()
+        for row in checker.modified:
+            writer.writerow(row)
+
+
+def parse_args(argv=None):
+    """Define and immediately parse command line arguments."""
+    parser = argparse.ArgumentParser(
+        description="Validate and transform a tabular samplesheet.",
+        epilog="Example: python check_samplesheet.py samplesheet.csv samplesheet.valid.csv",
+    )
+    parser.add_argument(
+        "file_in",
+        metavar="FILE_IN",
+        type=Path,
+        help="Tabular input samplesheet in CSV or TSV format.",
+    )
+    parser.add_argument(
+        "file_out",
+        metavar="FILE_OUT",
+        type=Path,
+        help="Transformed output samplesheet in CSV format.",
+    )
+    parser.add_argument(
+        "-l",
+        "--log-level",
+        help="The desired log level (default WARNING).",
+        choices=("CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"),
+        default="WARNING",
+    )
+    return parser.parse_args(argv)
+
+
+def main(argv=None):
+    """Coordinate argument parsing and program execution."""
+    args = parse_args(argv)
+    logging.basicConfig(level=args.log_level, format="[%(levelname)s] %(message)s")
+    if not args.file_in.is_file():
+        logger.error(f"The given input file {args.file_in} was not found!")
+        sys.exit(2)
+    args.file_out.parent.mkdir(parents=True, exist_ok=True)
+    check_samplesheet(args.file_in, args.file_out)
+
+
+if __name__ == "__main__":
+    sys.exit(main())
diff --git a/conf/base.config b/conf/base.config
new file mode 100644
index 00000000..c358798e
--- /dev/null
+++ b/conf/base.config
@@ -0,0 +1,65 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    sanger-tol/genomeassembly Nextflow base config file
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    A 'blank slate' config file, appropriate for general use on most high performance
+    compute environments. Assumes that all software is installed and available on
+    the PATH. Runs in `local` mode - all jobs will be run on the logged in environment.
+----------------------------------------------------------------------------------------
+*/
+
+process {
+
+    // TODO nf-core: Check the defaults for all processes
+    cpus   = { check_max( 1    * task.attempt, 'cpus'   ) }
+    memory = { check_max( 6.GB * task.attempt, 'memory' ) }
+    time   = { check_max( 4.h  * task.attempt, 'time'   ) }
+
+    errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' }
+    maxRetries    = 1
+    maxErrors     = '-1'
+
+    // Process-specific resource requirements
+    // NOTE - Please try and re-use the labels below as much as possible.
+    //        These labels are used and recognised by default in DSL2 files hosted on nf-core/modules.
+    //        If possible, it would be nice to keep the same label naming convention when
+    //        adding in your local modules too.
+    // TODO nf-core: Customise requirements for specific processes.
+    // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
+    withLabel:process_single {
+        cpus   = { check_max( 1    * task.attempt, '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'  ) }
+        time   = { check_max( 4.h   * task.attempt, 'time'    ) }
+    }
+    withLabel:process_medium {
+        cpus   = { check_max( 6     * task.attempt, 'cpus'    ) }
+        memory = { check_max( 36.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 8.h   * task.attempt, 'time'    ) }
+    }
+    withLabel:process_high {
+        cpus   = { check_max( 12    * task.attempt, 'cpus'    ) }
+        memory = { check_max( 72.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 16.h  * task.attempt, 'time'    ) }
+    }
+    withLabel:process_long {
+        time   = { check_max( 20.h  * task.attempt, 'time'    ) }
+    }
+    withLabel:process_high_memory {
+        memory = { check_max( 200.GB * task.attempt, 'memory' ) }
+    }
+    withLabel:error_ignore {
+        errorStrategy = 'ignore'
+    }
+    withLabel:error_retry {
+        errorStrategy = 'retry'
+        maxRetries    = 2
+    }
+    withName:CUSTOM_DUMPSOFTWAREVERSIONS {
+        cache = false
+    }
+}
diff --git a/conf/igenomes.config b/conf/igenomes.config
new file mode 100644
index 00000000..7a1b3ac6
--- /dev/null
+++ b/conf/igenomes.config
@@ -0,0 +1,432 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for iGenomes paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines reference genomes using iGenome paths.
+    Can be used by any config that customises the base path using:
+        $params.igenomes_base / --igenomes_base
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    // illumina iGenomes reference file paths
+    genomes {
+        'GRCh37' {
+            fasta       = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt"
+            mito_name   = "MT"
+            macs_gsize  = "2.7e9"
+            blacklist   = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed"
+        }
+        'GRCh38' {
+            fasta       = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed"
+            mito_name   = "chrM"
+            macs_gsize  = "2.7e9"
+            blacklist   = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
+        }
+        'GRCm38' {
+            fasta       = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt"
+            mito_name   = "MT"
+            macs_gsize  = "1.87e9"
+            blacklist   = "${projectDir}/assets/blacklists/GRCm38-blacklist.bed"
+        }
+        'TAIR10' {
+            fasta       = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt"
+            mito_name   = "Mt"
+        }
+        'EB2' {
+            fasta       = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/README.txt"
+        }
+        'UMD3.1' {
+            fasta       = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt"
+            mito_name   = "MT"
+        }
+        'WBcel235' {
+            fasta       = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed"
+            mito_name   = "MtDNA"
+            macs_gsize  = "9e7"
+        }
+        'CanFam3.1' {
+            fasta       = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt"
+            mito_name   = "MT"
+        }
+        'GRCz10' {
+            fasta       = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed"
+            mito_name   = "MT"
+        }
+        'BDGP6' {
+            fasta       = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed"
+            mito_name   = "M"
+            macs_gsize  = "1.2e8"
+        }
+        'EquCab2' {
+            fasta       = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/README.txt"
+            mito_name   = "MT"
+        }
+        'EB1' {
+            fasta       = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/README.txt"
+        }
+        'Galgal4' {
+            fasta       = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed"
+            mito_name   = "MT"
+        }
+        'Gm01' {
+            fasta       = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/README.txt"
+        }
+        'Mmul_1' {
+            fasta       = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt"
+            mito_name   = "MT"
+        }
+        'IRGSP-1.0' {
+            fasta       = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed"
+            mito_name   = "Mt"
+        }
+        'CHIMP2.1.4' {
+            fasta       = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt"
+            mito_name   = "MT"
+        }
+        'Rnor_5.0' {
+            fasta       = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.bed"
+            mito_name   = "MT"
+        }
+        'Rnor_6.0' {
+            fasta       = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed"
+            mito_name   = "MT"
+        }
+        'R64-1-1' {
+            fasta       = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed"
+            mito_name   = "MT"
+            macs_gsize  = "1.2e7"
+        }
+        'EF2' {
+            fasta       = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt"
+            mito_name   = "MT"
+            macs_gsize  = "1.21e7"
+        }
+        'Sbi1' {
+            fasta       = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/README.txt"
+        }
+        'Sscrofa10.2' {
+            fasta       = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/README.txt"
+            mito_name   = "MT"
+        }
+        'AGPv3' {
+            fasta       = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed"
+            mito_name   = "Mt"
+        }
+        'hg38' {
+            fasta       = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed"
+            mito_name   = "chrM"
+            macs_gsize  = "2.7e9"
+            blacklist   = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
+        }
+        'hg19' {
+            fasta       = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt"
+            mito_name   = "chrM"
+            macs_gsize  = "2.7e9"
+            blacklist   = "${projectDir}/assets/blacklists/hg19-blacklist.bed"
+        }
+        'mm10' {
+            fasta       = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt"
+            mito_name   = "chrM"
+            macs_gsize  = "1.87e9"
+            blacklist   = "${projectDir}/assets/blacklists/mm10-blacklist.bed"
+        }
+        'bosTau8' {
+            fasta       = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.bed"
+            mito_name   = "chrM"
+        }
+        'ce10' {
+            fasta       = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/README.txt"
+            mito_name   = "chrM"
+            macs_gsize  = "9e7"
+        }
+        'canFam3' {
+            fasta       = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt"
+            mito_name   = "chrM"
+        }
+        'danRer10' {
+            fasta       = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.bed"
+            mito_name   = "chrM"
+            macs_gsize  = "1.37e9"
+        }
+        'dm6' {
+            fasta       = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.bed"
+            mito_name   = "chrM"
+            macs_gsize  = "1.2e8"
+        }
+        'equCab2' {
+            fasta       = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/README.txt"
+            mito_name   = "chrM"
+        }
+        'galGal4' {
+            fasta       = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/README.txt"
+            mito_name   = "chrM"
+        }
+        'panTro4' {
+            fasta       = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/README.txt"
+            mito_name   = "chrM"
+        }
+        'rn6' {
+            fasta       = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.bed"
+            mito_name   = "chrM"
+        }
+        'sacCer3' {
+            fasta       = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BismarkIndex/"
+            readme      = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Annotation/README.txt"
+            mito_name   = "chrM"
+            macs_gsize  = "1.2e7"
+        }
+        'susScr3' {
+            fasta       = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BWAIndex/version0.6.0/"
+            bowtie2     = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/Bowtie2Index/"
+            star        = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/STARIndex/"
+            bismark     = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BismarkIndex/"
+            gtf         = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.gtf"
+            bed12       = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.bed"
+            readme      = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/README.txt"
+            mito_name   = "chrM"
+        }
+    }
+}
diff --git a/conf/modules.config b/conf/modules.config
new file mode 100644
index 00000000..da58a5d8
--- /dev/null
+++ b/conf/modules.config
@@ -0,0 +1,41 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config file for defining DSL2 per module options and publishing paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Available keys to override module options:
+        ext.args   = Additional arguments appended to command in module.
+        ext.args2  = Second set of arguments appended to command in module (multi-tool modules).
+        ext.args3  = Third set of arguments appended to command in module (multi-tool modules).
+        ext.prefix = File name prefix for output files.
+----------------------------------------------------------------------------------------
+*/
+
+process {
+
+    publishDir = [
+        path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+    ]
+
+    withName: SAMPLESHEET_CHECK {
+        publishDir = [
+            path: { "${params.outdir}/pipeline_info" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: FASTQC {
+        ext.args = '--quiet'
+    }
+
+    withName: CUSTOM_DUMPSOFTWAREVERSIONS {
+        publishDir = [
+            path: { "${params.outdir}/pipeline_info" },
+            mode: params.publish_dir_mode,
+            pattern: '*_versions.yml'
+        ]
+    }
+
+}
diff --git a/conf/test.config b/conf/test.config
new file mode 100644
index 00000000..7e606857
--- /dev/null
+++ b/conf/test.config
@@ -0,0 +1,29 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run sanger-tol/genomeassembly -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
+    // TODO nf-core: Give any required params for the test so that command line flags are not needed
+    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
+
+    // Genome references
+    genome = 'R64-1-1'
+}
diff --git a/conf/test_full.config b/conf/test_full.config
new file mode 100644
index 00000000..f5acd9dc
--- /dev/null
+++ b/conf/test_full.config
@@ -0,0 +1,24 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running full-size tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a full size pipeline test.
+
+    Use as follows:
+        nextflow run sanger-tol/genomeassembly -profile test_full,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Full test profile'
+    config_profile_description = 'Full test dataset to check pipeline function'
+
+    // Input data for full size test
+    // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA)
+    // TODO nf-core: Give any required params for the test so that command line flags are not needed
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv'
+
+    // Genome references
+    genome = 'R64-1-1'
+}
diff --git a/docs/README.md b/docs/README.md
new file mode 100644
index 00000000..df92463a
--- /dev/null
+++ b/docs/README.md
@@ -0,0 +1,8 @@
+# sanger-tol/genomeassembly: Documentation
+
+The sanger-tol/genomeassembly documentation is split into the following pages:
+
+- [Usage](usage.md)
+  - An overview of how the pipeline works, how to run it and a description of all of the different command-line flags.
