Merge pull request #889 from nf-core/dev

Release 2.14.0

Author: d4straub

.github/workflows/awsfulltest.yml

@@ -4,56 +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/ampliseq' && 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/ampliseq' && 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/request-action@v2.x
-        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: ${{ failure() && github.event_name != 'workflow_dispatch' }}
+      - name: Set revision variable
+        id: revision
         run: |
-          echo "No review approvals found. At least 2 approvals are required to run this action automatically."
-          exit 1
+          echo "revision=${{ (github.event_name == 'workflow_dispatch' || github.event_name == 'release') && github.sha || 'dev' }}" >> "$GITHUB_OUTPUT"
 
-      - name: Check for enough approvals (>=2)
-        id: test_variables
-        if: github.event_name != 'workflow_dispatch'
-        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
       - 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/ampliseq/work-${{ github.sha }}
+          revision: ${{ steps.revision.outputs.revision }}
+          workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/ampliseq/work-${{ steps.revision.outputs.revision }}
           parameters: |
             {
               "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}",
-              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/ampliseq/results-${{ github.sha }}"
+              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/ampliseq/results-${{ steps.revision.outputs.revision }}"
             }
           profiles: test_full
 

.nf-core.yml

@@ -9,7 +9,7 @@ lint:
         - params.report_template
         - params.report_css
         - params.report_logo
-nf_core_version: 3.2.0
+nf_core_version: 3.2.1
 repository_type: pipeline
 template:
   author: Daniel Straub, Alexander Peltzer
@@ -21,7 +21,7 @@ template:
   outdir: .
   skip_features:
     - igenomes
-  version: 2.13.0
+  version: 2.14.0
 update:
   https://github.com/nf-core/modules.git:
     nf-core:

CHANGELOG.md

@@ -3,7 +3,40 @@
 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).
 
-## nf-core/ampliseq version 2.13.0 - 2025-04-01
+## nf-core/ampliseq version 2.14.0 - 2025-05-23
+
+### `Added`
+
+- [#879](https://github.com/nf-core/ampliseq/pull/879) - Add `sbdi-gtdb=R10-RS226-1` as parameter to `--dada_ref_taxonomy` and make this version the default for `sbdi-gtdb`.
+- [#882](https://github.com/nf-core/ampliseq/pull/882) - Add `gtdb=R10-RS226` as parameter to `--dada_ref_taxonomy` and make this version the default for `gtdb`.
+- [#883](https://github.com/nf-core/ampliseq/pull/883) - Add BOLD databases `plantae-bold-its1` & `plantae-bold-trnL`, for plant samples with markers ITS1 and trnL, versions 20240510, for DADA2 as parameter to `--dada2_ref_taxonomy`.
+- [#885](https://github.com/nf-core/ampliseq/pull/885) - Add `pr2=5.1.0` as parameter to `--dada_ref_taxonomy` and make this version the default for `pr2`.
+
+### `Changed`
+
+- [#871](https://github.com/nf-core/ampliseq/pull/871) - Multi-region analysis is now easier with custom databases. No alignment file of the reference sequences are needed.
+
+| **Parameter**             | **Description**                                                                                         |
+| ------------------------- | ------------------------------------------------------------------------------------------------------- |
+| **sidle_ref_tax_custom**  | Changed: Previously three files, now one file: path to reference taxonomy strings                       |
+| **sidle_ref_seq_custom**  | New: Path to reference taxonomy sequences in fasta format                                               |
+| **sidle_ref_aln_custom**  | New: Path to multiple sequence alignment of reference taxonomy sequences in fasta format                |
+| **sidle_ref_degenerates** | New: Only effective with `--sidle_ref_tax_custom`, filter reference sequences, default: 5               |
+| **sidle_ref_cleaning**    | New: Arguments regarding ad-hoc cleaning, with `--sidle_ref_tax_custom` default is '--p-database silva' |
+
+### `Fixed`
+
+- [#872](https://github.com/nf-core/ampliseq/pull/872) - Follow nextflow's strict syntax
+- [#876](https://github.com/nf-core/ampliseq/pull/876) - Pulled the updated vsearch/clusters module from nf-core to fix a bug where a wildcard expansion trigging an arguments-too-long error.
+- [#878](https://github.com/nf-core/ampliseq/pull/878) - Downgraded nf-schema from 2.3.0 to 2.2.0 due to incompatibilities with nextflow stable versions 25.05 and newer
+- [#881](https://github.com/nf-core/ampliseq/pull/881) - Template update for nf-core/tools version 3.2.1
+- [#887](https://github.com/nf-core/ampliseq/pull/887) - Updated documentation to include all updates
+
+### `Dependencies`
+
+### `Removed`
+
+## nf-core/ampliseq version 2.13.0 - 2025-04-04
 
