[Do not merge!] Pseudo PR for first release

.github/workflows/awsfulltest.yml

@@ -45,9 +45,6 @@ jobs:
 
       - name: Launch workflow via Seqera Platform
         uses: seqeralabs/action-tower-launch@v2
-        # TODO nf-core: You can customise AWS full pipeline tests as required
-        # Add full size test data (but still relatively small datasets for few samples)
-        # on the `test_full.config` test runs with only one set of parameters
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}

.github/workflows/ci.yml

@@ -8,7 +8,6 @@ on:
   release:
     types: [published]
   workflow_dispatch:
-
 env:
   NXF_ANSI_LOG: false
   NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/.singularity
@@ -27,6 +26,7 @@ jobs:
     strategy:
       matrix:
         NXF_VER:
+          - "24.04.2"
           - "24.04.2"
           - "latest-everything"
         profile:
@@ -79,6 +79,31 @@ jobs:
           echo $(realpath $CONDA)/condabin >> $GITHUB_PATH
           echo $(realpath python) >> $GITHUB_PATH
 
+      - name: Set up Apptainer
+        if: matrix.profile == 'singularity'
+        uses: eWaterCycle/setup-apptainer@main
+
+      - name: Set up Singularity
+        if: matrix.profile == 'singularity'
+        run: |
+          mkdir -p $NXF_SINGULARITY_CACHEDIR
+          mkdir -p $NXF_SINGULARITY_LIBRARYDIR
+
+      - name: Set up Miniconda
+        if: matrix.profile == 'conda'
+        uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3
+        with:
+          miniconda-version: "latest"
+          auto-update-conda: true
+          conda-solver: libmamba
+          channels: conda-forge,bioconda
+
+      - name: Set up Conda
+        if: matrix.profile == 'conda'
+        run: |
+          echo $(realpath $CONDA)/condabin >> $GITHUB_PATH
+          echo $(realpath python) >> $GITHUB_PATH
+
       - name: Clean up Disk space
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 

.github/workflows/download_pipeline.yml

@@ -57,6 +57,9 @@ jobs:
           python-version: "3.12"
           architecture: "x64"
 
+      - name: Setup Apptainer
+        uses: eWaterCycle/setup-apptainer@4bb22c52d4f63406c49e94c804632975787312b3 # v2.0.0
+
       - name: Setup Apptainer
         uses: eWaterCycle/setup-apptainer@4bb22c52d4f63406c49e94c804632975787312b3 # v2.0.0
         with:

.github/workflows/linting_comment.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@80620a5d27ce0ae443b965134db88467fc607b43 # v7
+        uses: dawidd6/action-download-artifact@20319c5641d495c8a52e688b7dc5fada6c3a9fbc # v8
         with:
           workflow: linting.yml
           workflow_conclusion: completed

.github/workflows/release-announcements.yml

@@ -27,39 +27,6 @@ jobs:
 
             ${{ steps.get_topics.outputs.topics }} #nfcore #openscience #nextflow #bioinformatics
 
-  send-tweet:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5
-        with:
-          python-version: "3.10"
-      - name: Install dependencies
-        run: pip install tweepy==4.14.0
-      - name: Send tweet
-        shell: python
-        run: |
-          import os
-          import tweepy
-
-          client = tweepy.Client(
-              access_token=os.getenv("TWITTER_ACCESS_TOKEN"),
-              access_token_secret=os.getenv("TWITTER_ACCESS_TOKEN_SECRET"),
-              consumer_key=os.getenv("TWITTER_CONSUMER_KEY"),
-              consumer_secret=os.getenv("TWITTER_CONSUMER_SECRET"),
-          )
-          tweet = os.getenv("TWEET")
-          client.create_tweet(text=tweet)
-        env:
-          TWEET: |
-            Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}!
-
-            Please see the changelog: ${{ github.event.release.html_url }}
-          TWITTER_CONSUMER_KEY: ${{ secrets.TWITTER_CONSUMER_KEY }}
-          TWITTER_CONSUMER_SECRET: ${{ secrets.TWITTER_CONSUMER_SECRET }}
-          TWITTER_ACCESS_TOKEN: ${{ secrets.TWITTER_ACCESS_TOKEN }}
-          TWITTER_ACCESS_TOKEN_SECRET: ${{ secrets.TWITTER_ACCESS_TOKEN_SECRET }}
-
   bsky-post:
     runs-on: ubuntu-latest
     steps:

