Merge pull request nf-core#366 from nf-core/nf-test-conversion

Add nf-test

.github/workflows/ci.yml

@@ -1,70 +1,75 @@
-name: nf-core CI
 # This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
+name: nf-core CI
 on:
   push:
     branches:
-      - dev
+      - "dev"
   pull_request:
+    branches:
+      - "dev"
+      - "master"
   release:
-    types: [published]
+    types:
+      - "published"
 
 env:
   NXF_ANSI_LOG: false
+  NFTEST_VER: "0.8.4"
 
 concurrency:
-  group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}"
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
 jobs:
-  test:
-    name: Run pipeline with test data (AMP and ARG)
-    # Only run on push if this is the nf-core dev branch (merged PRs)
-    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/funcscan') }}"
+  define_nxf_versions:
+    name: Choose nextflow versions to test against depending on target branch
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        NXF_VER:
-          - "23.04.0"
-          - "latest-everything"
-        parameters:
-          - "-profile docker,test_preannotated --annotation_tool prodigal"
-          - "-profile docker,test --annotation_tool prokka"
-          - "-profile docker,test --annotation_tool bakta --annotation_bakta_db_downloadtype light --arg_skip_deeparg --arg_skip_amrfinderplus" # Skip deeparg and amrfinderplus due to otherwise running out of space on GitHub Actions
-
+    outputs:
+      matrix: ${{ steps.nxf_versions.outputs.matrix }}
     steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
-
-      - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v2
-        with:
-          version: "${{ matrix.NXF_VER }}"
-
-      - name: Disk space cleanup
-        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
-
-      - name: Run pipeline with test data (AMP/ARG workflows)
+      - id: nxf_versions
         run: |
-          nextflow run ${GITHUB_WORKSPACE} ${{ matrix.parameters }} --outdir ./results
+          if [[ "${{ github.event_name }}" == "pull_request" && "${{ github.base_ref }}" == "dev" && "${{ matrix.NXF_VER }}" != "latest-everything" ]]; then
+            echo matrix='["latest-everything"]' | tee -a $GITHUB_OUTPUT
+          else
+            echo matrix='["latest-everything", "23.10.0"]' | tee -a $GITHUB_OUTPUT
+          fi
 
-  test_bgc:
-    name: Run pipeline with test data (BGC)
-    # Only run on push if this is the nf-core dev branch (merged PRs)
-    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/funcscan') }}"
+  test:
+    name: nf-test
+    needs: define_nxf_versions
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
-        NXF_VER:
-          - "23.04.0"
-          - "latest-everything"
-        parameters:
-          - "-profile docker,test_preannotated_bgc --annotation_tool prodigal"
-          - "-profile docker,test_bgc --annotation_tool prokka"
-          - "-profile docker,test_bgc --annotation_tool bakta --annotation_bakta_db_downloadtype light"
+        NXF_VER: ${{ fromJson(needs.define_nxf_versions.outputs.matrix) }}
+        tags:
+          - "test"
+          - "test_nothing"
+          - "test_bakta"
+          - "test_prokka"
+          - "test_bgc_pyrodigal"
+          - "test_bgc_bakta"
+          - "test_bgc_prokka"
+          - "test_taxonomy_pyrodigal"
+          - "test_taxonomy_bakta"
+          - "test_taxonomy_prokka"
+          - "test_preannotated"
+          - "test_preannotated_bgc"
+        profile:
+          - "docker"
 
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@v2
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+
+      - name: Check out test data
+        uses: actions/checkout@v3
+        with:
+          repository: nf-core/test-datasets
+          ref: funcscan
+          path: test-datasets/
+          fetch-depth: 1
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v1
@@ -74,37 +79,23 @@ jobs:
       - name: Disk space cleanup
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 
-      - name: Run pipeline with test data (BGC workflow)
+      - name: Install nf-test
         run: |
-          nextflow run ${GITHUB_WORKSPACE} ${{ matrix.parameters }} --outdir ./results --bgc_skip_deepbgc
+          wget -qO- https://code.askimed.com/install/nf-test | bash -s $NFTEST_VER
+          sudo mv nf-test /usr/local/bin/
 
