[Do not merge!] Pseudo PR for first release

.github/actions/get-shards/action.yml

@@ -44,7 +44,6 @@ runs:
         # Default values for shard and total_shards
         shard="[]"
         total_shards=0
-
         # Check if there are related tests
         if echo "$nftest_output" | grep -q 'No tests to execute'; then
           echo "No related tests found."

.github/actions/nf-test/action.yml

@@ -70,7 +70,6 @@ runs:
 
           # Save the absolute path of the test.tap file to the output
           echo "tap_file_path=$(realpath test.tap)" >> $GITHUB_OUTPUT
-
     - name: Generate test summary
       if: always()
       shell: bash
@@ -84,6 +83,7 @@ runs:
           touch .summary_header
         fi
 
+
         if [ -f test.tap ]; then
           while IFS= read -r line; do
             if [[ $line =~ ^ok ]]; then

.github/workflows/nf-test-gpu.yml

@@ -0,0 +1,127 @@
+name: Run GPU nf-tests
+on:
+  push:
+    branches:
+      - dev
+  pull_request:
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      runners:
+        description: "Runners to test on"
+        type: string
+        default: "gpu"
+
+# Cancel if a newer run is started
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+env:
+  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+  # renovate: datasource=github-releases depName=askimed/nf-test versioning=semver
+  NFT_VER: "0.9.3"
+  NXF_ANSI_LOG: false
+  NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/.singularity
+  NXF_SINGULARITY_LIBRARYDIR: ${{ github.workspace }}/.singularity
+  # renovate: datasource=github-releases depName=nextflow-io/nextflow versioning=semver
+  NXF_VER: "24.10.5"
+
+jobs:
+  get-shards:
+    runs-on:
+      - runs-on=${{ github.run_id }}-nf-test-get-shards-gpu
+      - runner=2cpu-linux-x64
+    name: "Get Shards"
+    outputs:
+      shard: ${{ steps.set-shards.outputs.shard }}
+      total_shards: ${{ steps.set-shards.outputs.total_shards }}
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+        with:
+          fetch-depth: 0
+
+      - name: run nf-test-shard action
+        id: set-shards
+        uses: ./.github/actions/get-shards
+        env:
+          NFT_VER: ${{ env.NFT_VER }}
+        with:
+          tags: "gpu"
+          max_shards: 2
+
+      - name: Set outputs
+        id: set-outputs
+        run: |
+          echo "shard=${{ steps.set-shards.outputs.shard }}" >> $GITHUB_ENV
+          echo "total_shards=${{ steps.set-shards.outputs.total_shards }}" >> $GITHUB_ENV
+
+  nf-test-gpu:
+    needs: [get-shards]
+    runs-on: "runs-on=${{ github.run_id }}/family=g4dn.xlarge/image=ubuntu24-gpu-x64"
+    name: "GPU Test | ${{ matrix.profile }} | ${{ matrix.shard }} | ${{ matrix.NXF_VER }} | ${{ matrix.filters }}"
+    env:
+      NXF_VER: ${{ matrix.NXF_VER }}
+
+    # Only run on push if this is the nf-core dev branch (merged PRs)
+    # and number of shards is greater than 0
+    if: |
+      needs.get-shards.outputs.total_shards > 0 &&
+      (
+        github.event_name != 'push' ||
+        ( github.event_name == 'push' && github.repository == 'nf-core/lsmquant' )
+      )
+    strategy:
+      fail-fast: false
+      matrix:
+        profile: [docker, singularity]
+        shard: ${{ fromJson(needs.get-shards.outputs.shard) }}
+        NXF_VER:
+          - "24.10.5"
+        filters: [pipeline]
+
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+        with:
+          fetch-depth: 0
+
+      - name: Test CUDA
+        run: |
+          nvidia-smi -L
+
+      - name: Run nf-test Action
+        uses: ./.github/actions/nf-test
+        with:
+          profile: ${{ matrix.profile }},gpu
+          shard: ${{ matrix.shard }}
+          total_shards: ${{ needs.get-shards.outputs.total_shards }}
+          filters: ${{ matrix.filters }}
+          tags: "gpu"
+
+  confirm-pass:
+    runs-on:
+      - runs-on=${{ github.run_id }}-confirm-pass
+      - runner=2cpu-linux-x64
+    needs: [nf-test-gpu]
+    if: always()
+    steps:
+      - name: One or more tests failed
+        if: ${{ contains(needs.*.result, 'failure') }}
+        run: exit 1
+
+      - name: One or more tests cancelled
+        if: ${{ contains(needs.*.result, 'cancelled') }}
+        run: exit 1
+
+      - name: All tests ok
+        if: ${{ contains(needs.*.result, 'success') }}
+        run: exit 0
+
+      - name: debug-print
+        if: always()
+        run: |
+          echo "toJSON(needs) = ${{ toJSON(needs) }}"
+          echo "toJSON(needs.*.result) = ${{ toJSON(needs.*.result) }}"

