Merge pull request #11 from MPUSP/dev

feat: update github CI workflows and config options

Author: m-jahn

.github/workflows/conventional-prs.yml

@@ -1,4 +1,5 @@
-name: Lint PR
+name: Conventional PRs
+
 on:
   pull_request_target:
     types:
@@ -11,10 +12,5 @@ permissions:
   pull-requests: read
 
 jobs:
-  main:
-    name: Validate PR title
-    runs-on: ubuntu-latest
-    steps:
-      - uses: amannn/action-semantic-pull-request@v5
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+  conventional-prs:
+    uses: MPUSP/mpusp-github-actions/.github/workflows/conventional-prs.yml@main

.github/workflows/deploy-apptainer.yml

@@ -0,0 +1,17 @@
+name: Deploy Apptainer
+
+on:
+  workflow_run:
+    workflows: ["Release Please"]
+    types:
+      - completed
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  packages: write
+
+jobs:
+  deploy-apptainer:
+    if: ${{ github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success' }}
+    uses: MPUSP/mpusp-github-actions/.github/workflows/deploy-apptainer.yml@main

.github/workflows/deploy_apptainer.yml

@@ -1,20 +1,14 @@
+name: Release Please
+
 on:
   push:
-    branches:
-      - main
+    branches: [main]
 
 permissions:
   contents: write
   pull-requests: write
   issues: write
 
-name: release-please
-
 jobs:
   release-please:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: googleapis/release-please-action@v4
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          release-type: simple
+    uses: MPUSP/mpusp-github-actions/.github/workflows/release-please.yml@main

.github/workflows/main.yml

@@ -0,0 +1,12 @@
+name: Snakemake Tests
+
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+  snakemake-tests:
+    uses: MPUSP/mpusp-github-actions/.github/workflows/snakemake-tests.yml@main
+    with:
+      cores: 2
+      dryrun: false

.github/workflows/release-please.yml

@@ -1,6 +1,10 @@
 samplesheet: "config/samples.csv"
 tool: ["prokka"]
 
+reference:
+  fasta: ""
+  gff: ""
+
 pgap:
   bin: "path/to/pgap.py"
   use_yaml_config: True
@@ -18,12 +22,14 @@ bakta:
   extra: "--keep-contig-headers --compliant"
 
 quast:
-  reference_fasta: ""
-  reference_gff: ""
   extra: ""
 
 panaroo:
   skip: False
   remove_source: "cmsearch"
   remove_feature: "tRNA|rRNA|ncRNA|exon|sequence_feature"
   extra: "--clean-mode strict --remove-invalid-genes"
+
+fastani:
+  skip: False
+  extra: ""

.github/workflows/snakemake-tests.yml

@@ -1,7 +1,7 @@
 # snakemake-assembly-postprocessing
 
 [![Snakemake](https://img.shields.io/badge/snakemake-≥8.24.1-brightgreen.svg)](https://snakemake.github.io)
-[![GitHub actions status](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/main.yml/badge.svg)](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/main.yml)
+[![GitHub Actions](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/snakemake-tests.yml/badge.svg)](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/snakemake-tests.yml)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
 [![run with apptainer](https://img.shields.io/badge/run%20with-apptainer-1D355C.svg?labelColor=000000)](https://apptainer.org/)
 [![workflow catalog](https://img.shields.io/badge/Snakemake%20workflow%20catalog-darkgreen)](https://snakemake.github.io/snakemake-workflow-catalog/docs/workflows/MPUSP/snakemake-assembly-postprocessing)

.test/config/config.yml

@@ -9,6 +9,7 @@ A Snakemake workflow for the post-processing of microbial genome assemblies.
    3. [bakta](https://github.com/oschwengers/bakta), a fast, alignment-free annotation tool. Note: Bakta will automatically download its companion database from zenodo (light: 1.5 GB, full: 40 GB)
 3. Create a QC report for the assemblies using [Quast](https://github.com/ablab/quast)
 4. Create a pangenome analysis (orthologs/homologs) using [Panaroo](https://gthlab.au/panaroo/)
+5. Compute pairwise average nucleotide identity (ANI) between the assemblies using [FastANI](https://github.com/ParBLiSS/FastANI) and plot a phylogenetic tree based on the ANI distances.
 
 ## Running the workflow
 
@@ -22,34 +23,4 @@ The samplesheet table has the following layout:
 | EC2224 | "Streptococcus pyogenes" | SF370  | SPY       | assembly.fasta |
 | ...    | ...                      | ...    | ...       | ...            |
 
-**Note:** Pangenome analysis with `Panaroo` requires at least two samples.
-
-### Parameters
-
-This table lists all parameters that can be used to run the workflow.
-
-| Parameter | Type | Details | Default |
-|:---|:---|:---|:---|
-| **samplesheet** | string | Path to the sample sheet file in csv format | |
-| **tool** | array[string] | Annotation tool to use (one of `prokka`, `pgap`, `bakta`) | |
-| **pgap** | | PGAP configuration object |  |
-| bin | string | Path to the PGAP script | |
-| use_yaml_config | boolean | Whether to use YAML configuration for PGAP | `False` |
-| _prepare_yaml_files_ | | Paths to YAML templates for PGAP | |
-| generic | string | Path to the generic YAML configuration file | |
-| submol | string | Path to the submol YAML configuration file | |
-| **prokka** | | Prokka configuration object | |
-| center | string | Center name for Prokka annotation (used in sequence IDs) | |
-| extra | string | Extra command-line arguments for Prokka | `--addgenes` |
-| **bakta** | | Bakta configuration object | |
-| download_db | string | Bakta database type (`full`, `light`, or `none`) | `light` |
-| existing_db | string | Path to an existing Bakta database (optional). Needs to be combined with `download_db='none'` | `--keep-contig-headers --compliant` |
-| extra | string | Extra command-line arguments for Bakta | |
-| **quast** | | QUAST configuration object | |
-| reference_fasta | string | Path to the reference genome for QUAST | |
-| reference_gff | string | Path to the reference annotation for QUAST |
-| extra | string | Extra command-line arguments for QUAST | |
-| **panaroo** | | Panaroo configuration object | |
-| remove_source | string | Source types to remove in Panaroo (regex supported) | `cmsearch` |
-| remove_feature | string | Feature types to remove in Panaroo (regex supported) | `tRNA\|rRNA\|ncRNA\|exon\|sequence_feature` |
-| extra | string | Extra command-line arguments for Panaroo | `--clean-mode strict --remove-invalid-genes` |
+**Note:** Pangenome analysis with `Panaroo` and pairwise similarity analysis with `FastANI` requires at least two samples.

README.md

@@ -1,6 +1,10 @@
 samplesheet: "config/samples.csv"
 tool: ["prokka"]
 
+reference:
+  fasta: ""
+  gff: ""
+
 pgap:
   bin: "path/to/pgap.py"
   use_yaml_config: True
@@ -18,12 +22,14 @@ bakta:
   extra: "--keep-contig-headers --compliant"
 
 quast:
-  reference_fasta: ""
-  reference_gff: ""
   extra: ""
 
 panaroo:
   skip: False
   remove_source: "cmsearch"
   remove_feature: "tRNA|rRNA|ncRNA|exon|sequence_feature"
   extra: "--clean-mode strict --remove-invalid-genes"
+
+fastani:
+  skip: False
+  extra: ""