-  test_taxonomy:
-    name: Run pipeline with test data (AMP, ARG and BGC with taxonomy)
-    # Only run on push if this is the nf-core dev branch (merged PRs)
-    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/funcscan') }}"
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        NXF_VER:
-          - "23.04.0"
-          - "latest-everything"
-        parameters:
-          - "-profile docker,test_taxonomy --annotation_tool prodigal"
-          - "-profile docker,test_taxonomy --annotation_tool prokka"
-          - "-profile docker,test_taxonomy --annotation_tool bakta --annotation_bakta_db_downloadtype light"
+      - name: Run nf-test
+        run: |
+          nf-test test --tag ${{ matrix.tags }} --profile ${{ matrix.tags }},${{ matrix.profile }} --junitxml=test.xml
 
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+      - name: Output log on failure
+        if: failure()
+        run: |
+          sudo apt install bat > /dev/null
+          batcat --decorations=always --color=always ${{ github.workspace }}/.nf-test/*/tests/output/pipeline_info/software_versions.yml
 
-      - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
+      - name: Publish Test Report
+        uses: mikepenz/action-junit-report@v3
+        if: always() # always run even if the previous step fails
         with:
-          version: "${{ matrix.NXF_VER }}"
-
-      - name: Disk space cleanup
-        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
-
-      - name: Run pipeline with test data (AMP, ARG and BGC taxonomy workflows)
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} ${{ matrix.parameters }} --outdir ./results
+          report_paths: "*.xml"

.nf-core.yml

@@ -1,2 +1,4 @@
 repository_type: pipeline
+lint:
+  actions_ci: False ## TODO: re-activate once nf-test ci.yml structure updated
 nf_core_version: "2.14.1"

CHANGELOG.md

@@ -16,7 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#375](https://github.com/nf-core/funcscan/pull/375) Merged pipeline template of nf-core/tools version 2.14.1. (by @jfy133)
 - [#381](https://github.com/nf-core/funcscan/pull/381) Added support for supplying pre-annotated sequences to the pipeline. (by @jfy133, @jasmezz)
 - [#382](https://github.com/nf-core/funcscan/pull/382) Optimised BGC screening run time and prevent crashes due to too-short contigs by adding contig length filtering for BGC workflow only. (by @jfy133, @darcy220606)
-- [#384](https://github.com/nf-core/funcscan/pull/384) Deprecated AMPcombi and exchanged it with full suite of AMPcombi2 submodules. (by @darcy220606)
+- [#366](https://github.com/nf-core/funcscan/pull/366) Added nf-test on pipeline level. (by @jfy133, @Darcy220606, @jasmezz)
 
 ### `Fixed`
 
@@ -38,22 +38,28 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 | Tool          | Previous version | New version |
 | ------------- | ---------------- | ----------- |
+| AMPcombi      | 0.1.7            | 0.2.2       |
 | AMPlify       | 1.1.0            | 2.0.0       |
 | AMRFinderPlus | 3.11.18          | 3.12.8      |
 | antiSMASH     | 6.1.1            | 7.1.0       |
+| bioawk        | 1.0              | NA          |
 | DeepARG       | 1.0.2            | 1.0.4       |
 | DeepBGC       | 0.1.30           | 0.1.31      |
 | GECCO         | 0.9.8            | 0.9.10      |
 | hAMRonization | 1.1.1            | 1.1.4       |
 | HMMER         | 3.3.2            | 3.4         |
+| MMSeqs        | NA               | 2:15.6f452  |
 | MultiQC       | 1.15             | 1.22.3      |
 | Pyrodigal     | 2.1.0            | 3.3.0       |
 | RGI           | 5.2.1            | 6.0.3       |
+| seqkit        | NA               | 2.8.1       |
 | tabix/htslib  | 1.11             | 1.19.1      |
-| ampcombi      | 0.1.7            | 0.2.2       |
 