.github/workflows/nf-test.yml

@@ -64,11 +64,12 @@ jobs:
     runs-on: # use self-hosted runners
       - runs-on=${{ github.run_id }}-nf-test
       - runner=4cpu-linux-x64
+      - volume=80gb
     strategy:
       fail-fast: false
       matrix:
         shard: ${{ fromJson(needs.nf-test-changes.outputs.shard) }}
-        profile: [conda, docker, singularity]
+        profile: [docker, singularity]
         isMain:
           - ${{ github.base_ref == 'master' || github.base_ref == 'main' }}
         # Exclude conda and singularity on dev
@@ -99,6 +100,7 @@ jobs:
           profile: ${{ matrix.profile }}
           shard: ${{ matrix.shard }}
           total_shards: ${{ env.TOTAL_SHARDS }}
+          tags: "stub"
 
       - name: Report test status
         if: ${{ always() }}

.gitignore

@@ -7,3 +7,5 @@ testing/
 testing*
 *.pyc
 null/
+.nf-test*
+.nf-test/

.nf-core.yml

@@ -9,4 +9,7 @@ template:
   name: lsmquant
   org: nf-core
   outdir: .
-  version: 1.0dev
+  skip_features:
+    - fastqc
+    - igenomes
+  version: 1.0.0

CHANGELOG.md

@@ -3,14 +3,46 @@
 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]
+## v1.0.0 - [date]
 
 Initial release of nf-core/lsmquant, created with the [nf-core](https://nf-co.re/) template.
 
 ### `Added`
 
+The main functionalities of the NuMorph toolbox are added up until the nuclei quantification via a 3DUnet
+
+local Modules:
+
+- numorphintensity
+- numorphalign
+- numorphstitch
+- numorphresample
+- numorphregister
+- numorph3dunet
+- mat2json
+- stagefiles
+
+nf-core Modules:
+
+- multiqc
+- unzipfiles
+
+local subworkflows:
+
+- numorphpreprocessing:
+  - numorphintensity
+  - numorphalign
+  - numorphstitch
+  - mat2json
+- ara-registration
+  - numorphresample
+  - numorphregister
+  - mat2json
+
 ### `Fixed`
 
 ### `Dependencies`
 
+Custom numorph container `numorphpreprocessing`, `numorphanalyze`, `mat2json`, and `numorph3dunet`are on the nf-core quay io repository. Compiled matlab application [numorph_preprocessing](https://github.com/CaroAMN/numorph_preprocessing), [mat2json](https://github.com/CaroAMN/mat2json) and the source code for the [3Dunet](https://github.com/CaroAMN/numorph_3dunet) python package are public repositories. The source code of the tools are found here [NuMorph_dev](https://github.com/CaroAMN/Numorph_dev/tree/main)
+
 ### `Deprecated`

