Merge branch 'dev' into olgabot/add-metromap

Author: olgabot

.github/workflows/awsfulltest.yml

@@ -4,44 +4,23 @@ 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/proteinannotator' && 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/proteinannotator' && 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: ${{ failure() && github.event_name != 'workflow_dispatch' }}
-        run: |
-          echo "No review approvals found. At least 2 approvals are required to run this action automatically."
-          exit 1
-
-      - name: Check for enough approvals (>=2)
-        id: test_variables
-        if: github.event_name != 'workflow_dispatch'
+      - name: Set revision variable
+        id: revision
         run: |
-          JSON_RESPONSE='${{ 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
@@ -52,12 +31,12 @@ jobs:
           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/proteinannotator/work-${{ github.sha }}
+          revision: ${{ steps.revision.outputs.revision }}
+          workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/proteinannotator/work-${{ steps.revision.outputs.revision }}
           parameters: |
             {
               "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}",
-              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/proteinannotator/results-${{ github.sha }}"
+              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/proteinannotator/results-${{ steps.revision.outputs.revision }}"
             }
           profiles: test_full
 

.github/workflows/ci.yml

@@ -83,5 +83,6 @@ 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

@@ -1,16 +1,20 @@
+lint:
+  files_unchanged:
+    - assets/nf-core-proteinannotator_logo_light.png
+    - docs/images/nf-core-proteinannotator_logo_light.png
+    - docs/images/nf-core-proteinannotator_logo_dark.png
+nf_core_version: 3.2.1
 repository_type: pipeline
-
-nf_core_version: 3.2.0
-
-lint: {}
-
 template:
-  org: nf-core
-  name: proteinannotator
+  author: Olga Botvinnik
   description: The best protein annotation pipeline in the world. Protein fasta ->
     ??? -> Annotations!
-  author: Olga Botvinnik
   version: 1.0.0dev
   force: true
   outdir: .
+  skip_features:
+    - fastqc
+    - igenomes
   is_nfcore: true
+  name: proteinannotator
+  org: nf-core

CHANGELOG.md

@@ -9,6 +9,8 @@ Initial release of nf-core/proteinannotator, created with the [nf-core](https://
 
 ### `Added`
 
+- [[PR #13](https://github.com/nf-core/proteinannotator/pull/13)] Add nf-core seqkit/stats module
+
 ### `Fixed`
 
 ### `Dependencies`

CITATIONS.md

@@ -10,10 +10,6 @@
 
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
-
-> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
-
 - [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.

README.md

@@ -36,26 +36,23 @@
 
 ![Protein annotator metromap. Protein fasta files are summarized with `seqkit stats`, then functionally annotated with InterProScan, DIAMOND-blastp, UniFire, and Kmerseek](assets/proteinannotator-metromap.excalidraw.png)
 
+
 ## 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
+id,fasta
+species1,species1_proteins.fasta
+species2,species2_proteins.fasta
 ```
 
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
-
--->
+Each row represents a fasta file of proteins from a single species.
 
 Now, you can run the pipeline using:
 

assets/nf-core-proteinannotator_logo_light.png

@@ -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,
+id,fasta
+species1,species1_proteins.fasta
+species2,species2_proteins.fasta

assets/samplesheet.csv

@@ -7,27 +7,20 @@
     "items": {
         "type": "object",
         "properties": {
-            "sample": {
+            "id": {
                 "type": "string",
                 "pattern": "^\\S+$",
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
                 "meta": ["id"]
             },
-            "fastq_1": {
+            "fasta": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
-            },
-            "fastq_2": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "pattern": "^\\S+\\.f(ast)?a(\\.gz)?$",
+                "errorMessage": "Fasta file for each sample must be provided, cannot contain spaces and must have extension '.fa.gz', '.fa', '.fasta', or '.fasta.gz'"
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["id", "fasta"]
     }
 }