 ### `Deprecated`
 
+- [#384](https://github.com/nf-core/funcscan/pull/384) Deprecated AMPcombi and exchanged it with full suite of AMPcombi2 submodules. (by @darcy220606)
+- [#382](https://github.com/nf-core/funcscan/pull/382) Optimised BGC screening run time and prevent crashes due to too-short contigs by adding contig length filtering for BGC workflow only. Bioawk is replaced with seqkit (by @jfy133, @darcy220606)
+
 ## v1.1.6 - [2024-07-08]
 
 ### `Added`

conf/test.config

@@ -11,7 +11,7 @@
 */
 
 params {
-    config_profile_name        = 'Test profile'
+    config_profile_name        = 'AMP/ARG Pyrodigal test profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Limit resources so that this can run on GitHub Actions
@@ -21,12 +21,13 @@ params {
 
     // Input data
     input                = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
-    amp_hmmsearch_models = params.pipelines_testdata_base_path + 'funcscan/hmms/mybacteriocin.hmm'
 
     annotation_tool      = 'pyrodigal'
 
     run_arg_screening    = true
     arg_fargene_hmmmodel = 'class_a,class_b_1_2'
 
     run_amp_screening    = true
+    amp_run_hmmsearch    = true
+    amp_hmmsearch_models = params.pipelines_testdata_base_path + 'funcscan/hmms/mybacteriocin.hmm'
 }

conf/test_bakta.config

@@ -0,0 +1,34 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/funcscan -profile test_bakta,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'AMP/ARG Bakta test profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '8.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input                            = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
+
+    annotation_tool                  = 'bakta'
+    annotation_bakta_db_downloadtype = 'light'
+
+    run_amp_screening                = true
+    amp_run_hmmsearch                = true
+    amp_hmmsearch_models             = params.pipelines_testdata_base_path + 'funcscan/hmms/mybacteriocin.hmm'
+
+    run_arg_screening                = true
+    arg_fargene_hmmmodel             = 'class_a,class_b_1_2'
+}

conf/test_bgc_bakta.config

@@ -0,0 +1,34 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/funcscan -profile test_bgc_bakta,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'BGC Bakta test profile'
+    config_profile_description = 'Minimal test dataset to check BGC workflow function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '8.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input                            = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
+
+    annotation_tool                  = 'bakta'
+    annotation_bakta_db_downloadtype = "light"
+
+    run_arg_screening                = false
+    run_amp_screening                = false
+    run_bgc_screening                = true
+
+    bgc_run_hmmsearch                = true
+    bgc_hmmsearch_models             = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
+}

conf/test_bgc_prokka.config

@@ -0,0 +1,33 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/funcscan -profile test_bgc_prokka,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'BGC Prokka test profile'
+    config_profile_description = 'Minimal test dataset to check BGC workflow function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '8.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input                = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
+
+    annotation_tool      = 'prokka'
+
+    run_arg_screening    = false
+    run_amp_screening    = false
+    run_bgc_screening    = true
+
+    bgc_run_hmmsearch    = true
+    bgc_hmmsearch_models = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
+}

conf/test_bgc.config → conf/test_bgc_pyrodigal.config

@@ -5,13 +5,13 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/funcscan -profile test_bgc,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/funcscan -profile test_bgc_pyrodigal,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */
 
 params {
-    config_profile_name        = 'BGC test profile'
+    config_profile_name        = 'BGC Pyrodigal test profile'
     config_profile_description = 'Minimal test dataset to check BGC workflow function'
 
     // Limit resources so that this can run on GitHub Actions
@@ -20,12 +20,14 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input                = 'https://raw.githubusercontent.com/nf-core/test-datasets/funcscan/samplesheet_reduced.csv'
-    bgc_hmmsearch_models = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
+    input                = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
 
     annotation_tool      = 'pyrodigal'
 
-    run_arg_screening = false
-    run_amp_screening = false
-    run_bgc_screening = true
+    run_arg_screening    = false
+    run_amp_screening    = false
+    run_bgc_screening    = true
+
+    bgc_run_hmmsearch    = true
+    bgc_hmmsearch_models = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
 }