+- [Output](output.md)
+  - An overview of the different results produced by the pipeline and how to interpret them.
diff --git a/docs/images/mqc_fastqc_adapter.png b/docs/images/mqc_fastqc_adapter.png
new file mode 100755
index 00000000..361d0e47
Binary files /dev/null and b/docs/images/mqc_fastqc_adapter.png differ
diff --git a/docs/images/mqc_fastqc_counts.png b/docs/images/mqc_fastqc_counts.png
new file mode 100755
index 00000000..cb39ebb8
Binary files /dev/null and b/docs/images/mqc_fastqc_counts.png differ
diff --git a/docs/images/mqc_fastqc_quality.png b/docs/images/mqc_fastqc_quality.png
new file mode 100755
index 00000000..a4b89bf5
Binary files /dev/null and b/docs/images/mqc_fastqc_quality.png differ
diff --git a/docs/output.md b/docs/output.md
new file mode 100644
index 00000000..da276a1e
--- /dev/null
+++ b/docs/output.md
@@ -0,0 +1,68 @@
+# sanger-tol/genomeassembly: Output
+
+## Introduction
+
+This document describes the output produced by the pipeline. Most of the plots are taken from the MultiQC report, which summarises results at the end of the pipeline.
+
+The directories listed below will be created in the results directory after the pipeline has finished. All paths are relative to the top-level results directory.
+
+<!-- TODO nf-core: Write this documentation describing your workflow's output -->
+
+## Pipeline overview
+
+The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
+
+- [FastQC](#fastqc) - Raw read QC
+- [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
+- [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
+
+### FastQC
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `fastqc/`
+  - `*_fastqc.html`: FastQC report containing quality metrics.
+  - `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images.
+
+</details>
+
+[FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
+
+![MultiQC - FastQC sequence counts plot](images/mqc_fastqc_counts.png)
+
+![MultiQC - FastQC mean quality scores plot](images/mqc_fastqc_quality.png)
+
+![MultiQC - FastQC adapter content plot](images/mqc_fastqc_adapter.png)
+
+> **NB:** The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They may contain adapter sequence and potentially regions with low quality.
+
+### MultiQC
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `multiqc/`
+  - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
+  - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
+  - `multiqc_plots/`: directory containing static images from the report in various formats.
+
+</details>
+
+[MultiQC](http://multiqc.info) is a visualization tool that generates a single HTML report summarising all samples in your project. Most of the pipeline QC results are visualised in the report and further statistics are available in the report data directory.
+
+Results generated by MultiQC collate pipeline QC from supported tools e.g. FastQC. The pipeline has special steps which also allow the software versions to be reported in the MultiQC output for future traceability. For more information about how to use MultiQC reports, see <http://multiqc.info>.
+
+### Pipeline information
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `pipeline_info/`
+  - Reports generated by Nextflow: `execution_report.html`, `execution_timeline.html`, `execution_trace.txt` and `pipeline_dag.dot`/`pipeline_dag.svg`.
+  - Reports generated by the pipeline: `pipeline_report.html`, `pipeline_report.txt` and `software_versions.yml`. The `pipeline_report*` files will only be present if the `--email` / `--email_on_fail` parameter's are used when running the pipeline.
+  - Reformatted samplesheet files used as input to the pipeline: `samplesheet.valid.csv`.
+
+</details>
+
+[Nextflow](https://www.nextflow.io/docs/latest/tracing.html) provides excellent functionality for generating various reports relevant to the running and execution of the pipeline. This will allow you to troubleshoot errors with the running of the pipeline, and also provide you with other information such as launch commands, run times and resource usage.
diff --git a/docs/usage.md b/docs/usage.md
new file mode 100644
index 00000000..4a51a186
--- /dev/null
+++ b/docs/usage.md
@@ -0,0 +1,254 @@
+# sanger-tol/genomeassembly: Usage
+
+> _Documentation of pipeline parameters is generated automatically from the pipeline schema and can no longer be found in markdown files._
+
+## Introduction
+
+<!-- TODO nf-core: Add documentation about anything specific to running your pipeline. For general topics, please point to (and add to) the main nf-core website. -->
+
+## Samplesheet input
+
+You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row as shown in the examples below.
+
+```console
+--input '[path to samplesheet file]'
+```
+
+### Multiple runs of the same sample
+
+The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 3 lanes:
+
+```console
+sample,fastq_1,fastq_2
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz
+CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz
+```
+
+### Full samplesheet
+
+The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. The samplesheet can have as many columns as you desire, however, there is a strict requirement for the first 3 columns to match those defined in the table below.
+
+A final samplesheet file consisting of both single- and paired-end data may look something like the one below. This is for 6 samples, where `TREATMENT_REP3` has been sequenced twice.
+
+```console
+sample,fastq_1,fastq_2
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+CONTROL_REP2,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz
+CONTROL_REP3,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz
+TREATMENT_REP1,AEG588A4_S4_L003_R1_001.fastq.gz,
+TREATMENT_REP2,AEG588A5_S5_L003_R1_001.fastq.gz,
+TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz,
+TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz,
+```
+
+| Column    | Description                                                                                                                                                                            |
+| --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `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 (`_`). |
+| `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
+| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
+
+An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
+
+## Running the pipeline
+
+The typical command for running the pipeline is as follows:
+
+```console
+nextflow run sanger-tol/genomeassembly --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile docker
+```
+
+This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles.
+
+Note that the pipeline will create the following files in your working directory:
+
+```console
+work                # Directory containing the nextflow working files
+<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.
+```
+
+### Updating the pipeline
+
+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
+nextflow pull sanger-tol/genomeassembly
+```
+
+### Reproducibility
+
+It is a good idea to specify a pipeline version when running the pipeline on your data. This ensures that a specific version of the pipeline code and software are used when you run your pipeline. If you keep using the same tag, you'll be running the same version of the pipeline, even if there have been changes to the code since.
+
+First, go to the [sanger-tol/genomeassembly releases page](https://github.com/sanger-tol/genomeassembly/releases) and find the latest version number - numeric only (eg. `1.3.1`). Then specify this when running the pipeline with `-r` (one hyphen) - eg. `-r 1.3.1`.
+
+This version number will be logged in reports when you run the pipeline, so that you'll know what you used when you look back in the future.
+
+## Core Nextflow arguments
+
+> **NB:** These options are part of Nextflow and use a _single_ hyphen (pipeline parameters use a double-hyphen).
+
+### `-profile`
+
+Use this parameter to choose a configuration profile. Profiles can give configuration presets for different compute environments.
+
+Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Conda) - see below. When using Biocontainers, most of these software packaging methods pull Docker containers from quay.io e.g [FastQC](https://quay.io/repository/biocontainers/fastqc) except for Singularity which directly downloads Singularity images via https hosted by the [Galaxy project](https://depot.galaxyproject.org/singularity/) and Conda which downloads and installs software locally from [Bioconda](https://bioconda.github.io/).
+
+> We highly recommend the use of Docker or Singularity containers for full pipeline reproducibility, however when this is not possible, Conda is also supported.
+
+The pipeline also dynamically loads configurations from [https://github.com/nf-core/configs](https://github.com/nf-core/configs) when it runs, making multiple config profiles for various institutional clusters available at run time. For more information and to see if your system is available in these configs please see the [nf-core/configs documentation](https://github.com/nf-core/configs#documentation).
+
+Note that multiple profiles can be loaded, for example: `-profile test,docker` - the order of arguments is important!
+They are loaded in sequence, so later profiles can overwrite earlier profiles.
+
+If `-profile` is not specified, the pipeline will run locally and expect all software to be installed and available on the `PATH`. This is _not_ recommended.
+
+- `docker`
+  - A generic configuration profile to be used with [Docker](https://docker.com/)
+- `singularity`
+  - A generic configuration profile to be used with [Singularity](https://sylabs.io/docs/)
+- `podman`
+  - A generic configuration profile to be used with [Podman](https://podman.io/)
+- `shifter`
+  - A generic configuration profile to be used with [Shifter](https://nersc.gitlab.io/development/shifter/how-to-use/)
+- `charliecloud`
+  - A generic configuration profile to be used with [Charliecloud](https://hpc.github.io/charliecloud/)
+- `conda`
+  - A generic configuration profile to be used with [Conda](https://conda.io/docs/). Please only use Conda as a last resort i.e. when it's not possible to run the pipeline with Docker, Singularity, Podman, Shifter or Charliecloud.
+- `test`
+  - A profile with a complete configuration for automated testing
+  - Includes links to test data so needs no other parameters
+
+### `-resume`
+
+Specify this when restarting a pipeline. Nextflow will use cached results from any pipeline steps where the inputs are the same, continuing from where it got to previously. For input to be considered the same, not only the names must be identical but the files' contents as well. For more info about this parameter, see [this blog post](https://www.nextflow.io/blog/2019/demystifying-nextflow-resume.html).
+
+You can also supply a run name to resume a specific run: `-resume [run-name]`. Use the `nextflow log` command to show previous run names.
+
+### `-c`
+
+Specify the path to a specific config file (this is a core Nextflow command). See the [nf-core website documentation](https://nf-co.re/usage/configuration) for more information.
+
+## Custom configuration
+
+### Resource requests
+
+Whilst the default requirements set within the pipeline will hopefully work for most people and with most input data, you may find that you want to customise the compute resources that the pipeline requests. Each step in the pipeline has a default set of requirements for number of CPUs, memory and time. For most of the steps in the pipeline, if the job exits with any of the error codes specified [here](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/base.config#L18) it will automatically be resubmitted with higher requests (2 x original, then 3 x original). If it still fails after the third attempt then the pipeline execution is stopped.
+
+For example, if the nf-core/rnaseq pipeline is failing after multiple re-submissions of the `STAR_ALIGN` process due to an exit code of `137` this would indicate that there is an out of memory issue:
+
+```console
+[62/149eb0] NOTE: Process `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137) -- Execution is retried (1)
+Error executing process > 'NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)'
+
+Caused by:
+    Process `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137)
+
+Command executed:
+    STAR \
+        --genomeDir star \
+        --readFilesIn WT_REP1_trimmed.fq.gz  \
+        --runThreadN 2 \
+        --outFileNamePrefix WT_REP1. \
+        <TRUNCATED>
+
+Command exit status:
+    137
+
+Command output:
+    (empty)
+
+Command error:
+    .command.sh: line 9:  30 Killed    STAR --genomeDir star --readFilesIn WT_REP1_trimmed.fq.gz --runThreadN 2 --outFileNamePrefix WT_REP1. <TRUNCATED>
+Work dir:
+    /home/pipelinetest/work/9d/172ca5881234073e8d76f2a19c88fb
+
+Tip: you can replicate the issue by changing to the process work dir and entering the command `bash .command.run`
+```
+
+To bypass this error you would need to find exactly which resources are set by the `STAR_ALIGN` process. The quickest way is to search for `process STAR_ALIGN` in the [nf-core/rnaseq Github repo](https://github.com/nf-core/rnaseq/search?q=process+STAR_ALIGN).
+We have standardised the structure of Nextflow DSL2 pipelines such that all module files will be present in the `modules/` directory and so, based on the search results, the file we want is `modules/nf-core/software/star/align/main.nf`.
+If you click on the link to that file you will notice that there is a `label` directive at the top of the module that is set to [`label process_high`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/modules/nf-core/software/star/align/main.nf#L9).
+The [Nextflow `label`](https://www.nextflow.io/docs/latest/process.html#label) directive allows us to organise workflow processes in separate groups which can be referenced in a configuration file to select and configure subset of processes having similar computing requirements.
+The default values for the `process_high` label are set in the pipeline's [`base.config`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/base.config#L33-L37) which in this case is defined as 72GB.
+Providing you haven't set any other standard nf-core parameters to **cap** the [maximum resources](https://nf-co.re/usage/configuration#max-resources) used by the pipeline then we can try and bypass the `STAR_ALIGN` process failure by creating a custom config file that sets at least 72GB of memory, in this case increased to 100GB.
+The custom config below can then be provided to the pipeline via the [`-c`](#-c) parameter as highlighted in previous sections.
+
+```nextflow
+process {
+    withName: 'NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN' {
+        memory = 100.GB
+    }
+}
+```
+
+> **NB:** We specify the full process name i.e. `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN` in the config file because this takes priority over the short name (`STAR_ALIGN`) and allows existing configuration using the full process name to be correctly overridden.
