Merge pull request #42 from phac-nml/testing-no-skip

Adding Additional Testing
phac-nml · Mar 12, 2024 · e21f0a7 · e21f0a7
2 parents 26b1211 + 865fe4d
commit e21f0a7
Show file tree

Hide file tree

Showing 4 changed files with 66 additions and 18 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -54,4 +54,7 @@ jobs:
         run: |
           nf-test test
 
+      - name: Nextflow run with test profile
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
 
diff --git a/conf/test.config b/conf/test.config
@@ -15,15 +15,28 @@ params {
     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 = '6.GB'
-    max_time   = '6.h'
+    max_memory = "2.GB"
+    max_cpus = 1
+    max_time   = '3.h'
 
     // Input data
-    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
-    // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
+    input = "https://raw.githubusercontent.com/phac-nml/mikrokondo/dev/tests/data/samplesheets/samplesheet-small-assembly.csv"
+    outdir = "results"
 
-    // Genome references
-    genome = 'R64-1-1'
+    platform = "illumina"
+
+    mash.mash_sketch = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy-staph-ecoli.msh"
+    mash.min_kmer = 1
+
+    r_contaminants.mega_mm2_idx = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy.mmi"
+
+    fastp.args.illumina = "-Q"
+    min_reads = 100
+
+    skip_bakta = true
+    skip_staramr = false
+    skip_mobrecon = false
+    skip_checkm = false
+    skip_raw_read_metrics = false
+    skip_polishing = false
 }
diff --git a/nextflow.config b/nextflow.config
@@ -919,6 +919,8 @@ profiles {
     test_stub {includeConfig 'conf/test_stub.config'}
     // Remove when merge into main
     test_samplesheet {includeConfig 'conf/test_sample_sheet.config'}
+
+    test { includeConfig 'conf/test.config' }
 }
 
 plugins {

diff --git a/tests/main.nf.test b/tests/main.nf.test
@@ -13,12 +13,16 @@ nextflow_pipeline {
 
                 platform = "illumina"
 
-                mash { mash_sketch = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy-staph-ecoli.msh" }
+                mash
+                {
+                    mash_sketch = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy-staph-ecoli.msh"
+                    min_kmer = 1
+                }
+
                 r_contaminants { mega_mm2_idx = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy.mmi" }
 
                 fastp { args { illumina = "-Q"} }
                 min_reads = 100
-                mash { min_kmer = 1 }
 
                 skip_bakta = true
                 skip_staramr = true
@@ -71,19 +75,23 @@ nextflow_pipeline {
 
                 platform = "illumina"
 
-                mash { mash_sketch = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy-staph-ecoli.msh" }
+                mash
+                {
+                    mash_sketch = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy-staph-ecoli.msh"
+                    min_kmer = 1
+                }
+
                 r_contaminants { mega_mm2_idx = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy.mmi" }
 
                 fastp { args { illumina = "-Q"} }
                 min_reads = 100
-                mash { min_kmer = 1 }
 
                 skip_bakta = true
-                skip_staramr = true
-                skip_mobrecon = true
-                skip_checkm = true
-                skip_raw_read_metrics = true
-                skip_polishing = true
+                skip_staramr = false
+                skip_mobrecon = false
+                skip_checkm = false
+                skip_raw_read_metrics = false
+                skip_polishing = false
 
                 max_memory = "2.GB"
                 max_cpus = 1
@@ -97,6 +105,11 @@ nextflow_pipeline {
             // parse output json file
             def json = path("$launchDir/results/SummaryReport/final_report.json").json
 
+            assert json.short.short.RawReadSummary.R1."total_bp".equals(118750)
+            assert json.short.short.RawReadSummary.R1."total_reads".equals(475)
+            assert json.short.short.RawReadSummary.R1."read_qual_mean".equals(40.0)
+            assert json.short.short.RawReadSummary.R1."mean_sequence_length".equals(250.0)
+
             assert json.short.short.FastP.summary.sequencing.equals("paired end (250 cycles + 250 cycles)")
             assert json.short.short.FastP.summary.before_filtering.total_reads.equals(950)
             assert json.short.short.FastP.filtering_result.passed_filter_reads.equals(950)
@@ -116,12 +129,29 @@ nextflow_pipeline {
             assert json.short.short.QUAST."0"."GC (%)".equals("52.96")
             assert json.short.short.QUAST."0"."Avg. coverage depth".equals("47")
 
+            assert json.short.short.StarAMR."0"."Isolate ID".equals("short_polished")
+            assert json.short.short.StarAMR."0"."Data Type".equals("MLST")
+            assert json.short.short.StarAMR."1"."Isolate ID".equals("short_polished")
+            assert json.short.short.StarAMR."1"."Data Type".equals("Plasmid")
+            assert json.short.short.StarAMR."2"."Isolate ID".equals("short_polished")
+            assert json.short.short.StarAMR."2"."Data Type".equals("Resistance")
+            assert json.short.short.StarAMR."2"."Predicted Phenotype".equals("Sensitive")
+
+            assert json.short.short.CheckM."0"."# genomes".equals("5656")
+            assert json.short.short.CheckM."0"."# markers".equals("56")
+            assert json.short.short.CheckM."0"."# marker sets".equals("24")
+            assert json.short.short.CheckM."0".Contamination.equals("0.00")
+
+            assert json.short.short.SevenGeneMLSTReport[0].filename.equals("short_polished.fasta.gz")
+
+            assert json.short.short.Abricate."0".RESISTANCE.equals("NoData")  // All Abricate results for this are "NoData".
+
             def assembly_path = "$launchDir/results/assembly/length_filtered_contigs/short_filtered.fasta.gz"
             assert path(assembly_path).exists()
 
             // parse assembly file
             def assembly_header = path(assembly_path).linesGzip[0]
-            assert assembly_header.equals(">NODE_1_length_4949_cov_23.917254")
+            assert assembly_header.startsWith(">NODE_1_length_4949_cov_23.917254")  // _pilon_pilon_pilon gets appended
 
             // compare IRIDA Next JSON output
             def iridanext_json = path("$launchDir/results/iridanext.output.json").json