 ### `Added`
 

CITATIONS.md

@@ -81,27 +81,31 @@
 
   > M. A. Moynihan & C. Furbo Reeder 2023. nifHdada2 GitHub repository, v2.0.5. Zenodo. doi: http://doi.org/10.5281/zenodo.7996213
 
+- [BOLD Plantae](https://boldsystems.org/)
+
+  > Kesisoglou, G., Keisaris, S., & Pechlivanis, N. (2025). BOLD (Plantae - ITS1, ITS2, trnL) training data formatted for DADA2 [Data set]. Zenodo. doi: https://doi.org/10.5281/zenodo.15089110
+
 ### Phylogenetic placement
 
 - [nf-core/phyloplace](https://nf-co.re/phyloplace)
 
-  > Daniel Lundin. (2023). nf-core/phyloplace: First release (1.0.0). Zenodo. https://doi.org/10.5281/zenodo.7643948
+  > Daniel Lundin. (2023). nf-core/phyloplace: First release (1.0.0). Zenodo. doi: https://doi.org/10.5281/zenodo.7643948
 
 - [HMMER](https://pubmed.ncbi.nlm.nih.gov/22039361/)
 
-  > Eddy, Sean R. “Accelerated Profile HMM Searches.” PLoS Comput Biol 7, no. 10 (October 20, 2011): e1002195. https://doi.org/10.1371/journal.pcbi.1002195.
+  > Eddy, Sean R. “Accelerated Profile HMM Searches.” PLoS Comput Biol 7, no. 10 (October 20, 2011): e1002195. doi: https://doi.org/10.1371/journal.pcbi.1002195.
 
 - [MAFFT](https://pubmed.ncbi.nlm.nih.gov/12136088/)
 
-  > Katoh, Kazutaka, Kazuharu Misawa, Kei‐ichi Kuma, and Takashi Miyata. “MAFFT: A Novel Method for Rapid Multiple Sequence Alignment Based on Fast Fourier Transform.” Nucleic Acids Research 30, no. 14 (July 15, 2002): 3059–66. https://doi.org/10.1093/nar/gkf436.
+  > Katoh, Kazutaka, Kazuharu Misawa, Kei‐ichi Kuma, and Takashi Miyata. “MAFFT: A Novel Method for Rapid Multiple Sequence Alignment Based on Fast Fourier Transform.” Nucleic Acids Research 30, no. 14 (July 15, 2002): 3059–66. doi: https://doi.org/10.1093/nar/gkf436.
 
 - [EPA-NG](https://pubmed.ncbi.nlm.nih.gov/30165689/)
 
-  > Barbera, Pierre, Alexey M Kozlov, Lucas Czech, Benoit Morel, Diego Darriba, Tomáš Flouri, and Alexandros Stamatakis. “EPA-Ng: Massively Parallel Evolutionary Placement of Genetic Sequences.” Systematic Biology 68, no. 2 (March 1, 2019): 365–69. https://doi.org/10.1093/sysbio/syy054.
+  > Barbera, Pierre, Alexey M Kozlov, Lucas Czech, Benoit Morel, Diego Darriba, Tomáš Flouri, and Alexandros Stamatakis. “EPA-Ng: Massively Parallel Evolutionary Placement of Genetic Sequences.” Systematic Biology 68, no. 2 (March 1, 2019): 365–69. doi: https://doi.org/10.1093/sysbio/syy054.
 