+>
+> If you get a warning suggesting that the process selector isn't recognised check that the process name has been specified correctly.
+
+### Updating containers
+
+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. If for some reason you need to use a different version of a particular tool with the pipeline then you just need to identify the `process` name and override the Nextflow `container` definition for that process using the `withName` declaration. For example, in the [nf-core/viralrecon](https://nf-co.re/viralrecon) pipeline a tool called [Pangolin](https://github.com/cov-lineages/pangolin) has been used during the COVID-19 pandemic to assign lineages to SARS-CoV-2 genome sequenced samples. Given that the lineage assignments change quite frequently it doesn't make sense to re-release the nf-core/viralrecon everytime a new version of Pangolin has been released. However, you can override the default container used by the pipeline by creating a custom config file and passing it as a command-line argument via `-c custom.config`.
+
+1. Check the default version used by the pipeline in the module file for [Pangolin](https://github.com/nf-core/viralrecon/blob/a85d5969f9025409e3618d6c280ef15ce417df65/modules/nf-core/software/pangolin/main.nf#L14-L19)
+2. Find the latest version of the Biocontainer available on [Quay.io](https://quay.io/repository/biocontainers/pangolin?tag=latest&tab=tags)
+3. Create the custom config accordingly:
+
+   - For Docker:
+
+     ```nextflow
+     process {
+         withName: PANGOLIN {
+             container = 'quay.io/biocontainers/pangolin:3.0.5--pyhdfd78af_0'
+         }
+     }
+     ```
+
+   - For Singularity:
+
+     ```nextflow
+     process {
+         withName: PANGOLIN {
+             container = 'https://depot.galaxyproject.org/singularity/pangolin:3.0.5--pyhdfd78af_0'
+         }
+     }
+     ```
+
+   - For Conda:
+
+     ```nextflow
+     process {
+         withName: PANGOLIN {
+             conda = 'bioconda::pangolin=3.0.5'
+         }
+     }
+     ```
+
+> **NB:** If you wish to periodically update individual tool-specific results (e.g. Pangolin) generated by the pipeline then you must ensure to keep the `work/` directory otherwise the `-resume` ability of the pipeline will be compromised and it will restart from scratch.
+
+### nf-core/configs
+
+In most cases, you will only need to create a custom config as a one-off but if you and others within your organisation are likely to be running nf-core pipelines regularly and need to use the same settings regularly it may be a good idea to request that your custom config file is uploaded to the `nf-core/configs` git repository. Before you do this please can you test that the config file works with your pipeline of choice using the `-c` parameter. You can then create a pull request to the `nf-core/configs` repository with the addition of your config file, associated documentation file (see examples in [`nf-core/configs/docs`](https://github.com/nf-core/configs/tree/master/docs)), and amending [`nfcore_custom.config`](https://github.com/nf-core/configs/blob/master/nfcore_custom.config) to include your custom profile.
+
+See the main [Nextflow documentation](https://www.nextflow.io/docs/latest/config.html) for more information about creating your own configuration files.
+
+If you have any questions or issues please send us a message on [Slack](https://nf-co.re/join/slack) on the [`#configs` channel](https://nfcore.slack.com/channels/configs).
+
+## Running in the background
+
+Nextflow handles job submissions and supervises the running jobs. The Nextflow process must run until the pipeline is finished.
+
+The Nextflow `-bg` flag launches Nextflow in the background, detached from your terminal so that the workflow does not stop if you log out of your session. The logs are saved to a file.
+
+Alternatively, you can use `screen` / `tmux` or similar tool to create a detached session which you can log back into at a later time.
+Some HPC setups also allow you to run nextflow within a cluster job submitted your job scheduler (from where it submits more jobs).
+
+## Nextflow memory requirements
+
+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
+NXF_OPTS='-Xms1g -Xmx4g'
+```
diff --git a/lib/NfcoreSchema.groovy b/lib/NfcoreSchema.groovy
new file mode 100755
index 00000000..b3d092f8
--- /dev/null
+++ b/lib/NfcoreSchema.groovy
@@ -0,0 +1,529 @@
+//
+// This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template.
+//
+
+import org.everit.json.schema.Schema
+import org.everit.json.schema.loader.SchemaLoader
+import org.everit.json.schema.ValidationException
+import org.json.JSONObject
+import org.json.JSONTokener
+import org.json.JSONArray
+import groovy.json.JsonSlurper
+import groovy.json.JsonBuilder
+
+class NfcoreSchema {
+
+    //
+    // Resolve Schema path relative to main workflow directory
+    //
+    public static String getSchemaPath(workflow, schema_filename='nextflow_schema.json') {
+        return "${workflow.projectDir}/${schema_filename}"
+    }
+
+    //
+    // Function to loop over all parameters defined in schema and check
+    // whether the given parameters adhere to the specifications
+    //
+    /* groovylint-disable-next-line UnusedPrivateMethodParameter */
+    public static void validateParameters(workflow, params, log, schema_filename='nextflow_schema.json') {
+        def has_error = false
+        //~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~//
+        // Check for nextflow core params and unexpected params
+        def json = new File(getSchemaPath(workflow, schema_filename=schema_filename)).text
+        def Map schemaParams = (Map) new JsonSlurper().parseText(json).get('definitions')
+        def nf_params = [
+            // Options for base `nextflow` command
+            'bg',
+            'c',
+            'C',
+            'config',
+            'd',
+            'D',
+            'dockerize',
+            'h',
+            'log',
+            'q',
+            'quiet',
+            'syslog',
+            'v',
+            'version',
+
+            // Options for `nextflow run` command
+            'ansi',
+            'ansi-log',
+            'bg',
+            'bucket-dir',
+            'c',
+            'cache',
+            'config',
+            'dsl2',
+            'dump-channels',
+            'dump-hashes',
+            'E',
+            'entry',
+            'latest',
+            'lib',
+            'main-script',
+            'N',
+            'name',
+            'offline',
+            'params-file',
+            'pi',
+            'plugins',
+            'poll-interval',
+            'pool-size',
+            'profile',
+            'ps',
+            'qs',
+            'queue-size',
+            'r',
+            'resume',
+            'revision',
+            'stdin',
+            'stub',
+            'stub-run',
+            'test',
+            'w',
+            'with-charliecloud',
+            'with-conda',
+            'with-dag',
+            'with-docker',
+            'with-mpi',
+            'with-notification',
+            'with-podman',
+            'with-report',
+            'with-singularity',
+            'with-timeline',
+            'with-tower',
+            'with-trace',
+            'with-weblog',
+            'without-docker',
+            'without-podman',
+            'work-dir'
+        ]
+        def unexpectedParams = []
+
+        // Collect expected parameters from the schema
+        def expectedParams = []
+        def enums = [:]
+        for (group in schemaParams) {
+            for (p in group.value['properties']) {
+                expectedParams.push(p.key)
+                if (group.value['properties'][p.key].containsKey('enum')) {
+                    enums[p.key] = group.value['properties'][p.key]['enum']
+                }
+            }
+        }
+
+        for (specifiedParam in params.keySet()) {
+            // nextflow params
+            if (nf_params.contains(specifiedParam)) {
+                log.error "ERROR: You used a core Nextflow option with two hyphens: '--${specifiedParam}'. Please resubmit with '-${specifiedParam}'"
+                has_error = true
+            }
+            // unexpected params
+            def params_ignore = params.schema_ignore_params.split(',') + 'schema_ignore_params'
+            def expectedParamsLowerCase = expectedParams.collect{ it.replace("-", "").toLowerCase() }
+            def specifiedParamLowerCase = specifiedParam.replace("-", "").toLowerCase()
+            def isCamelCaseBug = (specifiedParam.contains("-") && !expectedParams.contains(specifiedParam) && expectedParamsLowerCase.contains(specifiedParamLowerCase))
+            if (!expectedParams.contains(specifiedParam) && !params_ignore.contains(specifiedParam) && !isCamelCaseBug) {
+                // Temporarily remove camelCase/camel-case params #1035
+                def unexpectedParamsLowerCase = unexpectedParams.collect{ it.replace("-", "").toLowerCase()}
+                if (!unexpectedParamsLowerCase.contains(specifiedParamLowerCase)){
+                    unexpectedParams.push(specifiedParam)
+                }
+            }
+        }
+
+        //~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~//
+        // Validate parameters against the schema
+        InputStream input_stream = new File(getSchemaPath(workflow, schema_filename=schema_filename)).newInputStream()
+        JSONObject raw_schema = new JSONObject(new JSONTokener(input_stream))
+
+        // Remove anything that's in params.schema_ignore_params
+        raw_schema = removeIgnoredParams(raw_schema, params)
+
+        Schema schema = SchemaLoader.load(raw_schema)
+
+        // Clean the parameters
+        def cleanedParams = cleanParameters(params)
+
+        // Convert to JSONObject
+        def jsonParams = new JsonBuilder(cleanedParams)
+        JSONObject params_json = new JSONObject(jsonParams.toString())
+
+        // Validate
+        try {
+            schema.validate(params_json)
+        } catch (ValidationException e) {
+            println ''
+            log.error 'ERROR: Validation of pipeline parameters failed!'