.gitpod.yml

@@ -1,4 +1,4 @@
-image: nfcore/gitpod:latest
+image: nfcore/gitpod:dev
 tasks:
   - name: Update Nextflow and setup pre-commit
     command: |

.nf-core.yml

@@ -1,4 +1,4 @@
-nf_core_version: 3.1.2
+nf_core_version: 3.2.0
 repository_type: pipeline
 template:
   author: Tanya Sarkin Jain

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ repos:
           - prettier@3.2.5
 
   - repo: https://github.com/editorconfig-checker/editorconfig-checker.python
-    rev: "3.0.3"
+    rev: "3.1.2"
     hooks:
       - id: editorconfig-checker
         alias: ec

CHANGELOG.md

@@ -3,14 +3,31 @@
 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).
 
-## v0.1.0 - [date]
+## dev
 
-Initial release of nf-core/pacvar, created with the [nf-core](https://nf-co.re/) template.
+### `Added`
+
+### `Fixed`
+
+- [#28](https://github.com/nf-core/pacvar/pull/28) Updated the JSON schema to make input validation stricter, thus preventing more errors during the pipeline run.
+
+### `Dependencies`
+
+### `Deprecated`
+
+## v1.0.1 - Sardine [02/26/2025]
 
 ### `Added`
 
 ### `Fixed`
 
+- [#19](https://github.com/nf-core/pacvar/pull/19) Changed files produced downstream from PBSV to have an output file name containing 'sv' to indicate origin of the files, as with those files downstream from GATK4 and Deepvariant have 'snv' in output file name (@tanyasarkjain)
+- [#21](https://github.com/nf-core/pacvar/pull/21) Tweaks to the channels passed into HiPhase - specifically ensure that the inputted VCF and BAM channel are ordered in the same way (according to their shared meta). (@tanyasarkjain)
+
 ### `Dependencies`
 
 ### `Deprecated`
+
+## v1.0.0 - Goldfish [01/31/2025]
+
+Initial release of nf-core/pacvar, created with the [nf-core](https://nf-co.re/) template.

CITATIONS.md

@@ -18,6 +18,34 @@
 
 > 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.
 
+- [lima](https://github.com/PacificBiosciences/barcoding)
+
+- [pbmm2](https://github.com/PacificBiosciences/pbmm2)
+
+- [SAMtools](https://pubmed.ncbi.nlm.nih.gov/19505943/)
+
+  > Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R; 1000 Genome Project Data Processing Subgroup. The Sequence Alignment/Map format and SAMtools. Bioinformatics. 2009 Aug 15;25(16):2078-9. doi: 10.1093/bioinformatics/btp352. Epub 2009 Jun 8. PubMed PMID: 19505943; PubMed Central PMCID: PMC2723002.
+
+- [deepvariant](https://pubmed.ncbi.nlm.nih.gov/30247488/)
+
+  > Poplin, R., Chang, PC., Alexander, D. et al. A universal SNP and small-indel variant caller using deep neural networks. Nat Biotechnol 36, 983–987 (2018). https://doi.org/10.1038/nbt.4235
+
+- [HaplotypeCaller](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+
+  > Poplin R, Ruano-Rubio V, DePristo MA, Fennell TJ, Carneiro MO, Van der Auwera GA, Kling DE, Gauthier LD, Levy-Moonshine A, Roazen D, Shakir K, Thibault J, Chandran S, Whelan C, Lek M, Gabriel S, Daly MJ, Neale B, MacArthur DG, Banks E. (2017). Scaling accurate genetic variant discovery to tens of thousands of samples bioRxiv, 201178. DOI: 10.1101/201178
+
+- [bcftools](https://pubmed.ncbi.nlm.nih.gov/33590861/)
+
+  > Danecek P, Bonfield JK, Liddle J, Marshall J, Ohan V, Pollard MO, Whitwham A, Keane T, McCarthy SA, Davies RM, Li H. Twelve years of SAMtools and BCFtools. Gigascience. 2021 Feb 16;10(2):giab008. doi: 10.1093/gigascience/giab008. PMID: 33590861; PMCID: PMC7931819.
+
+- [HiPhase](https://pubmed.ncbi.nlm.nih.gov/38269623/)
+
+  > Holt JM, Saunders CT, Rowell WJ, Kronenberg Z, Wenger AM, Eberle M. HiPhase: jointly phasing small, structural, and tandem repeat variants from HiFi sequencing. Bioinformatics. 2024 Feb 1;40(2):btae042. doi: 10.1093/bioinformatics/btae042. PMID: 38269623; PMCID: PMC10868326.
+
+- [pbsv](https://github.com/PacificBiosciences/pbsv)
+
+- [TRGT](https://github.com/PacificBiosciences/trgt)
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -6,7 +6,7 @@
 </h1>
 