 - [Gappa](https://pubmed.ncbi.nlm.nih.gov/32016344/)
 
-  > Czech, Lucas, Pierre Barbera, and Alexandros Stamatakis. “Genesis and Gappa: Processing, Analyzing and Visualizing Phylogenetic (Placement) Data.” Bioinformatics 36, no. 10 (May 1, 2020): 3263–65. https://doi.org/10.1093/bioinformatics/btaa070.
+  > Czech, Lucas, Pierre Barbera, and Alexandros Stamatakis. “Genesis and Gappa: Processing, Analyzing and Visualizing Phylogenetic (Placement) Data.” Bioinformatics 36, no. 10 (May 1, 2020): 3263–65. doi: https://doi.org/10.1093/bioinformatics/btaa070.
 
 ### Multi region analysis (also include Greengenes 13_8 or SILVA 128)
 

README.md

@@ -10,7 +10,7 @@
 
 [![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.1493841-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.1493841)[![Cite Publication](https://img.shields.io/badge/Cite%20Us!-Cite%20Publication-important?labelColor=000000)](https://doi.org/10.3389/fmicb.2020.550420)
 
-[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A524.04.2-23aa62.svg?labelColor=000000)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A524.04.2-23aa62.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/ampliseq/releases/tag/2.13.0"
+  This report has been generated by the <a href="https://github.com/nf-core/ampliseq/releases/tag/2.14.0"
   target="_blank">nf-core/ampliseq</a> analysis pipeline. For information about how
-  to interpret these results, please see the <a href="https://nf-co.re/ampliseq/2.13.0/docs/output"
+  to interpret these results, please see the <a href="https://nf-co.re/ampliseq/2.14.0/docs/output"
   target="_blank">documentation</a>.
 report_section_order:
   "nf-core-ampliseq-methods-description":

bin/taxref_reformat_plantae.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+# The file for taxonomy assignment, identified by containing "toSpecies" in the name
+gunzip -c *toSpecies*gz > assignTaxonomy.fna
+
+# and the file for add species, identified by containing "assign" in the name, is renamed
+mv *assign*gz addSpecies.fna.gz

conf/modules.config

@@ -286,8 +286,12 @@ process {
     }
 
     withName: SIDLE_DBFILT {
-        ext.args = { params.sidle_ref_taxonomy.startsWith("greengenes") ? '--p-num-degenerates 3' : '--p-num-degenerates 5' } // 3 for greengenes, 5 for SILVA 128
-        ext.args2 = { params.sidle_ref_taxonomy.startsWith("greengenes") ? '--p-exclude "p__;,k__;,mitochondria,chloroplast" --p-mode contains' : '--p-exclude "mitochondria,chloroplast" --p-mode contains' } // "p__;,k__;" for greengenes
+        ext.args = {
+            params.sidle_ref_tax_custom ? "--p-num-degenerates ${params.sidle_ref_degenerates}" :
+                params.sidle_ref_taxonomy.startsWith("greengenes") ? '--p-num-degenerates 3' : '--p-num-degenerates 5' } // 3 for greengenes, 5 for SILVA 128
+        ext.args2 = {
+            params.sidle_ref_tax_custom ? '--p-exclude "mitochondria,chloroplast" --p-mode contains' :
+                params.sidle_ref_taxonomy.startsWith("greengenes") ? '--p-exclude "p__;,k__;,mitochondria,chloroplast" --p-mode contains' : '--p-exclude "mitochondria,chloroplast" --p-mode contains' } // "p__;,k__;" for greengenes
         publishDir = [
             path: { "${params.outdir}/sidle/DB/1_prefiltering" },
             mode: params.publish_dir_mode,
@@ -361,7 +365,9 @@ process {
 
     withName: SIDLE_TAXRECON {
         ext.args = {
-            params.sidle_ref_taxonomy.startsWith("greengenes") ? '--p-database "greengenes"' :
+            params.sidle_ref_cleaning ?:
+                params.sidle_ref_tax_custom ? '--p-database "silva"' :
+                params.sidle_ref_taxonomy.startsWith("greengenes") ? '--p-database "greengenes"' :
                 params.sidle_ref_taxonomy.startsWith("silva") ? '--p-database "silva"' : '--p-database "none"'
             }
         publishDir = [