+            JSONObject exceptionJSON = e.toJSON()
+            printExceptions(exceptionJSON, params_json, log, enums)
+            println ''
+            has_error = true
+        }
+
+        // Check for unexpected parameters
+        if (unexpectedParams.size() > 0) {
+            Map colors = NfcoreTemplate.logColours(params.monochrome_logs)
+            println ''
+            def warn_msg = 'Found unexpected parameters:'
+            for (unexpectedParam in unexpectedParams) {
+                warn_msg = warn_msg + "\n* --${unexpectedParam}: ${params[unexpectedParam].toString()}"
+            }
+            log.warn warn_msg
+            log.info "- ${colors.dim}Ignore this warning: params.schema_ignore_params = \"${unexpectedParams.join(',')}\" ${colors.reset}"
+            println ''
+        }
+
+        if (has_error) {
+            System.exit(1)
+        }
+    }
+
+    //
+    // Beautify parameters for --help
+    //
+    public static String paramsHelp(workflow, params, command, schema_filename='nextflow_schema.json') {
+        Map colors = NfcoreTemplate.logColours(params.monochrome_logs)
+        Integer num_hidden = 0
+        String output  = ''
+        output        += 'Typical pipeline command:\n\n'
+        output        += "  ${colors.cyan}${command}${colors.reset}\n\n"
+        Map params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename))
+        Integer max_chars  = paramsMaxChars(params_map) + 1
+        Integer desc_indent = max_chars + 14
+        Integer dec_linewidth = 160 - desc_indent
+        for (group in params_map.keySet()) {
+            Integer num_params = 0
+            String group_output = colors.underlined + colors.bold + group + colors.reset + '\n'
+            def group_params = params_map.get(group)  // This gets the parameters of that particular group
+            for (param in group_params.keySet()) {
+                if (group_params.get(param).hidden && !params.show_hidden_params) {
+                    num_hidden += 1
+                    continue;
+                }
+                def type = '[' + group_params.get(param).type + ']'
+                def description = group_params.get(param).description
+                def defaultValue = group_params.get(param).default != null ? " [default: " + group_params.get(param).default.toString() + "]" : ''
+                def description_default = description + colors.dim + defaultValue + colors.reset
+                // Wrap long description texts
+                // Loosely based on https://dzone.com/articles/groovy-plain-text-word-wrap
+                if (description_default.length() > dec_linewidth){
+                    List olines = []
+                    String oline = "" // " " * indent
+                    description_default.split(" ").each() { wrd ->
+                        if ((oline.size() + wrd.size()) <= dec_linewidth) {
+                            oline += wrd + " "
+                        } else {
+                            olines += oline
+                            oline = wrd + " "
+                        }
+                    }
+                    olines += oline
+                    description_default = olines.join("\n" + " " * desc_indent)
+                }
+                group_output += "  --" +  param.padRight(max_chars) + colors.dim + type.padRight(10) + colors.reset + description_default + '\n'
+                num_params += 1
+            }
+            group_output += '\n'
+            if (num_params > 0){
+                output += group_output
+            }
+        }
+        if (num_hidden > 0){
+            output += colors.dim + "!! Hiding $num_hidden params, use --show_hidden_params to show them !!\n" + colors.reset
+        }
+        output += NfcoreTemplate.dashedLine(params.monochrome_logs)
+        return output
+    }
+
+    //
+    // Groovy Map summarising parameters/workflow options used by the pipeline
+    //
+    public static LinkedHashMap paramsSummaryMap(workflow, params, schema_filename='nextflow_schema.json') {
+        // Get a selection of core Nextflow workflow options
+        def Map workflow_summary = [:]
+        if (workflow.revision) {
+            workflow_summary['revision'] = workflow.revision
+        }
+        workflow_summary['runName']      = workflow.runName
+        if (workflow.containerEngine) {
+            workflow_summary['containerEngine'] = workflow.containerEngine
+        }
+        if (workflow.container) {
+            workflow_summary['container'] = workflow.container
+        }
+        workflow_summary['launchDir']    = workflow.launchDir
+        workflow_summary['workDir']      = workflow.workDir
+        workflow_summary['projectDir']   = workflow.projectDir
+        workflow_summary['userName']     = workflow.userName
+        workflow_summary['profile']      = workflow.profile
+        workflow_summary['configFiles']  = workflow.configFiles.join(', ')
+
+        // Get pipeline parameters defined in JSON Schema
+        def Map params_summary = [:]
+        def params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename))
+        for (group in params_map.keySet()) {
+            def sub_params = new LinkedHashMap()
+            def group_params = params_map.get(group)  // This gets the parameters of that particular group
+            for (param in group_params.keySet()) {
+                if (params.containsKey(param)) {
+                    def params_value = params.get(param)
+                    def schema_value = group_params.get(param).default
+                    def param_type   = group_params.get(param).type
+                    if (schema_value != null) {
+                        if (param_type == 'string') {
+                            if (schema_value.contains('$projectDir') || schema_value.contains('${projectDir}')) {
+                                def sub_string = schema_value.replace('\$projectDir', '')
+                                sub_string     = sub_string.replace('\${projectDir}', '')
+                                if (params_value.contains(sub_string)) {
+                                    schema_value = params_value
+                                }
+                            }
+                            if (schema_value.contains('$params.outdir') || schema_value.contains('${params.outdir}')) {
+                                def sub_string = schema_value.replace('\$params.outdir', '')
+                                sub_string     = sub_string.replace('\${params.outdir}', '')
+                                if ("${params.outdir}${sub_string}" == params_value) {
+                                    schema_value = params_value
+                                }
+                            }
+                        }
+                    }
+
+                    // We have a default in the schema, and this isn't it
+                    if (schema_value != null && params_value != schema_value) {
+                        sub_params.put(param, params_value)
+                    }
+                    // No default in the schema, and this isn't empty
+                    else if (schema_value == null && params_value != "" && params_value != null && params_value != false) {
+                        sub_params.put(param, params_value)
+                    }
+                }
+            }
+            params_summary.put(group, sub_params)
+        }
+        return [ 'Core Nextflow options' : workflow_summary ] << params_summary
+    }
+
+    //
+    // Beautify parameters for summary and return as string
+    //
+    public static String paramsSummaryLog(workflow, params) {
+        Map colors = NfcoreTemplate.logColours(params.monochrome_logs)
+        String output  = ''
+        def params_map = paramsSummaryMap(workflow, params)
+        def max_chars  = paramsMaxChars(params_map)
+        for (group in params_map.keySet()) {
+            def group_params = params_map.get(group)  // This gets the parameters of that particular group
+            if (group_params) {
+                output += colors.bold + group + colors.reset + '\n'
+                for (param in group_params.keySet()) {
+                    output += "  " + colors.blue + param.padRight(max_chars) + ": " + colors.green +  group_params.get(param) + colors.reset + '\n'
+                }
+                output += '\n'
+            }
+        }
+        output += "!! Only displaying parameters that differ from the pipeline defaults !!\n"
+        output += NfcoreTemplate.dashedLine(params.monochrome_logs)
+        return output
+    }
+
+    //
+    // Loop over nested exceptions and print the causingException
+    //
+    private static void printExceptions(ex_json, params_json, log, enums, limit=5) {
+        def causingExceptions = ex_json['causingExceptions']
+        if (causingExceptions.length() == 0) {
+            def m = ex_json['message'] =~ /required key \[([^\]]+)\] not found/
+            // Missing required param
+            if (m.matches()) {
+                log.error "* Missing required parameter: --${m[0][1]}"
+            }
+            // Other base-level error
+            else if (ex_json['pointerToViolation'] == '#') {
+                log.error "* ${ex_json['message']}"
+            }
+            // Error with specific param
+            else {
+                def param = ex_json['pointerToViolation'] - ~/^#\//
+                def param_val = params_json[param].toString()
+                if (enums.containsKey(param)) {
+                    def error_msg = "* --${param}: '${param_val}' is not a valid choice (Available choices"
+                    if (enums[param].size() > limit) {
+                        log.error "${error_msg} (${limit} of ${enums[param].size()}): ${enums[param][0..limit-1].join(', ')}, ... )"
+                    } else {
+                        log.error "${error_msg}: ${enums[param].join(', ')})"
+                    }
+                } else {
+                    log.error "* --${param}: ${ex_json['message']} (${param_val})"
+                }
+            }
+        }
+        for (ex in causingExceptions) {
+            printExceptions(ex, params_json, log, enums)
+        }
+    }
+
+    //
+    // Remove an element from a JSONArray
+    //
+    private static JSONArray removeElement(json_array, element) {
+        def list = []
+        int len = json_array.length()
+        for (int i=0;i<len;i++){
+            list.add(json_array.get(i).toString())
+        }
+        list.remove(element)
+        JSONArray jsArray = new JSONArray(list)
+        return jsArray
+    }
+
+    //
+    // Remove ignored parameters
+    //
+    private static JSONObject removeIgnoredParams(raw_schema, params) {
+        // Remove anything that's in params.schema_ignore_params
+        params.schema_ignore_params.split(',').each{ ignore_param ->
+            if(raw_schema.keySet().contains('definitions')){
+                raw_schema.definitions.each { definition ->
+                    for (key in definition.keySet()){
+                        if (definition[key].get("properties").keySet().contains(ignore_param)){
+                            // Remove the param to ignore
+                            definition[key].get("properties").remove(ignore_param)
+                            // If the param was required, change this
+                            if (definition[key].has("required")) {
+                                def cleaned_required = removeElement(definition[key].required, ignore_param)
+                                definition[key].put("required", cleaned_required)
+                            }
+                        }
+                    }
+                }
+            }
+            if(raw_schema.keySet().contains('properties') && raw_schema.get('properties').keySet().contains(ignore_param)) {
+                raw_schema.get("properties").remove(ignore_param)
+            }
+            if(raw_schema.keySet().contains('required') && raw_schema.required.contains(ignore_param)) {
+                def cleaned_required = removeElement(raw_schema.required, ignore_param)
+                raw_schema.put("required", cleaned_required)
+            }
+        }
+        return raw_schema
+    }
+
+    //
+    // Clean and check parameters relative to Nextflow native classes
+    //
+    private static Map cleanParameters(params) {
+        def new_params = params.getClass().newInstance(params)
+        for (p in params) {
+            // remove anything evaluating to false
+            if (!p['value']) {
+                new_params.remove(p.key)
+            }
+            // Cast MemoryUnit to String
+            if (p['value'].getClass() == nextflow.util.MemoryUnit) {
+                new_params.replace(p.key, p['value'].toString())
+            }
+            // Cast Duration to String
+            if (p['value'].getClass() == nextflow.util.Duration) {
+                new_params.replace(p.key, p['value'].toString().replaceFirst(/d(?!\S)/, "day"))
+            }
+            // Cast LinkedHashMap to String
+            if (p['value'].getClass() == LinkedHashMap) {
+                new_params.replace(p.key, p['value'].toString())
+            }
+        }
+        return new_params
+    }
+
+    //
+    // This function tries to read a JSON params file
+    //
+    private static LinkedHashMap paramsLoad(String json_schema) {
+        def params_map = new LinkedHashMap()
+        try {
+            params_map = paramsRead(json_schema)
+        } catch (Exception e) {
+            println "Could not read parameters settings from JSON. $e"
+            params_map = new LinkedHashMap()
+        }
+        return params_map
+    }
+
+    //
+    // Method to actually read in JSON file using Groovy.
+    // Group (as Key), values are all parameters
+    //    - Parameter1 as Key, Description as Value
+    //    - Parameter2 as Key, Description as Value
+    //    ....
+    // Group
+    //    -
+    private static LinkedHashMap paramsRead(String json_schema) throws Exception {
+        def json = new File(json_schema).text
+        def Map schema_definitions = (Map) new JsonSlurper().parseText(json).get('definitions')
+        def Map schema_properties = (Map) new JsonSlurper().parseText(json).get('properties')
+        /* Tree looks like this in nf-core schema
+        * definitions <- this is what the first get('definitions') gets us
+                group 1
+                    title
+                    description
+                        properties
+                        parameter 1
+                            type
+                            description
+                        parameter 2
+                            type
+                            description
+                group 2
+                    title
+                    description
+                        properties
+                        parameter 1
+                            type
+                            description
+        * properties <- parameters can also be ungrouped, outside of definitions
+                parameter 1
+                    type
+                    description
+        */
+
+        // Grouped params
+        def params_map = new LinkedHashMap()
+        schema_definitions.each { key, val ->
+            def Map group = schema_definitions."$key".properties // Gets the property object of the group
+            def title = schema_definitions."$key".title
+            def sub_params = new LinkedHashMap()
+            group.each { innerkey, value ->
+                sub_params.put(innerkey, value)
+            }
+            params_map.put(title, sub_params)
+        }
+
+        // Ungrouped params
+        def ungrouped_params = new LinkedHashMap()
+        schema_properties.each { innerkey, value ->
+            ungrouped_params.put(innerkey, value)
+        }
+        params_map.put("Other parameters", ungrouped_params)
+
+        return params_map
+    }
+
+    //
+    // Get maximum number of characters across all parameter names
+    //
+    private static Integer paramsMaxChars(params_map) {
+        Integer max_chars = 0
+        for (group in params_map.keySet()) {
+            def group_params = params_map.get(group)  // This gets the parameters of that particular group
+            for (param in group_params.keySet()) {
+                if (param.size() > max_chars) {
+                    max_chars = param.size()
+                }
+            }
+        }
+        return max_chars
+    }
+}
diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy
new file mode 100755
index 00000000..8f857360
--- /dev/null
+++ b/lib/NfcoreTemplate.groovy
@@ -0,0 +1,253 @@
+//
+// This file holds several functions used within the nf-core pipeline template.
+//
+
+import org.yaml.snakeyaml.Yaml
+
+class NfcoreTemplate {
+
+    //
+    // Check AWS Batch related parameters have been specified correctly
+    //
+    public static void awsBatch(workflow, params) {
+        if (workflow.profile.contains('awsbatch')) {
+            // Check params.awsqueue and params.awsregion have been set if running on AWSBatch
+            assert (params.awsqueue && params.awsregion) : "Specify correct --awsqueue and --awsregion parameters on AWSBatch!"
+            // Check outdir paths to be S3 buckets if running on AWSBatch
+            assert params.outdir.startsWith('s3:')       : "Outdir not on S3 - specify S3 Bucket to run on AWSBatch!"