 [![GitHub Actions CI Status](https://github.com/nf-core/pacvar/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/pacvar/actions/workflows/ci.yml)
-[![GitHub Actions Linting Status](https://github.com/nf-core/pacvar/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/pacvar/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/pacvar/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
+[![GitHub Actions Linting Status](https://github.com/nf-core/pacvar/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/pacvar/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/pacvar/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.14813048-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.14813048)
 [![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
 
 [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A524.04.2-23aa62.svg)](https://www.nextflow.io/)
@@ -19,52 +19,73 @@
 
 ## Introduction
 
-**nf-core/pacvar** is a bioinformatics pipeline that ...
+nf-core/pacvar is a bioinformatics pipeline that processes long-read PacBio data. Specifically, the pipeline provides two workflows: one for processing whole-genome sequencing data, and another for processing reads from the PureTarget expansion panel offered by PacBio. This second workflow characterizes tandem repeats. Because the pipeline is designed for PacBio reads, it uses PacBio’s officially released tools.
 
-<!-- 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
--->
+![nf-core/pacvar metro map](docs/images/pacvar_white_background.png)
 
-<!-- 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/contributing/design_guidelines#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/))
+Workflow Overview
+
+1. Demultiplex reads ([`lima`](https://lima.how))
+2. Align reads ([`pbmm2`](https://github.com/PacificBiosciences/pbmm2))
+3. Sort and index alignments ([`SAMtools`](https://sourceforge.net/projects/samtools/files/samtools/))
+
+WGS Workflow Overview
+
+1. Choice of SNP calling routes:
+   a. ([`deepvariant`](https://github.com/google/deepvariant))
+   b. ([`HaplotypeCaller`](https://gatk.broadinstitute.org/hc/en-us/articles/360037225632-HaplotypeCaller))
+2. Call SVs ([`pbsv`](https://github.com/PacificBiosciences/pbsv))
+3. Index VCF files ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html))
+4. Phase SNPs, SVs and BAM files ([`hiphase`](https://github.com/PacificBiosciences/HiPhase))
+
+Tandem Repeat Workflow Overview
+
+1. Genotype tandem repeats - produce spanning bams and vcf ([`TRGT`](https://github.com/PacificBiosciences/trgt))
+2. Index and Sort tandem tepeat spanning bam ([`SAMtools`](https://sourceforge.net/projects/samtools/files/samtools/))
+3. Plot repeat motif plots ([`TRGT`](https://github.com/PacificBiosciences/trgt))
+4. Sort spanning VCF ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html))
 
 ## 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):
-
 First, prepare a samplesheet with your input data that looks as follows:
 