CITATIONS.md

@@ -10,23 +10,31 @@
 
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+- [NuMorph](https://pubmed.ncbi.nlm.nih.gov/34644582/)
 
-> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+> Krupa O, Fragola G, Hadden-Ford E, Mory JT, Liu T, Humphrey Z, Rees BW, Krishnamurthy A, Snider WD, Zylka MJ, Wu G, Xing L, Stein JL. NuMorph: Tools for cortical cellular phenotyping in tissue-cleared whole-brain images. Cell Rep. 2021 Oct 12;37(2):109802. doi: 10.1016/j.celrep.2021.109802. PMID: 34644582; PMCID: PMC8530274.
 
-- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+- [BaSiC](https://www.nature.com/articles/ncomms14836)
 
-> 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.
+> Peng, T., Thorn, K., Schroeder, T. et al. A BaSiC tool for background and shading correction of optical microscopy images. Nat Commun 8, 14836 (2017). https://doi.org/10.1038/ncomms14836
 
-## Software packaging/containerisation tools
+- [elastix](https://pubmed.ncbi.nlm.nih.gov/19923044/)
+
+> Klein S, Staring M, Murphy K, Viergever MA, Pluim JP. elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med Imaging. 2010 Jan;29(1):196-205. doi: 10.1109/TMI.2009.2035616. Epub 2009 Nov 17. PMID: 19923044.
+
+- [3DUnetCNN](https://pubmed.ncbi.nlm.nih.gov/37555134/)
 
-- [Anaconda](https://anaconda.com)
+> Ellis DG, Aizenberg MR. Structural Brain Imaging Predicts Individual-Level Task Activation Maps Using Deep Learning. Front Neuroimaging. 2022 Apr 18;1:834883. doi: 10.3389/fnimg.2022.834883. PMID: 37555134; PMCID: PMC10406267.
 
-  > Anaconda Software Distribution. Computer software. Vers. 2-2.4.0. Anaconda, Nov. 2016. Web.
+[VLFeat](https://www.vlfeat.org/)
 
-- [Bioconda](https://pubmed.ncbi.nlm.nih.gov/29967506/)
+> A. Vedaldi and B. Fulkerson VLFeat: An Open and Portable Library of Computer Vision Algorithms (2008)
 
-  > 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.
+- [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
 
 - [BioContainers](https://pubmed.ncbi.nlm.nih.gov/28379341/)
 

README.md

@@ -17,41 +17,76 @@
 [![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/lsmquant)
 
 [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23lsmquant-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/lsmquant)[![Follow on Bluesky](https://img.shields.io/badge/bluesky-%40nf__core-1185fe?labelColor=000000&logo=bluesky)](https://bsky.app/profile/nf-co.re)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)
+![HiRSE Code Promo Badge](https://img.shields.io/badge/Promo-8db427?style=plastic&label=HiRSE&labelColor=005aa0&link=https%3A%2F%2Fgo.fzj.de%2FCodePromo)
 
 ## Introduction
 
-**nf-core/lsmquant** is a bioinformatics pipeline that ...
+**nf-core/lsmquant** is a bioinformatics pipeline that performs preprocessing and analysis of light-sheet microscopy images of tissue cleared samples. The pipeline takes 2D single-channel 16-bit `.tif` images as input. The preprocessing consists of intesity adjustment, channel alignment, and tile stitching to reconstruct the 3D image. For mousebrain samples it offers a registration to the Allen Mouse Brain Reference Atlas for precise region annotation. Cell nuclei quantification is perfomed on the nuclear channel by a 3D-Unet.
 