+        }
+    }
+
+    //
+    //  Warn if a -profile or Nextflow config has not been provided to run the pipeline
+    //
+    public static void checkConfigProvided(workflow, log) {
+        if (workflow.profile == 'standard' && workflow.configFiles.size() <= 1) {
+            log.warn "[$workflow.manifest.name] You are attempting to run the pipeline without any custom configuration!\n\n" +
+                    "This will be dependent on your local compute environment but can be achieved via one or more of the following:\n" +
+                    "   (1) Using an existing pipeline profile e.g. `-profile docker` or `-profile singularity`\n" +
+                    "   (2) Using an existing nf-core/configs for your Institution e.g. `-profile crick` or `-profile uppmax`\n" +
+                    "   (3) Using your own local custom config e.g. `-c /path/to/your/custom.config`\n\n" +
+                    "Please refer to the quick start section and usage docs for the pipeline.\n "
+        }
+    }
+
+    //
+    // Construct and send completion email
+    //
+    public static void email(workflow, params, summary_params, projectDir, log, multiqc_report=[]) {
+
+        // Set up the e-mail variables
+        def subject = "[$workflow.manifest.name] Successful: $workflow.runName"
+        if (!workflow.success) {
+            subject = "[$workflow.manifest.name] FAILED: $workflow.runName"
+        }
+
+        def summary = [:]
+        for (group in summary_params.keySet()) {
+            summary << summary_params[group]
+        }
+
+        def misc_fields = [:]
+        misc_fields['Date Started']              = workflow.start
+        misc_fields['Date Completed']            = workflow.complete
+        misc_fields['Pipeline script file path'] = workflow.scriptFile
+        misc_fields['Pipeline script hash ID']   = workflow.scriptId
+        if (workflow.repository) misc_fields['Pipeline repository Git URL']    = workflow.repository
+        if (workflow.commitId)   misc_fields['Pipeline repository Git Commit'] = workflow.commitId
+        if (workflow.revision)   misc_fields['Pipeline Git branch/tag']        = workflow.revision
+        misc_fields['Nextflow Version']           = workflow.nextflow.version
+        misc_fields['Nextflow Build']             = workflow.nextflow.build
+        misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp
+
+        def email_fields = [:]
+        email_fields['version']      = workflow.manifest.version
+        email_fields['runName']      = workflow.runName
+        email_fields['success']      = workflow.success
+        email_fields['dateComplete'] = workflow.complete
+        email_fields['duration']     = workflow.duration
+        email_fields['exitStatus']   = workflow.exitStatus
+        email_fields['errorMessage'] = (workflow.errorMessage ?: 'None')
+        email_fields['errorReport']  = (workflow.errorReport ?: 'None')
+        email_fields['commandLine']  = workflow.commandLine
+        email_fields['projectDir']   = workflow.projectDir
+        email_fields['summary']      = summary << misc_fields
+
+        // On success try attach the multiqc report
+        def mqc_report = null
+        try {
+            if (workflow.success) {
+                mqc_report = multiqc_report.getVal()
+                if (mqc_report.getClass() == ArrayList && mqc_report.size() >= 1) {
+                    if (mqc_report.size() > 1) {
+                        log.warn "[$workflow.manifest.name] Found multiple reports from process 'MULTIQC', will use only one"
+                    }
+                    mqc_report = mqc_report[0]
+                }
+            }
+        } catch (all) {
+            if (multiqc_report) {
+                log.warn "[$workflow.manifest.name] Could not attach MultiQC report to summary email"
+            }
+        }
+
+        // Check if we are only sending emails on failure
+        def email_address = params.email
+        if (!params.email && params.email_on_fail && !workflow.success) {
+            email_address = params.email_on_fail
+        }
+
+        // Render the TXT template
+        def engine       = new groovy.text.GStringTemplateEngine()
+        def tf           = new File("$projectDir/assets/email_template.txt")
+        def txt_template = engine.createTemplate(tf).make(email_fields)
+        def email_txt    = txt_template.toString()
+
+        // Render the HTML template
+        def hf            = new File("$projectDir/assets/email_template.html")
+        def html_template = engine.createTemplate(hf).make(email_fields)
+        def email_html    = html_template.toString()
+
+        // Render the sendmail template
+        def max_multiqc_email_size = params.max_multiqc_email_size as nextflow.util.MemoryUnit
+        def smail_fields           = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ]
+        def sf                     = new File("$projectDir/assets/sendmail_template.txt")
+        def sendmail_template      = engine.createTemplate(sf).make(smail_fields)
+        def sendmail_html          = sendmail_template.toString()
+
+        // Send the HTML e-mail
+        Map colors = logColours(params.monochrome_logs)
+        if (email_address) {
+            try {
+                if (params.plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') }
+                // Try to send HTML e-mail using sendmail
+                [ 'sendmail', '-t' ].execute() << sendmail_html
+                log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-"
+            } catch (all) {
+                // Catch failures and try with plaintext
+                def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ]
+                if ( mqc_report.size() <= max_multiqc_email_size.toBytes() ) {
+                    mail_cmd += [ '-A', mqc_report ]
+                }
+                mail_cmd.execute() << email_html
+                log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (mail)-"
+            }
+        }
+
+        // Write summary e-mail HTML to a file
+        def output_d = new File("${params.outdir}/pipeline_info/")
+        if (!output_d.exists()) {
+            output_d.mkdirs()
+        }
+        def output_hf = new File(output_d, "pipeline_report.html")
+        output_hf.withWriter { w -> w << email_html }
+        def output_tf = new File(output_d, "pipeline_report.txt")
+        output_tf.withWriter { w -> w << email_txt }
+    }
+
+    //
+    // Print pipeline summary on completion
+    //
+    public static void summary(workflow, params, log) {
+        Map colors = logColours(params.monochrome_logs)
+        if (workflow.success) {
+            if (workflow.stats.ignoredCount == 0) {
+                log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Pipeline completed successfully${colors.reset}-"
+            } else {
+                log.info "-${colors.purple}[$workflow.manifest.name]${colors.red} Pipeline completed successfully, but with errored process(es) ${colors.reset}-"
+            }
+        } else {
+            log.info "-${colors.purple}[$workflow.manifest.name]${colors.red} Pipeline completed with errors${colors.reset}-"
+        }
+    }
+
+    //
+    // ANSII Colours used for terminal logging
+    //
+    public static Map logColours(Boolean monochrome_logs) {
+        Map colorcodes = [:]
+
+        // Reset / Meta
+        colorcodes['reset']      = monochrome_logs ? '' : "\033[0m"
+        colorcodes['bold']       = monochrome_logs ? '' : "\033[1m"
+        colorcodes['dim']        = monochrome_logs ? '' : "\033[2m"
+        colorcodes['underlined'] = monochrome_logs ? '' : "\033[4m"
+        colorcodes['blink']      = monochrome_logs ? '' : "\033[5m"
+        colorcodes['reverse']    = monochrome_logs ? '' : "\033[7m"
+        colorcodes['hidden']     = monochrome_logs ? '' : "\033[8m"
+
+        // Regular Colors
+        colorcodes['black']      = monochrome_logs ? '' : "\033[0;30m"
+        colorcodes['red']        = monochrome_logs ? '' : "\033[0;31m"
+        colorcodes['green']      = monochrome_logs ? '' : "\033[0;32m"
+        colorcodes['yellow']     = monochrome_logs ? '' : "\033[0;33m"
+        colorcodes['blue']       = monochrome_logs ? '' : "\033[0;34m"
+        colorcodes['purple']     = monochrome_logs ? '' : "\033[0;35m"
+        colorcodes['cyan']       = monochrome_logs ? '' : "\033[0;36m"
+        colorcodes['white']      = monochrome_logs ? '' : "\033[0;37m"
+
+        // Bold
+        colorcodes['bblack']     = monochrome_logs ? '' : "\033[1;30m"
+        colorcodes['bred']       = monochrome_logs ? '' : "\033[1;31m"
+        colorcodes['bgreen']     = monochrome_logs ? '' : "\033[1;32m"
+        colorcodes['byellow']    = monochrome_logs ? '' : "\033[1;33m"
+        colorcodes['bblue']      = monochrome_logs ? '' : "\033[1;34m"
+        colorcodes['bpurple']    = monochrome_logs ? '' : "\033[1;35m"
+        colorcodes['bcyan']      = monochrome_logs ? '' : "\033[1;36m"
+        colorcodes['bwhite']     = monochrome_logs ? '' : "\033[1;37m"
+
+        // Underline
+        colorcodes['ublack']     = monochrome_logs ? '' : "\033[4;30m"
+        colorcodes['ured']       = monochrome_logs ? '' : "\033[4;31m"
+        colorcodes['ugreen']     = monochrome_logs ? '' : "\033[4;32m"
+        colorcodes['uyellow']    = monochrome_logs ? '' : "\033[4;33m"
+        colorcodes['ublue']      = monochrome_logs ? '' : "\033[4;34m"
+        colorcodes['upurple']    = monochrome_logs ? '' : "\033[4;35m"
+        colorcodes['ucyan']      = monochrome_logs ? '' : "\033[4;36m"
+        colorcodes['uwhite']     = monochrome_logs ? '' : "\033[4;37m"
+
+        // High Intensity
+        colorcodes['iblack']     = monochrome_logs ? '' : "\033[0;90m"
+        colorcodes['ired']       = monochrome_logs ? '' : "\033[0;91m"
+        colorcodes['igreen']     = monochrome_logs ? '' : "\033[0;92m"
+        colorcodes['iyellow']    = monochrome_logs ? '' : "\033[0;93m"
+        colorcodes['iblue']      = monochrome_logs ? '' : "\033[0;94m"
+        colorcodes['ipurple']    = monochrome_logs ? '' : "\033[0;95m"
+        colorcodes['icyan']      = monochrome_logs ? '' : "\033[0;96m"
+        colorcodes['iwhite']     = monochrome_logs ? '' : "\033[0;97m"
+
+        // Bold High Intensity
+        colorcodes['biblack']    = monochrome_logs ? '' : "\033[1;90m"
+        colorcodes['bired']      = monochrome_logs ? '' : "\033[1;91m"
+        colorcodes['bigreen']    = monochrome_logs ? '' : "\033[1;92m"
+        colorcodes['biyellow']   = monochrome_logs ? '' : "\033[1;93m"
+        colorcodes['biblue']     = monochrome_logs ? '' : "\033[1;94m"
+        colorcodes['bipurple']   = monochrome_logs ? '' : "\033[1;95m"
+        colorcodes['bicyan']     = monochrome_logs ? '' : "\033[1;96m"
+        colorcodes['biwhite']    = monochrome_logs ? '' : "\033[1;97m"
+
+        return colorcodes
+    }
+
+    //
+    // Does what is says on the tin
+    //
+    public static String dashedLine(monochrome_logs) {
+        Map colors = logColours(monochrome_logs)
+        return "-${colors.dim}----------------------------------------------------${colors.reset}-"
+    }
+
+    //
+    // nf-core logo
+    //
+    public static String logo(workflow, monochrome_logs) {
+        Map colors = logColours(monochrome_logs)
+        String.format(
+            """\n
+            ${dashedLine(monochrome_logs)}
+            ${colors.purple}  ${workflow.manifest.name} v${workflow.manifest.version}${colors.reset}
+            ${dashedLine(monochrome_logs)}
+            """.stripIndent()
+        )
+    }
+}
diff --git a/lib/Utils.groovy b/lib/Utils.groovy
new file mode 100755
index 00000000..28567bd7
--- /dev/null
+++ b/lib/Utils.groovy
@@ -0,0 +1,40 @@
+//
+// This file holds several Groovy functions that could be useful for any Nextflow pipeline
+//
+
+import org.yaml.snakeyaml.Yaml
+
+class Utils {
+
+    //
+    // When running with -profile conda, warn if channels have not been set-up appropriately
+    //
+    public static void checkCondaChannels(log) {
+        Yaml parser = new Yaml()
+        def channels = []
+        try {
+            def config = parser.load("conda config --show channels".execute().text)
+            channels = config.channels
+        } catch(NullPointerException | IOException e) {
+            log.warn "Could not verify conda channel configuration."