 `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,bam,pbi
+CONTROL,AEG588A1_S1_L002_R1_001.bam,AEG588A1_S1_L002_R1_001.pbi
 ```
 
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
+Note that the `.pbi` file is not required. If you choose not to include it, your input file might look like this:
 
--->
+```csv
+sample,bam,pbi
+CONTROL,AEG588A1_S1_L002_R1_001.bam
+```
 
-Now, you can run the pipeline using:
+Each row represents an unaligned bam file and their associated index (optional).
 
-<!-- TODO nf-core: update the following command to include all required parameters for a minimal example -->
+Now, you can run the pipeline. Below is an example
 
 ```bash
 nextflow run nf-core/pacvar \
    -profile <docker/singularity/.../institute> \
    --input samplesheet.csv \
+   --workflow <wgs/repeat> \
+   --barcodes barcodes.bed \
+   --intervals intervals.bed \
+   --genome <GENOME NAME (e.g. GATK.GRCh38)> \
    --outdir <OUTDIR>
 ```
 
+optional paramaters include: `--skip_demultiplexing`, `--skip_snp`, `--skip_sv`, `--skip_phase`.
+
 > [!WARNING]
 > Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).
+> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).
 
 For more details and further functionality, please refer to the [usage documentation](https://nf-co.re/pacvar/usage) and the [parameter documentation](https://nf-co.re/pacvar/parameters).
 
@@ -80,8 +101,6 @@ nf-core/pacvar was originally written by Tanya Sarkin Jain.
 
 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).
@@ -90,10 +109,9 @@ For further information or help, don't hesitate to get in touch on the [Slack `#
 
 ## 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 nf-core/pacvar for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
+If you use nf-core/pacvar for your analysis, please cite it using the following doi: [10.5281/zenodo.14813048](https://doi.org/10.5281/zenodo.14813048) and publication:
 
-<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
+> Tanya Jain, Claire Clelland, nf-core/pacvar: a pipeline for analyzing longread PacBio whole genome and repeat expansion sequencing data, Bioinformatics, 2025;, btaf116, https://doi.org/10.1093/bioinformatics/btaf116
 
 An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
 

assets/multiqc_config.yml

@@ -1,7 +1,8 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/pacvar/releases/tag/0.1.0" target="_blank">nf-core/pacvar</a>
-  analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/pacvar/0.1.0/docs/output" target="_blank">documentation</a>.
+  This report has been generated by the <a href="https://github.com/nf-core/pacvar/releases/tag/1.0.1"
+  target="_blank">nf-core/pacvar</a> analysis pipeline. For information about how
+  to interpret these results, please see the <a href="https://nf-co.re/pacvar/1.0.1/docs/output"
+  target="_blank">documentation</a>.
 report_section_order:
   "nf-core-pacvar-methods-description":
     order: -1000

assets/samplesheet.csv

@@ -1,3 +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,
+sample,bam,pbi
+sample1,/path/to/bam/file/AEG588A1_1.bam,/path/to/bai/file/AEG588A1_1.pbi
+sample2,/path/to/bam/file/AEG588A4_2.bam

assets/schema_input.json

@@ -8,26 +8,26 @@
         "type": "object",
         "properties": {
             "sample": {
-                "type": "string",
-                "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces",
-                "meta": ["id"]
+                "errorMessage": "Sample ID must be provided and must be an integer or string that cannot contain spaces",
+                "meta": ["id"],
+                "type": ["string", "integer"],
+                "pattern": "^\\S+$"
             },
-            "fastq_1": {
+            "bam": {
+                "errorMessage": "BAM or CRAM file cannot contain spaces, must exist and has the extension '.bam' or '.cram'. This is a required input.",
                 "type": "string",
+                "pattern": "^\\S+\\.(bam|cram)$",
                 "format": "file-path",
-                "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "exists": true
             },
-            "fastq_2": {
+            "pbi": {
+                "errorMessage": "BAI or CRAI index file cannot contain spaces, must exist and has the extension '.bai', '.crai' or '.pbi'",
                 "type": "string",
+                "pattern": "^\\S+\\.(bai|crai|pbi)$",
                 "format": "file-path",
-                "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "exists": true
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["sample", "bam"]
     }
 }