Merge pull request #807 from nf-core/dev

Release PR: 4.0.0

Author: jfy133

.github/CODEOWNERS

@@ -0,0 +1 @@
+*       @jfy133 @d4straub @prototaxites @muabnezor @dialvarezs

.github/workflows/awsfulltest.yml

@@ -4,57 +4,36 @@ name: nf-core AWS full size tests
 # It runs the -profile 'test_full' on AWS batch
 
 on:
-  pull_request:
-    branches:
-      - main
-      - master
   workflow_dispatch:
   pull_request_review:
     types: [submitted]
+  release:
+    types: [published]
 
 jobs:
   run-platform:
     name: Run AWS full tests
-    # run only if the PR is approved by at least 2 reviewers and against the master branch or manually triggered
-    if: github.repository == 'nf-core/mag' && github.event.review.state == 'approved' && github.event.pull_request.base.ref == 'master' || github.event_name == 'workflow_dispatch'
+    # run only if the PR is approved by at least 2 reviewers and against the master/main branch or manually triggered
+    if: github.repository == 'nf-core/mag' && github.event.review.state == 'approved' && (github.event.pull_request.base.ref == 'master' || github.event.pull_request.base.ref == 'main') || github.event_name == 'workflow_dispatch'
     runs-on: ubuntu-latest
     steps:
-      - name: Get PR reviews
-        uses: octokit/[email protected]
-        if: github.event_name != 'workflow_dispatch'
-        id: check_approvals
-        continue-on-error: true
-        with:
-          route: GET /repos/${{ github.repository }}/pulls/${{ github.event.pull_request.number }}/reviews?per_page=100
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Check for approvals
-        if: ${{ failure() && github.event_name != 'workflow_dispatch' }}
-        run: |
-          echo "No review approvals found. At least 2 approvals are required to run this action automatically."
-          exit 1
-
-      - name: Check for enough approvals (>=2)
-        id: test_variables
-        if: github.event_name != 'workflow_dispatch'
+      - name: Set revision variable
+        id: revision
         run: |
-          JSON_RESPONSE='${{ steps.check_approvals.outputs.data }}'
-          CURRENT_APPROVALS_COUNT=$(echo $JSON_RESPONSE | jq -c '[.[] | select(.state | contains("APPROVED")) ] | length')
-          test $CURRENT_APPROVALS_COUNT -ge 2 || exit 1 # At least 2 approvals are required
+          echo "revision=${{ (github.event_name == 'workflow_dispatch' || github.event_name == 'release') && github.sha || 'dev' }}" >> "$GITHUB_OUTPUT"
 
       - name: Launch workflow via Seqera Platform
         uses: seqeralabs/action-tower-launch@v2
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
           compute_env: ${{ secrets.TOWER_COMPUTE_ENV }}
-          revision: ${{ github.sha }}
-          workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/mag/work-${{ github.sha }}
+          revision: ${{ steps.revision.outputs.revision }}
+          workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/mag/work-${{ steps.revision.outputs.revision }}
           parameters: |
             {
               "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}",
-              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/mag/results-${{ github.sha }}"
+              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/mag/results-${{ steps.revision.outputs.revision }}"
             }
           profiles: test_full
 

.github/workflows/ci.yml

@@ -27,7 +27,7 @@ jobs:
     strategy:
       matrix:
         NXF_VER:
-          - "24.04.2"
+          - "25.04.2"
           - "latest-everything"
         profile:
           - "conda"
@@ -36,7 +36,7 @@ jobs:
         test_name:
           - "test"
         isMaster:
-          - ${{ github.base_ref == 'master' }}
+          - ${{ github.base_ref == 'main' }}
         # Exclude conda and singularity on dev
         exclude:
           - isMaster: false
@@ -88,6 +88,7 @@ jobs:
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 
       - name: "Run pipeline with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+        continue-on-error: ${{ matrix.NXF_VER == 'latest-everything' }}
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} --outdir ./results
 

.nf-core.yml

@@ -5,7 +5,7 @@ lint:
     - config_defaults:
         - params.phix_reference
         - params.lambda_reference
-nf_core_version: 3.2.0
+nf_core_version: 3.2.1
 repository_type: pipeline
 template:
   author: "Hadrien Gourlé, Daniel Straub, Sabrina Krakau, James A. Fellows Yates,
@@ -16,4 +16,4 @@ template:
   name: mag
   org: nf-core
   outdir: .
-  version: 3.4.0
+  version: 4.0.0

CHANGELOG.md

@@ -3,6 +3,42 @@
 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).
 