+            return
+        }
+
+        // Check that all channels are present
+        def required_channels = ['conda-forge', 'bioconda', 'defaults']
+        def conda_check_failed = !required_channels.every { ch -> ch in channels }
+
+        // Check that they are in the right order
+        conda_check_failed |= !(channels.indexOf('conda-forge') < channels.indexOf('bioconda'))
+        conda_check_failed |= !(channels.indexOf('bioconda') < channels.indexOf('defaults'))
+
+        if (conda_check_failed) {
+            log.warn "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
+                "  There is a problem with your Conda configuration!\n\n" +
+                "  You will need to set-up the conda-forge and bioconda channels correctly.\n" +
+                "  Please refer to https://bioconda.github.io/user/install.html#set-up-channels\n" +
+                "  NB: The order of the channels matters!\n" +
+                "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
+        }
+    }
+}
diff --git a/lib/WorkflowGenomeassembly.groovy b/lib/WorkflowGenomeassembly.groovy
new file mode 100755
index 00000000..d4cf936a
--- /dev/null
+++ b/lib/WorkflowGenomeassembly.groovy
@@ -0,0 +1,58 @@
+//
+// This file holds several functions specific to the workflow/genomeassembly.nf in the sanger-tol/genomeassembly pipeline
+//
+
+class WorkflowGenomeassembly {
+
+    //
+    // Check and validate parameters
+    //
+    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)
+        }
+    }
+
+    //
+    // Get workflow summary for MultiQC
+    //
+    public static String paramsSummaryMultiqc(workflow, summary) {
+        String summary_section = ''
+        for (group in summary.keySet()) {
+            def group_params = summary.get(group)  // This gets the parameters of that particular group
+            if (group_params) {
+                summary_section += "    <p style=\"font-size:110%\"><b>$group</b></p>\n"
+                summary_section += "    <dl class=\"dl-horizontal\">\n"
+                for (param in group_params.keySet()) {
+                    summary_section += "        <dt>$param</dt><dd><samp>${group_params.get(param) ?: '<span style=\"color:#999999;\">N/A</a>'}</samp></dd>\n"
+                }
+                summary_section += "    </dl>\n"
+            }
+        }
+
+        String yaml_file_text  = "id: '${workflow.manifest.name.replace('/','-')}-summary'\n"
+        yaml_file_text        += "description: ' - this information is collected when the pipeline is started.'\n"
+        yaml_file_text        += "section_name: '${workflow.manifest.name} Workflow Summary'\n"
+        yaml_file_text        += "section_href: 'https://github.com/${workflow.manifest.name}'\n"
+        yaml_file_text        += "plot_type: 'html'\n"
+        yaml_file_text        += "data: |\n"
+        yaml_file_text        += "${summary_section}"
+        return yaml_file_text
+    }//
+    // Exit pipeline if incorrect --genome key provided
+    //
+    private static void genomeExistsError(params, log) {
+        if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) {
+            log.error "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
+                "  Genome '${params.genome}' not found in any config files provided to the pipeline.\n" +
+                "  Currently, the available genome keys are:\n" +
+                "  ${params.genomes.keySet().join(", ")}\n" +
+                "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
+            System.exit(1)
+        }
+    }
+}
diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy
new file mode 100755
index 00000000..e2e23efc
--- /dev/null
+++ b/lib/WorkflowMain.groovy
@@ -0,0 +1,93 @@
+//
+// This file holds several functions specific to the main.nf workflow in the sanger-tol/genomeassembly pipeline
+//
+
+class WorkflowMain {
+
+    //
+    // Citation string for pipeline
+    //
+    public static String citation(workflow) {
+        return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" +
+            // TODO nf-core: Add Zenodo DOI for pipeline after first release
+            //"* The pipeline\n" +
+            //"  https://doi.org/10.5281/zenodo.XXXXXXX\n\n" +
+            "* The nf-core framework\n" +
+            "  https://doi.org/10.1038/s41587-020-0439-x\n\n" +
+            "* Software dependencies\n" +
+            "  https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md"
+    }
+
+    //
+    // Print help to screen if required
+    //
+    public static String help(workflow, params, log) {
+        def command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker"
+        def help_string = ''
+        help_string += NfcoreTemplate.logo(workflow, params.monochrome_logs)
+        help_string += NfcoreSchema.paramsHelp(workflow, params, command)
+        help_string += '\n' + citation(workflow) + '\n'
+        help_string += NfcoreTemplate.dashedLine(params.monochrome_logs)
+        return help_string
+    }
+
+    //
+    // Print parameter summary log to screen
+    //
+    public static String paramsSummaryLog(workflow, params, log) {
+        def summary_log = ''
+        summary_log += NfcoreTemplate.logo(workflow, params.monochrome_logs)
+        summary_log += NfcoreSchema.paramsSummaryLog(workflow, params)
+        summary_log += '\n' + citation(workflow) + '\n'
+        summary_log += NfcoreTemplate.dashedLine(params.monochrome_logs)
+        return summary_log
+    }
+
+    //
+    // Validate parameters and print summary to screen
+    //
+    public static void initialise(workflow, params, log) {
+        // Print help to screen if required
+        if (params.help) {
+            log.info help(workflow, params, log)
+            System.exit(0)
+        }
+
+        // Validate workflow parameters via the JSON schema
+        if (params.validate_params) {
+            NfcoreSchema.validateParameters(workflow, params, log)
+        }
+
+        // Print parameter summary log to screen
+
+        log.info paramsSummaryLog(workflow, params, log)
+
+        // Check that a -profile or Nextflow config has been provided to run the pipeline
+        NfcoreTemplate.checkConfigProvided(workflow, log)
+
+        // Check that conda channels are set-up correctly
+        if (params.enable_conda) {
+            Utils.checkCondaChannels(log)
+        }
+
+        // Check AWS batch settings
+        NfcoreTemplate.awsBatch(workflow, params)
+
+        // Check input has been provided
+        if (!params.input) {
+            log.error "Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'"
+            System.exit(1)
+        }
+    }
+    //
+    // Get attribute from genome config file e.g. fasta
+    //
+    public static Object getGenomeAttribute(params, attribute) {
+        if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) {
+            if (params.genomes[ params.genome ].containsKey(attribute)) {
+                return params.genomes[ params.genome ][ attribute ]
+            }
+        }
+        return null
+    }
+}
diff --git a/lib/nfcore_external_java_deps.jar b/lib/nfcore_external_java_deps.jar
new file mode 100644
index 00000000..805c8bb5
Binary files /dev/null and b/lib/nfcore_external_java_deps.jar differ
diff --git a/main.nf b/main.nf
new file mode 100644
index 00000000..ad0fe7f5
--- /dev/null
+++ b/main.nf
@@ -0,0 +1,61 @@
+#!/usr/bin/env nextflow
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    sanger-tol/genomeassembly
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Github : https://github.com/sanger-tol/genomeassembly
+----------------------------------------------------------------------------------------
+*/
+
+nextflow.enable.dsl = 2
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    GENOME PARAMETER VALUES
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+params.fasta = WorkflowMain.getGenomeAttribute(params, 'fasta')
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    VALIDATE & PRINT PARAMETER SUMMARY
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+WorkflowMain.initialise(workflow, params, log)
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    NAMED WORKFLOW FOR PIPELINE
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+include { GENOMEASSEMBLY } from './workflows/genomeassembly'
+
+//
+// WORKFLOW: Run main sanger-tol/genomeassembly analysis pipeline
+//
+workflow SANGERTOL_GENOMEASSEMBLY {
+    GENOMEASSEMBLY ()
+}
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    RUN ALL WORKFLOWS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+//
+// WORKFLOW: Execute a single named workflow for the pipeline
+// See: https://github.com/nf-core/rnaseq/issues/619
+//
+workflow {
+    SANGERTOL_GENOMEASSEMBLY ()
+}
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    THE END
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
diff --git a/modules.json b/modules.json
new file mode 100644
index 00000000..15974abc
--- /dev/null
+++ b/modules.json
@@ -0,0 +1,21 @@
+{
+    "name": "sanger-tol/genomeassembly",
+    "homePage": "https://github.com/sanger-tol/genomeassembly",
+    "repos": {
+        "nf-core/modules": {
+            "base_path": "modules",
+            "git_url": "https://github.com/nf-core/modules.git",
+            "modules": {
+                "custom/dumpsoftwareversions": {
+                    "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                },
+                "fastqc": {
+                    "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                },
+                "multiqc": {
+                    "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+                }
+            }
+        }
+    }
+}
diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf
new file mode 100644
index 00000000..e6d213b0
--- /dev/null
+++ b/modules/local/samplesheet_check.nf
@@ -0,0 +1,27 @@
+process SAMPLESHEET_CHECK {
+    tag "$samplesheet"
+
+    conda (params.enable_conda ? "conda-forge::python=3.8.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/python:3.8.3' :
+        'quay.io/biocontainers/python:3.8.3' }"
+
+    input:
+    path samplesheet
+
+    output:
+    path '*.csv'       , emit: csv
+    path "versions.yml", emit: versions
+
+    script: // This script is bundled with the pipeline, in sanger-tol/genomeassembly/bin/
+    """
+    check_samplesheet.py \\
+        $samplesheet \\
+        samplesheet.valid.csv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python --version | sed 's/Python //g')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf b/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf
new file mode 100644
index 00000000..327d5100
--- /dev/null
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf
@@ -0,0 +1,24 @@
+process CUSTOM_DUMPSOFTWAREVERSIONS {
+    label 'process_low'
+
+    // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container
+    conda (params.enable_conda ? "bioconda::multiqc=1.11" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/multiqc:1.11--pyhdfd78af_0' :
+        'quay.io/biocontainers/multiqc:1.11--pyhdfd78af_0' }"
+
+    input:
+    path versions
+
+    output:
+    path "software_versions.yml"    , emit: yml
+    path "software_versions_mqc.yml", emit: mqc_yml
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    template 'dumpsoftwareversions.py'
+}
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml b/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml
new file mode 100644
index 00000000..60b546a0
--- /dev/null
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml
@@ -0,0 +1,34 @@
+name: custom_dumpsoftwareversions
+description: Custom module used to dump software versions within the nf-core pipeline template
+keywords:
+  - custom
+  - version
+tools:
+  - custom:
+      description: Custom module used to dump software versions within the nf-core pipeline template
+      homepage: https://github.com/nf-core/tools
+      documentation: https://github.com/nf-core/tools
+      licence: ["MIT"]
+input:
+  - versions:
+      type: file
+      description: YML file containing software versions
+      pattern: "*.yml"
+
+output:
+  - yml:
+      type: file
+      description: Standard YML file containing software versions
+      pattern: "software_versions.yml"
+  - mqc_yml:
+      type: file
+      description: MultiQC custom content YML file containing software versions
+      pattern: "software_versions_mqc.yml"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@drpatelh"
+  - "@grst"
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py
new file mode 100644
index 00000000..ab8f4f15
--- /dev/null
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py
@@ -0,0 +1,90 @@
+#!/usr/bin/env python
+
+import platform
+from textwrap import dedent
+
+import yaml
+
+
+def _make_versions_html(versions):
+    html = [
+        dedent(
+            """\\
+            <style>
+            #nf-core-versions tbody:nth-child(even) {
+                background-color: #f2f2f2;
+            }
+            </style>
+            <table class="table" style="width:100%" id="nf-core-versions">
+                <thead>
+                    <tr>
+                        <th> Process Name </th>
+                        <th> Software </th>
+                        <th> Version  </th>
+                    </tr>
+                </thead>
+            """
+        )
+    ]
+    for process, tmp_versions in sorted(versions.items()):
+        html.append("<tbody>")
+        for i, (tool, version) in enumerate(sorted(tmp_versions.items())):
+            html.append(
+                dedent(
+                    f"""\\
+                    <tr>
+                        <td><samp>{process if (i == 0) else ''}</samp></td>
+                        <td><samp>{tool}</samp></td>
+                        <td><samp>{version}</samp></td>
+                    </tr>
+                    """
+                )
+            )
+        html.append("</tbody>")
+    html.append("</table>")
+    return "\\n".join(html)
+
+
+versions_this_module = {}
+versions_this_module["${task.process}"] = {
+    "python": platform.python_version(),
+    "yaml": yaml.__version__,
+}
+
+with open("$versions") as f:
+    versions_by_process = yaml.load(f, Loader=yaml.BaseLoader) | versions_this_module
+
+# aggregate versions by the module name (derived from fully-qualified process name)
+versions_by_module = {}
+for process, process_versions in versions_by_process.items():
+    module = process.split(":")[-1]
+    try:
+        assert versions_by_module[module] == process_versions, (
+            "We assume that software versions are the same between all modules. "
+            "If you see this error-message it means you discovered an edge-case "
+            "and should open an issue in nf-core/tools. "
+        )
+    except KeyError:
+        versions_by_module[module] = process_versions
+
+versions_by_module["Workflow"] = {
+    "Nextflow": "$workflow.nextflow.version",
+    "$workflow.manifest.name": "$workflow.manifest.version",
+}
+
+versions_mqc = {
+    "id": "software_versions",
+    "section_name": "${workflow.manifest.name} Software Versions",
+    "section_href": "https://github.com/${workflow.manifest.name}",
+    "plot_type": "html",
+    "description": "are collected at run time from the software output.",
+    "data": _make_versions_html(versions_by_module),
+}
+
+with open("software_versions.yml", "w") as f:
+    yaml.dump(versions_by_module, f, default_flow_style=False)
+with open("software_versions_mqc.yml", "w") as f:
+    yaml.dump(versions_mqc, f, default_flow_style=False)
+
+with open("versions.yml", "w") as f:
+    yaml.dump(versions_this_module, f, default_flow_style=False)
diff --git a/modules/nf-core/modules/fastqc/main.nf b/modules/nf-core/modules/fastqc/main.nf
new file mode 100644
index 00000000..ed6b8c50
--- /dev/null
+++ b/modules/nf-core/modules/fastqc/main.nf
@@ -0,0 +1,47 @@
+process FASTQC {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::fastqc=0.11.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0' :
+        'quay.io/biocontainers/fastqc:0.11.9--0' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.html"), emit: html
+    tuple val(meta), path("*.zip") , emit: zip
+    path  "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    // Add soft-links to original FastQs for consistent naming in pipeline
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if (meta.single_end) {
+        """
+        [ ! -f  ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz
+        fastqc $args --threads $task.cpus ${prefix}.fastq.gz
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" )
+        END_VERSIONS
+        """
+    } else {
+        """
+        [ ! -f  ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz
+        [ ! -f  ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz
+        fastqc $args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" )
+        END_VERSIONS
+        """
+    }
+}
diff --git a/modules/nf-core/modules/fastqc/meta.yml b/modules/nf-core/modules/fastqc/meta.yml
new file mode 100644
index 00000000..4da5bb5a
--- /dev/null
+++ b/modules/nf-core/modules/fastqc/meta.yml
@@ -0,0 +1,52 @@
+name: fastqc
+description: Run FastQC on sequenced reads
+keywords:
+  - quality control
+  - qc
+  - adapters
+  - fastq
+tools:
+  - fastqc:
+      description: |
+        FastQC gives general quality metrics about your reads.
