Config restructure

.github/workflows/ci.yml

@@ -97,18 +97,14 @@ jobs:
     strategy:
       matrix:
         # Run remaining test profiles with minimum nextflow version
-        test_name:
-          [
-            test_host_rm,
-            test_hybrid,
-            test_hybrid_host_rm,
-            test_busco_auto,
-            test_ancient_dna,
-            test_adapterremoval,
-            test_binrefinement,
-            test_virus_identification,
+        profile: [
+            test_nothing, ## fast config to kill all other jobs if something fundamentally wrong
             test_single_end,
-            test_concoct,
+            test_alternatives,
+            test_preassembly_binrefine, ## TODO CHE KOUTPUT
+            test_hybrid_host_rm,
+            #test_extras,
+            #test_bigdb,
           ]
     steps:
       - name: Free some space
@@ -129,37 +125,4 @@ jobs:
 
       - name: Run pipeline with ${{ matrix.test_name }} test profile
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},docker --outdir ./results
-
-  checkm:
-    name: Run single test to checkm due to database download
-    # Only run on push if this is the nf-core dev branch (merged PRs)
-    if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/mag') }}
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Free some space
-        run: |
-          sudo rm -rf "/usr/local/share/boost"
-          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
-
-      - name: Check out pipeline code
-        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
-
-      - name: Install Nextflow
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
-
-      - name: Clean up Disk space
-        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
-
-      - name: Download and prepare CheckM database
-        run: |
-          mkdir -p databases/checkm
-          wget https://zenodo.org/records/7401545/files/checkm_data_2015_01_16.tar.gz -P databases/checkm
-          tar xzvf databases/checkm/checkm_data_2015_01_16.tar.gz -C databases/checkm/
-
-      - name: Run pipeline with ${{ matrix.profile }} test profile
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results --binqc_tool checkm --checkm_db databases/checkm
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.profile }},docker --outdir ./results

conf/test_bbnorm.config → conf/test_alternatives.config

@@ -1,11 +1,12 @@
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    Nextflow config file for running minimal tests
+    Nextflow config file for running minimal tests of alternative tools from default
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    Defines input files and everything required to run a fast and simple pipeline test.
+    Defines input files and everything required to run a fast and simple pipeline test
+    of all alternative tools from a default test run.
 
     Use as follows:
-        nextflow run nf-core/mag -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/mag -profile test_alternatives,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */
@@ -21,25 +22,23 @@ process {
 
 params {
     config_profile_name         = 'Test profile'
-    config_profile_description  = 'Minimal test dataset to check pipeline function'
+    config_profile_description  = 'Minimal test dataset with alternative tools to check pipeline function'
 
-    // Input data
-    input                       = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
-    keep_phix                   = true
-    skip_clipping               = true
-    skip_prokka                 = true
-    skip_prodigal               = true
-    skip_quast                  = true
-    skip_binning                = true
+    // Input data -> Defaults
+    input                       = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.multirun.csv'
     centrifuge_db               = params.pipelines_testdata_base_path + 'mag/test_data/minigut_cf.tar.gz'
     kraken2_db                  = params.pipelines_testdata_base_path + 'mag/test_data/minigut_kraken.tgz'
-    skip_krona                  = true
+    skip_krona                  = false
     min_length_unbinned_contigs = 1
     max_unbinned_contigs        = 2
     busco_db                    = "https://busco-data.ezlab.org/v5/data/lineages/bacteria_odb10.2024-01-08.tar.gz"
     busco_clean                 = true
     skip_gtdbtk                 = true
-    gtdbtk_min_completeness     = 0.01
-    bbnorm                      = true
-    coassemble_group            = true
+    gtdbtk_min_completeness     = 0
+    skip_concoct                = true
+
+    // Alternate tools from default test
+    clip_tool                   = 'adapterremoval'
+    binqc_tool                  = 'checkm'
+    bin_domain_classification   = true
 }

conf/test_binrefinement.config → conf/test_preassembly_binrefine.config

@@ -26,17 +26,22 @@ params {
     // Input data
     input                         = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
     assembly_input                = params.pipelines_testdata_base_path + 'mag/samplesheets/assembly_samplesheet.csv'
-    centrifuge_db                 = params.pipelines_testdata_base_path + 'mag/test_data/minigut_cf.tar.gz'
-    kraken2_db                    = params.pipelines_testdata_base_path + 'mag/test_data/minigut_kraken.tgz'
     skip_krona                    = true
     min_length_unbinned_contigs   = 1
     max_unbinned_contigs          = 2
+    skip_metaeuk                  = false
+    metaeuk_db                    = 'https://github.com/nf-core/test-datasets/raw/modules/data/proteomics/database/yeast_UPS.fasta'
+    run_virus_identification      = true
+    genomad_splits                = 4
     busco_db                      = "https://busco-data.ezlab.org/v5/data/lineages/bacteria_odb10.2024-01-08.tar.gz"
     skip_gtdbtk                   = true
     gtdbtk_min_completeness       = 0.01
     refine_bins_dastool           = true
     refine_bins_dastool_threshold = 0
-    // TODO not using 'both' until #489 merged
     postbinning_input             = 'refined_bins_only'
     busco_clean                   = true
+    run_gunc                      = true
+
+    // For runtime reasons
+    skip_prokka = true // CONCOCT makes hundreds of bins, and Prokka is slow (keeping on runs for 28m, without 22m),
 }

conf/test_single_end.config

@@ -33,7 +33,6 @@ params {
     binning_map_mode            = 'own'
     min_length_unbinned_contigs = 1000000
     max_unbinned_contigs        = 2
-    skip_gtdbtk                 = true
     skip_concoct                = true
     skip_binqc                  = true
     skip_gtdbtk                 = true