-<!-- TODO nf-core:
-   Complete this sentence with a 2-3 sentence summary of what types of data the pipeline ingests, a brief overview of the
-   major pipeline sections and the types of output it produces. You're giving an overview to someone new
-   to nf-core here, in 15-20 seconds. For an example, see https://github.com/nf-core/rnaseq/blob/master/README.md#introduction
--->
+<div style="text-align: center;">
+<img src="docs/images/lsmquant-metromap.svg" alt="lasmquant metromap">
+</div>
 
-<!-- TODO nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core
-     workflows use the "tube map" design for that. See https://nf-co.re/docs/guidelines/graphic_design/workflow_diagrams#examples for examples.   -->
-<!-- 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/))
+## Basic workflow
+
+**Preprocessing**
+
+1. Intensity Adjustment
+2. Channel Alignment
+3. Iterative Stitching
+
+**ARA Registration**
+
+4. ARA Registration subworkflow (optional)
+5. Cell Nuclei Quantification
+
+**Full**
+
+1. Preprocessing
+2. Nuclei quantification
+
+## Pipeline Summary
+
+The pipeline consists of two major workflows `preprocessing` and the `full` workflow. The `ara-regsitration` is an optional subworkflow that works only for whole mouse brain samples.
+
+### Preprocessing
+
+Preprocessing is performed on raw 2D single-channel 16-bit `.tif` images produced by a light sheet microscope. Three individual steps are performed:
+
+- **Intensity adjustments** to correct for the Gaussian shape of the lightsheet and intensity differences between adjacent tiles
+- **Image channel alignment** using a 2D rigid approach or a nonlinear 3D approach using Elastix.
+- **Image tile stitching** via an iterative 2D stitching approach by calculating z displacements and xy translations using phase correlation and SIFT.
+
+### Full
+
+Quantification of cell-nuclei is performed using a 3D-Unet. It is performed on the nuclear channel only, assuming that the corresponding image file names contain the pattern `C1`.
+
+### ARA Registration
+
+Optional registration to the Allen Reference Atlas (ARA) for functional brain region annotation can be perfomed before segmentation.
+This includes the following two steps:
+
+- Downsampling of the high resolution stitched images
+- Registration to the ARA
 
 ## Usage
 
 > [!NOTE]
 > If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
 
-<!-- TODO nf-core: Describe the minimum required steps to execute the pipeline, e.g. how to prepare samplesheets.
-     Explain what rows and columns represent. For instance (please edit as appropriate):
+To run the pipeline you need to provide a samplesheet with your data in the following structure:
 
-First, prepare a samplesheet with your input data that looks as follows:
-
-`samplesheet.csv`:
+`samplesheet.csv`
 
 ```csv
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+sample_id,img_directory,parameter_file
+TEST1,path/to/image-files,path/to/parameter/file.csv
 ```
 
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
+The parameter csv file includes sample specific parameters that are used for processing the given data. It needs to follow a specific structure.
 
--->
+Please get the basic template file [here](../assets/params_template_lsmquant.csv).
+`parametersheet.csv`
 
 Now, you can run the pipeline using:
 
@@ -60,8 +95,9 @@ Now, you can run the pipeline using:
 ```bash
 nextflow run nf-core/lsmquant \
    -profile <docker/singularity/.../institute> \
-   --input samplesheet.csv \
-   --outdir <OUTDIR>
+   --input <samplesheet.csv> \
+   --outdir <OUTDIR> \
+   --stage <stage>
 ```
 
 > [!WARNING]
@@ -79,6 +115,14 @@ For more details about the output files and reports, please refer to the
 
 nf-core/lsmquant was originally written by Carolin Schwitalla.
 
+The pipeline is mainly based on the NuMorph (Nuclear-Based Morphometry) toolbox developed by Krupa et al., 2021.
+
+> **NuMorph: Tools for cortical cellular phenotyping in tissue-cleared whole-brain images**
+>
+> Krupa O, Fragola G, Hadden-Ford E, Mory JT, Liu T, Humphrey Z, Rees BW, Krishnamurthy A, Snider WD, Zylka MJ, Wu G, Xing L, Stein JL.
+>
+> Cell Rep. 2021 Oct 12, doi: [10.1016/j.celrep.2021.109802](https://doi.org/10.1016%2Fj.celrep.2021.109802)
+
 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 -->