+        It provides information about the quality score distribution
+        across your reads, the per base sequence content (%A/C/G/T).
+        You get information about adapter contamination and other
+        overrepresented sequences.
+      homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
+      documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
+      licence: ["GPL-2.0-only"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - html:
+      type: file
+      description: FastQC report
+      pattern: "*_{fastqc.html}"
+  - zip:
+      type: file
+      description: FastQC report archive
+      pattern: "*_{fastqc.zip}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@drpatelh"
+  - "@grst"
+  - "@ewels"
+  - "@FelixKrueger"
diff --git a/modules/nf-core/modules/multiqc/main.nf b/modules/nf-core/modules/multiqc/main.nf
new file mode 100644
index 00000000..1264aac1
--- /dev/null
+++ b/modules/nf-core/modules/multiqc/main.nf
@@ -0,0 +1,31 @@
+process MULTIQC {
+    label 'process_medium'
+
+    conda (params.enable_conda ? 'bioconda::multiqc=1.12' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/multiqc:1.12--pyhdfd78af_0' :
+        'quay.io/biocontainers/multiqc:1.12--pyhdfd78af_0' }"
+
+    input:
+    path multiqc_files
+
+    output:
+    path "*multiqc_report.html", emit: report
+    path "*_data"              , emit: data
+    path "*_plots"             , optional:true, emit: plots
+    path "versions.yml"        , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    multiqc -f $args .
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        multiqc: \$( multiqc --version | sed -e "s/multiqc, version //g" )
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/modules/multiqc/meta.yml b/modules/nf-core/modules/multiqc/meta.yml
new file mode 100644
index 00000000..6fa891ef
--- /dev/null
+++ b/modules/nf-core/modules/multiqc/meta.yml
@@ -0,0 +1,40 @@
+name: MultiQC
+description: Aggregate results from bioinformatics analyses across many samples into a single report
+keywords:
+  - QC
+  - bioinformatics tools
+  - Beautiful stand-alone HTML report
+tools:
+  - multiqc:
+      description: |
+        MultiQC searches a given directory for analysis logs and compiles a HTML report.
+        It's a general use tool, perfect for summarising the output from numerous bioinformatics tools.
+      homepage: https://multiqc.info/
+      documentation: https://multiqc.info/docs/
+      licence: ["GPL-3.0-or-later"]
+input:
+  - multiqc_files:
+      type: file
+      description: |
+        List of reports / files recognised by MultiQC, for example the html and zip output of FastQC
+output:
+  - report:
+      type: file
+      description: MultiQC report file
+      pattern: "multiqc_report.html"
+  - data:
+      type: dir
+      description: MultiQC data dir
+      pattern: "multiqc_data"
+  - plots:
+      type: file
+      description: Plots created by MultiQC
+      pattern: "*_data"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@abhi18av"
+  - "@bunop"
+  - "@drpatelh"
diff --git a/nextflow.config b/nextflow.config
new file mode 100644
index 00000000..4ed05ae1
--- /dev/null
+++ b/nextflow.config
@@ -0,0 +1,214 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    sanger-tol/genomeassembly Nextflow config file
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Default config options for all compute environments
+----------------------------------------------------------------------------------------
+*/
+
+// Global default params, used in configs
+params {
+
+    // TODO nf-core: Specify your pipeline's command line flags
+    // Input options
+    input                      = null
+
+
+    // References
+    genome                     = null
+    igenomes_base              = 's3://ngi-igenomes/igenomes'
+    igenomes_ignore            = false
+    // MultiQC options
+    multiqc_config             = null
+    multiqc_title              = null
+    max_multiqc_email_size     = '25.MB'
+
+    // Boilerplate options
+    outdir                     = null
+    tracedir                   = "${params.outdir}/pipeline_info"
+    publish_dir_mode           = 'copy'
+    email                      = null
+    email_on_fail              = null
+    plaintext_email            = false
+    monochrome_logs            = false
+    help                       = false
+    validate_params            = true
+    show_hidden_params         = false
+    schema_ignore_params       = 'genomes'
+    enable_conda               = false
+
+
+    // Config options
+    custom_config_version      = 'master'
+    custom_config_base         = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
+    config_profile_description = null
+    config_profile_contact     = null
+    config_profile_url         = null
+    config_profile_name        = null
+
+
+    // Max resource options
+    // Defaults only, expecting to be overwritten
+    max_memory                 = '128.GB'
+    max_cpus                   = 16
+    max_time                   = '240.h'
+
+}
+
+// Load base.config by default for all pipelines
+includeConfig 'conf/base.config'
+
+// Load nf-core custom profiles from different Institutions
+try {
+    includeConfig "${params.custom_config_base}/nfcore_custom.config"
+} catch (Exception e) {
+    System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
+}
+
+// Load sanger-tol/genomeassembly custom profiles from different institutions.
+// Warning: Uncomment only if a pipeline-specific instititutional config already exists on nf-core/configs!
+// try {
+//   includeConfig "${params.custom_config_base}/pipeline/genomeassembly.config"
+// } catch (Exception e) {
+//   System.err.println("WARNING: Could not load nf-core/config/genomeassembly profiles: ${params.custom_config_base}/pipeline/genomeassembly.config")
+// }
+
+
+
+profiles {
+    debug { process.beforeScript = 'echo $HOSTNAME' }
+    conda {
+        params.enable_conda    = true
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+    }
+    docker {
+        docker.enabled         = true
+        docker.userEmulation   = true
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+    }
+    singularity {
+        singularity.enabled    = true
+        singularity.autoMounts = true
+        docker.enabled         = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+    }
+    podman {
+        podman.enabled         = true
+        docker.enabled         = false
+        singularity.enabled    = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+    }
+    shifter {
+        shifter.enabled        = true
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        charliecloud.enabled   = false
+    }
+    charliecloud {
+        charliecloud.enabled   = true
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+    }
+    test      { includeConfig 'conf/test.config'      }
+    test_full { includeConfig 'conf/test_full.config' }
+}
+
+
+// Load igenomes.config if required
+if (!params.igenomes_ignore) {
+    includeConfig 'conf/igenomes.config'
+} else {
+    params.genomes = [:]
+}
+
+
+// Export these variables to prevent local Python/R libraries from conflicting with those in the container
+// The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container.
+// See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable.
+
+env {
+    PYTHONNOUSERSITE = 1
+    R_PROFILE_USER   = "/.Rprofile"
+    R_ENVIRON_USER   = "/.Renviron"
+    JULIA_DEPOT_PATH = "/usr/local/share/julia"
+}
+
+// Capture exit codes from upstream processes when piping
+process.shell = ['/bin/bash', '-euo', 'pipefail']
+
+def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss')
+timeline {
+    enabled = true
+    file    = "${params.tracedir}/execution_timeline_${trace_timestamp}.html"
+}
+report {
+    enabled = true
+    file    = "${params.tracedir}/execution_report_${trace_timestamp}.html"
+}
+trace {
+    enabled = true
+    file    = "${params.tracedir}/execution_trace_${trace_timestamp}.txt"
+}
+dag {
+    enabled = true
+    file    = "${params.tracedir}/pipeline_dag_${trace_timestamp}.html"
+}
+
+manifest {
+    name            = 'sanger-tol/genomeassembly'
+    author          = '@ksenia-krasheninnikova'
+    homePage        = 'https://github.com/sanger-tol/genomeassembly'
+    description     = ''
+    mainScript      = 'main.nf'
+    nextflowVersion = '!>=21.10.3'
+    version         = '1.0dev'
+}
+
+// Load modules.config for DSL2 module specific options
+includeConfig 'conf/modules.config'
+
+// Function to ensure that resource requirements don't go beyond
+// a maximum limit
+def check_max(obj, type) {
+    if (type == 'memory') {
+        try {
+            if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1)
+                return params.max_memory as nextflow.util.MemoryUnit
+            else
+                return obj
+        } catch (all) {
+            println "   ### ERROR ###   Max memory '${params.max_memory}' is not valid! Using default value: $obj"
+            return obj
+        }
+    } else if (type == 'time') {
+        try {
+            if (obj.compareTo(params.max_time as nextflow.util.Duration) == 1)
+                return params.max_time as nextflow.util.Duration
+            else
+                return obj
+        } catch (all) {
+            println "   ### ERROR ###   Max time '${params.max_time}' is not valid! Using default value: $obj"
+            return obj
+        }
+    } else if (type == 'cpus') {
+        try {
+            return Math.min( obj, params.max_cpus as int )
+        } catch (all) {
+            println "   ### ERROR ###   Max cpus '${params.max_cpus}' is not valid! Using default value: $obj"
+            return obj
+        }
+    }
+}
diff --git a/nextflow_schema.json b/nextflow_schema.json
new file mode 100644
index 00000000..6171d079
--- /dev/null
+++ b/nextflow_schema.json
@@ -0,0 +1,269 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema",
+    "$id": "https://raw.githubusercontent.com/sanger-tol/genomeassembly/master/nextflow_schema.json",
+    "title": "sanger-tol/genomeassembly pipeline parameters",
+    "description": "",
+    "type": "object",
+    "definitions": {
+        "input_output_options": {
+            "title": "Input/output options",
+            "type": "object",
+            "fa_icon": "fas fa-terminal",
+            "description": "Define where the pipeline should find input data and save output data.",
+            "required": ["input", "outdir"],
+            "properties": {
+                "input": {
+                    "type": "string",
+                    "format": "file-path",
+                    "mimetype": "text/csv",
+                    "pattern": "^\\S+\\.csv$",
+                    "schema": "assets/schema_input.json",
+                    "description": "Path to comma-separated file containing information about the samples in the experiment.",
+                    "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row.",
+                    "fa_icon": "fas fa-file-csv"
+                },
+                "outdir": {
+                    "type": "string",
+                    "format": "directory-path",
+                    "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
+                    "fa_icon": "fas fa-folder-open"
+                },
+                "email": {
+                    "type": "string",
+                    "description": "Email address for completion summary.",
+                    "fa_icon": "fas fa-envelope",
+                    "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
+                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
+                },
+                "multiqc_title": {
+                    "type": "string",
+                    "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
+                    "fa_icon": "fas fa-file-signature"
+                }
+            }
+        },
+        "reference_genome_options": {
+            "title": "Reference genome options",
+            "type": "object",
+            "fa_icon": "fas fa-dna",
+            "description": "Reference genome related files and options required for the workflow.",
+            "properties": {
+                "genome": {
+                    "type": "string",
+                    "description": "Name of iGenomes reference.",
+                    "fa_icon": "fas fa-book",
+                    "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details."