+## v4.0.0 - [2025-05-22]
+
+### `Added`
+
+- [#730](https://github.com/nf-core/mag/pull/730) - Added `--busco_db_lineage` to allow specifying a specific lineage for BUSCO database (added by @jfy133, @dialvarezs)
+- [#730](https://github.com/nf-core/mag/pull/730) - Added a new documentation section on database setup (by @jfy133, @dialvarezs)
+- [#784](https://github.com/nf-core/mag/pull/784) - Added `--bin_min_size` and `--bin_max_size` parameters to filter out bins based on size (requested by @maxibor, @alexhbnr, added by @jfy133, @prototaxites)
+- [#793](https://github.com/nf-core/mag/pull/793) - Document use of a SquashFS image with `--gtdb_db`, useful for limited inode infrastructure (by @muniheart)
+- [#805](https://github.com/nf-core/mag/pull/793) - Add support for fastp's `--trim_poly_g` option (by @jfy133)
+
+### `Changed`
+
+- [#730](https://github.com/nf-core/mag/pull/730) - Migrate from local BUSCO module to nf-core one, updating version (by @dialvarezs)
+- [#730](https://github.com/nf-core/mag/pull/730) - Use BUSCO database from nf-core test datasets (by @dialvarezs)
+- [#788](https://github.com/nf-core/mag/pull/788) - Tweak method of loading GTDB database in GTDBTK_CLASSIFYWF for more stability (reported by @alexhbnr, fix by @jfy133)
+- [#800](https://github.com/nf-core/mag/pull/800) - Default branch is now set to `main` (by @jfy133 and @mirpedrol)
+- [#801](https://github.com/nf-core/mag/pull/800) - Increase CheckM memory requests to match [recommended requirements](https://github.com/nf-core/mag/pull/800) (by @jfy133)
+
+### `Fixed`
+
+- [#789](https://github.com/nf-core/mag/pull/789) - Improve `--bowtie2_mode` description to clarify default settings (reported by @IceGreb, fix by @jfy133)
+- [#798](https://github.com/nf-core/mag/pull/798) - Fix overly strict database validation for `--metauk_db` and improve documentation (reported by @ruqse, fix by @jfy133)
+- [#804](https://github.com/nf-core/mag/pull/804) - Fix broken memory specification for FASTQC (reported by @jmichaelegana, fix by @awgymer & @jfy133)
+
+### `Dependencies`
+
+| Tool     | Previous version | New version |
+| -------- | ---------------- | ----------- |
+| BUSCO    | 5.4.3            | 5.8.3       |
+| csvtk    |                  | 0.31.0      |
+| nextflow | 24.04.2          | 25.04.2     |
+
+### `Deprecated`
+
+- [#730](https://github.com/nf-core/mag/pull/730) - Remove `--busco_auto_lineage_prok` due to update and simplified usage of BUSCO (added by @jfy133, @dialvarezs)
+
 ## 3.4.0 [2025-04-04]
 
 ### `Added`
@@ -11,6 +47,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#745](https://github.com/nf-core/mag/pull/745) - Added `trimmomatic` as an additional pre-processing tool (by @Pranjal-Bioinfo, @jfy133, @GallVp & @sateeshperi).
 - [#745](https://github.com/nf-core/mag/pull/745) - Added parameters for `concoct/cut_up_fasta.py` including `bin_concoct_chunksize`, `bin_concoct_overlap` and `bin_concoct_donotconcatlast` (by @Pranjal-Bioinfo, @jfy133, @GallVp & @sateeshperi).
 - [#777](https://github.com/nf-core/mag/pull/777) - Improved input validation through additional JSON keywords and error messages (by @agusinac)
+- [#784](https://github.com/nf-core/mag/pull/784) - Add ability to filter out bins based on bin size for downstream using `--bin_min_size`, `--bin_max_size` (reported by @maxibor & @alexhbnr, fix by @jfy133)
 
 ### `Changed`
 

README.md

@@ -10,7 +10,7 @@
 [![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
 [![Cite Publication](https://img.shields.io/badge/Cite%20Us!-Cite%20Publication-orange)](https://doi.org/10.1093/nargab/lqac007)
 
-[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A524.04.2-23aa62.svg)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A525.04.2-23aa62.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/)

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/3.4.0"
+  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/4.0.0"
   target="_blank">nf-core/mag</a> analysis pipeline. For information about how to
-  interpret these results, please see the <a href="https://nf-co.re/mag/3.4.0/docs/output"
+  interpret these results, please see the <a href="https://nf-co.re/mag/4.0.0/docs/output"
   target="_blank">documentation</a>.
 report_section_order:
   "nf-core-mag-methods-description":

assets/schema_assembly_input.json

@@ -1,6 +1,6 @@
 {
     "$schema": "https://json-schema.org/draft/2020-12/schema",
-    "$id": "https://raw.githubusercontent.com/nf-core/mag/master/assets/schema_input.json",
+    "$id": "https://raw.githubusercontent.com/nf-core/mag/main/assets/schema_input.json",
     "title": "nf-core/mag pipeline - params.input schema",
     "description": "Schema for the file provided with params.input",
     "type": "array",

assets/schema_input.json

@@ -1,6 +1,6 @@
 {
     "$schema": "https://json-schema.org/draft/2020-12/schema",
-    "$id": "https://raw.githubusercontent.com/nf-core/mag/master/assets/schema_input.json",
+    "$id": "https://raw.githubusercontent.com/nf-core/mag/main/assets/schema_input.json",
     "title": "nf-core/mag pipeline - params.input schema",
     "description": "Schema for the file provided with params.input",
     "type": "array",

bin/combine_tables.py

@@ -5,6 +5,7 @@
 
 import argparse
 import sys
+import warnings
 
 import pandas as pd
 
@@ -110,10 +111,14 @@ def main(args=None):
 
     if args.binqc_summary and args.binqc_tool == "busco":
         busco_results = pd.read_csv(args.binqc_summary, sep="\t")
-        if not bins.equals(busco_results["GenomeBin"].sort_values().reset_index(drop=True)):
+        busco_bins = set(busco_results["Input_file"])
+
+        if set(bins) != busco_bins and len(busco_bins.intersection(set(bins))) > 0:
+            warnings.warn("Bins in BUSCO summary do not match bins in bin depths summary")
+        elif len(busco_bins.intersection(set(bins))) == 0:
             sys.exit("Bins in BUSCO summary do not match bins in bin depths summary!")
         results = pd.merge(
-            results, busco_results, left_on="bin", right_on="GenomeBin", how="outer"
+            results, busco_results, left_on="bin", right_on="Input_file", how="outer"
         )  # assuming depths for all bins are given
 
     if args.binqc_summary and args.binqc_tool == "checkm":