+                },
+                "fasta": {
+                    "type": "string",
+                    "format": "file-path",
+                    "mimetype": "text/plain",
+                    "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
+                    "description": "Path to FASTA genome file.",
+                    "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
+                    "fa_icon": "far fa-file-code"
+                },
+                "igenomes_base": {
+                    "type": "string",
+                    "format": "directory-path",
+                    "description": "Directory / URL base for iGenomes references.",
+                    "default": "s3://ngi-igenomes/igenomes",
+                    "fa_icon": "fas fa-cloud-download-alt",
+                    "hidden": true
+                },
+                "igenomes_ignore": {
+                    "type": "boolean",
+                    "description": "Do not load the iGenomes reference config.",
+                    "fa_icon": "fas fa-ban",
+                    "hidden": true,
+                    "help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
+                }
+            }
+        },
+        "institutional_config_options": {
+            "title": "Institutional config options",
+            "type": "object",
+            "fa_icon": "fas fa-university",
+            "description": "Parameters used to describe centralised config profiles. These should not be edited.",
+            "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.",
+            "properties": {
+                "custom_config_version": {
+                    "type": "string",
+                    "description": "Git commit id for Institutional configs.",
+                    "default": "master",
+                    "hidden": true,
+                    "fa_icon": "fas fa-users-cog"
+                },
+                "custom_config_base": {
+                    "type": "string",
+                    "description": "Base directory for Institutional configs.",
+                    "default": "https://raw.githubusercontent.com/nf-core/configs/master",
+                    "hidden": true,
+                    "help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
+                    "fa_icon": "fas fa-users-cog"
+                },
+                "config_profile_name": {
+                    "type": "string",
+                    "description": "Institutional config name.",
+                    "hidden": true,
+                    "fa_icon": "fas fa-users-cog"
+                },
+                "config_profile_description": {
+                    "type": "string",
+                    "description": "Institutional config description.",
+                    "hidden": true,
+                    "fa_icon": "fas fa-users-cog"
+                },
+                "config_profile_contact": {
+                    "type": "string",
+                    "description": "Institutional config contact information.",
+                    "hidden": true,
+                    "fa_icon": "fas fa-users-cog"
+                },
+                "config_profile_url": {
+                    "type": "string",
+                    "description": "Institutional config URL link.",
+                    "hidden": true,
+                    "fa_icon": "fas fa-users-cog"
+                }
+            }
+        },
+        "max_job_request_options": {
+            "title": "Max job request options",
+            "type": "object",
+            "fa_icon": "fab fa-acquisitions-incorporated",
+            "description": "Set the top limit for requested resources for any single job.",
+            "help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.",
+            "properties": {
+                "max_cpus": {
+                    "type": "integer",
+                    "description": "Maximum number of CPUs that can be requested for any single job.",
+                    "default": 16,
+                    "fa_icon": "fas fa-microchip",
+                    "hidden": true,
+                    "help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`"
+                },
+                "max_memory": {
+                    "type": "string",
+                    "description": "Maximum amount of memory that can be requested for any single job.",
+                    "default": "128.GB",
+                    "fa_icon": "fas fa-memory",
+                    "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
+                    "hidden": true,
+                    "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
+                },
+                "max_time": {
+                    "type": "string",
+                    "description": "Maximum amount of time that can be requested for any single job.",
+                    "default": "240.h",
+                    "fa_icon": "far fa-clock",
+                    "pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$",
+                    "hidden": true,
+                    "help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
+                }
+            }
+        },
+        "generic_options": {
+            "title": "Generic options",
+            "type": "object",
+            "fa_icon": "fas fa-file-import",
+            "description": "Less common options for the pipeline, typically set in a config file.",
+            "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
+            "properties": {
+                "help": {
+                    "type": "boolean",
+                    "description": "Display help text.",
+                    "fa_icon": "fas fa-question-circle",
+                    "hidden": true
+                },
+                "publish_dir_mode": {
+                    "type": "string",
+                    "default": "copy",
+                    "description": "Method used to save pipeline results to output directory.",
+                    "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
+                    "fa_icon": "fas fa-copy",
+                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
+                    "hidden": true
+                },
+                "email_on_fail": {
+                    "type": "string",
+                    "description": "Email address for completion summary, only when pipeline fails.",
+                    "fa_icon": "fas fa-exclamation-triangle",
+                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
+                    "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
+                    "hidden": true
+                },
+                "plaintext_email": {
+                    "type": "boolean",
+                    "description": "Send plain-text email instead of HTML.",
+                    "fa_icon": "fas fa-remove-format",
+                    "hidden": true
+                },
+                "max_multiqc_email_size": {
+                    "type": "string",
+                    "description": "File size limit when attaching MultiQC reports to summary emails.",
+                    "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
+                    "default": "25.MB",
+                    "fa_icon": "fas fa-file-upload",
+                    "hidden": true
+                },
+                "monochrome_logs": {
+                    "type": "boolean",
+                    "description": "Do not use coloured log outputs.",
+                    "fa_icon": "fas fa-palette",
+                    "hidden": true
+                },
+                "multiqc_config": {
+                    "type": "string",
+                    "description": "Custom config file to supply to MultiQC.",
+                    "fa_icon": "fas fa-cog",
+                    "hidden": true
+                },
+                "tracedir": {
+                    "type": "string",
+                    "description": "Directory to keep pipeline Nextflow logs and reports.",
+                    "default": "${params.outdir}/pipeline_info",
+                    "fa_icon": "fas fa-cogs",
+                    "hidden": true
+                },
+                "validate_params": {
+                    "type": "boolean",
+                    "description": "Boolean whether to validate parameters against the schema at runtime",
+                    "default": true,
+                    "fa_icon": "fas fa-check-square",
+                    "hidden": true
+                },
+                "show_hidden_params": {
+                    "type": "boolean",
+                    "fa_icon": "far fa-eye-slash",
+                    "description": "Show all params when using `--help`",
+                    "hidden": true,
+                    "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters."
+                },
+                "enable_conda": {
+                    "type": "boolean",
+                    "description": "Run this workflow with Conda. You can also use '-profile conda' instead of providing this parameter.",
+                    "hidden": true,
+                    "fa_icon": "fas fa-bacon"
+                }
+            }
+        }
+    },
+    "allOf": [
+        {
+            "$ref": "#/definitions/input_output_options"
+        },
+        {
+            "$ref": "#/definitions/reference_genome_options"
+        },
+        {
+            "$ref": "#/definitions/institutional_config_options"
+        },
+        {
+            "$ref": "#/definitions/max_job_request_options"
+        },
+        {
+            "$ref": "#/definitions/generic_options"
+        }
+    ]
+}
diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf
new file mode 100644
index 00000000..0aecf87f
--- /dev/null
+++ b/subworkflows/local/input_check.nf
@@ -0,0 +1,44 @@
+//
+// Check input samplesheet and get read channels
+//
+
+include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check'
+
+workflow INPUT_CHECK {
+    take:
+    samplesheet // file: /path/to/samplesheet.csv
+
+    main:
+    SAMPLESHEET_CHECK ( samplesheet )
+        .csv
+        .splitCsv ( header:true, sep:',' )
+        .map { create_fastq_channel(it) }
+        .set { reads }
+
+    emit:
+    reads                                     // channel: [ val(meta), [ reads ] ]
+    versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ]
+}
+
+// Function to get list of [ meta, [ fastq_1, fastq_2 ] ]
+def create_fastq_channel(LinkedHashMap row) {
+    // create meta map
+    def meta = [:]
+    meta.id         = row.sample
+    meta.single_end = row.single_end.toBoolean()
+
+    // add path(s) of the fastq file(s) to the meta map
+    def fastq_meta = []
+    if (!file(row.fastq_1).exists()) {
+        exit 1, "ERROR: Please check input samplesheet -> Read 1 FastQ file does not exist!\n${row.fastq_1}"
+    }
+    if (meta.single_end) {
+        fastq_meta = [ meta, [ file(row.fastq_1) ] ]
+    } else {
+        if (!file(row.fastq_2).exists()) {
+            exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}"
+        }
+        fastq_meta = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ]
+    }
+    return fastq_meta
+}
diff --git a/workflows/genomeassembly.nf b/workflows/genomeassembly.nf
new file mode 100644
index 00000000..e4917f43
--- /dev/null
+++ b/workflows/genomeassembly.nf
@@ -0,0 +1,123 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    VALIDATE INPUTS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+def summary_params = NfcoreSchema.paramsSummaryMap(workflow, params)
+
+// Validate input parameters
+WorkflowGenomeassembly.initialise(params, log)
+
+// TODO nf-core: Add all file path parameters for the pipeline to the list below
+// Check input path parameters to see if they exist
+def checkPathParamList = [ params.input, params.multiqc_config, params.fasta ]
+for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
+
+// Check mandatory parameters
+if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input samplesheet not specified!' }
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    CONFIG FILES
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+ch_multiqc_config        = file("$projectDir/assets/multiqc_config.yml", checkIfExists: true)
+ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multiqc_config) : Channel.empty()
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    IMPORT LOCAL MODULES/SUBWORKFLOWS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+//
+// SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
+//
+include { INPUT_CHECK } from '../subworkflows/local/input_check'
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    IMPORT NF-CORE MODULES/SUBWORKFLOWS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+//
+// MODULE: Installed directly from nf-core/modules
+//
+include { FASTQC                      } from '../modules/nf-core/modules/fastqc/main'
+include { MULTIQC                     } from '../modules/nf-core/modules/multiqc/main'
+include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/modules/custom/dumpsoftwareversions/main'
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    RUN MAIN WORKFLOW
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+// Info required for completion email and summary
+def multiqc_report = []
+
+workflow GENOMEASSEMBLY {
+
+    ch_versions = Channel.empty()
+
+    //
+    // SUBWORKFLOW: Read in samplesheet, validate and stage input files
+    //
+    INPUT_CHECK (
+        ch_input
+    )
+    ch_versions = ch_versions.mix(INPUT_CHECK.out.versions)
+
+    //
+    // MODULE: Run FastQC
+    //
+    FASTQC (
+        INPUT_CHECK.out.reads
+    )
+    ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+
+    CUSTOM_DUMPSOFTWAREVERSIONS (
+        ch_versions.unique().collectFile(name: 'collated_versions.yml')
+    )
+
+    //
+    // MODULE: MultiQC
+    //
+    workflow_summary    = WorkflowGenomeassembly.paramsSummaryMultiqc(workflow, summary_params)
+    ch_workflow_summary = Channel.value(workflow_summary)
+
+    ch_multiqc_files = Channel.empty()
+    ch_multiqc_files = ch_multiqc_files.mix(Channel.from(ch_multiqc_config))
+    ch_multiqc_files = ch_multiqc_files.mix(ch_multiqc_custom_config.collect().ifEmpty([]))
+    ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
+    ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
+    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
+
+    MULTIQC (
+        ch_multiqc_files.collect()
+    )
+    multiqc_report = MULTIQC.out.report.toList()
+    ch_versions    = ch_versions.mix(MULTIQC.out.versions)
+}
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    COMPLETION EMAIL AND SUMMARY
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+workflow.onComplete {
+    if (params.email || params.email_on_fail) {
+        NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report)
+    }
+    NfcoreTemplate.summary(workflow, params, log)
+}
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    THE END
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/