Update/arborator gas 0.1.3

CHANGELOG.md

@@ -3,6 +3,10 @@
 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).
 
+## [0.3.2] - 2025-01-15
+
+- Updated the build of the arborator container in order to update the `genomic_address_service` dependency to [version 0.1.3](https://github.com/phac-nml/genomic_address_service/releases/tag/0.1.3), which fixes an issue with branch lengths in Newick files [PR 27](https://github.com/phac-nml/arboratornf/pull/27).
+
 ## [0.3.1] - 2024-11-05
 
 - Fixed the replacement of `docker.userEmulation` with `docker.runOptions      = '-u $(id -u):$(id -g)'` that was causing a bug in Azure
@@ -41,3 +45,4 @@ Initial release of the arboratornf pipeline to be used for running [Arborator](h
 [0.2.0]: https://github.com/phac-nml/arboratornf/releases/tag/0.2.0
 [0.3.0]: https://github.com/phac-nml/arboratornf/releases/tag/0.3.0
 [0.3.1]: https://github.com/phac-nml/arboratornf/releases/tag/0.3.1
+[0.3.2]: https://github.com/phac-nml/arboratornf/releases/tag/0.3.2

modules/local/arborator/main.nf

@@ -8,8 +8,8 @@ process ARBORATOR {
     label 'process_high'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-    'https://depot.galaxyproject.org/singularity/arborator%3A1.0.0--pyhdfd78af_1' :
-    'biocontainers/arborator:1.0.0--pyhdfd78af_1' }"
+    'https://depot.galaxyproject.org/singularity/arborator%3A1.0.0--pyhdfd78af_2' :
+    'biocontainers/arborator:1.0.0--pyhdfd78af_2' }"
 
     input:
     path merged_profiles // The allelic profiles

nextflow.config

@@ -214,7 +214,7 @@ manifest {
     description     = """Arborator: Genomic Profile Clustering and Summary"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '0.3.1'
+    version         = '0.3.2'
     doi             = ''
     defaultBranch   = 'main'
 }

tests/data/arborator/1/tree_all_single_partition.nwk

@@ -0,0 +1 @@
+(((((S5:1.000000,S3:1.000000):0.5,S4:1.500000):0.8333333333333335,S2:2.333333):1.1666666666666665,S1:3.500000):0.10000000000000009,S6:3.600000);

tests/data/samplesheets/samplesheet-all-single-partition.csv

@@ -0,0 +1,7 @@
+sample,mlst_alleles,metadata_partition,metadata_1,metadata_2,metadata_3,metadata_4,metadata_5,metadata_6,metadata_7,metadata_8
+S1,https://raw.githubusercontent.com/phac-nml/arboratornf/dev/tests/data/profiles/S1.mlst.json,1,"Escherichia coli","EHEC/STEC","Canada","O157:H7",21,"2024/05/30","beef",true
+S2,https://raw.githubusercontent.com/phac-nml/arboratornf/dev/tests/data/profiles/S2.mlst.json,1,"Escherichia coli","EHEC/STEC","The United States","O157:H7",55,"2024/05/21","milk",false
+S3,https://raw.githubusercontent.com/phac-nml/arboratornf/dev/tests/data/profiles/S3.mlst.json,1,"Escherichia coli","EPEC","France","O125",14,"2024/04/30","cheese",true
+S4,https://raw.githubusercontent.com/phac-nml/arboratornf/dev/tests/data/profiles/S4.mlst.json,1,"Escherichia coli","EPEC","France","O125",35,"2024/04/22","cheese",true
+S5,https://raw.githubusercontent.com/phac-nml/arboratornf/dev/tests/data/profiles/S5.mlst.json,1,"Escherichia coli","EAEC","Canada","O126:H27",61,"2012/09/01","milk",false
+S6,https://raw.githubusercontent.com/phac-nml/arboratornf/dev/tests/data/profiles/S6.mlst.json,1,"Escherichia coli","EAEC","Canada","O111:H21",43,"2011/12/25","fruit",false

tests/pipelines/main.nf.test

@@ -51,6 +51,14 @@ nextflow_pipeline {
             def expected_arborator_meta_included = path("$baseDir/tests/data/arborator/basic/metadata.included.tsv")
             assert actual_arborator_meta_included.text == expected_arborator_meta_included.text
 
+            def actual_arborator_tree_1 = path("$launchDir/results/arborator/1_tree.nwk")
+            def expected_arborator_tree_1 = path("$baseDir/tests/data/arborator/1/tree.nwk")
+            assert actual_arborator_tree_1.text == expected_arborator_tree_1.text
+
+            def actual_arborator_tree_2 = path("$launchDir/results/arborator/2_tree.nwk")
+            def expected_arborator_tree_2 = path("$baseDir/tests/data/arborator/2/tree.nwk")
+            assert actual_arborator_tree_2.text == expected_arborator_tree_2.text
+
             assert path("$launchDir/results/arborator/1_clusters.tsv").exists()
             assert path("$launchDir/results/arborator/1_loci.summary.tsv").exists()
             assert path("$launchDir/results/arborator/1_matrix.pq").exists()
@@ -109,6 +117,94 @@ nextflow_pipeline {
         }
     }
 
+    test("Small-scale test of full pipeline with all samples same partition, tree comparison"){
+        tag "pipeline"
+        tag "pipeline_all"
+        when {
+            params {
+                input = "$baseDir/tests/data/samplesheets/samplesheet-all-single-partition.csv"
+                outdir = "results"
+
+                metadata_partition_name = "outbreak"
+                metadata_1_header = "organism"
+                metadata_2_header = "subtype"
+                metadata_3_header = "country"
+                metadata_4_header = "serovar"
+                metadata_5_header = "age"
+                metadata_6_header = "date"
+                metadata_7_header = "source"
+                metadata_8_header = "special"
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert path("$launchDir/results").exists()
+
+            // Check merged profiles
+            def actual_profile_tsv = path("$launchDir/results/merged/profile.tsv")
+            def expected_profile_tsv = path("$baseDir/tests/data/profiles/merged_profiles.tsv")
+            assert actual_profile_tsv.text == expected_profile_tsv.text
+
+            // The goal of this test is to make sure that the produced tree has correct branches
+            // So other comparisons for metadata, etc, were removed
+            def actual_arborator_tree_1 = path("$launchDir/results/arborator/1_tree.nwk")
+            def expected_arborator_tree_1 = path("$baseDir/tests/data/arborator/1/tree_all_single_partition.nwk")
+            assert actual_arborator_tree_1.text == expected_arborator_tree_1.text
+
+            assert path("$launchDir/results/arborator/1_clusters.tsv").exists()
+            assert path("$launchDir/results/arborator/1_loci.summary.tsv").exists()
+            assert path("$launchDir/results/arborator/1_matrix.pq").exists()
+            assert path("$launchDir/results/arborator/1_matrix.tsv").exists()
+            assert path("$launchDir/results/arborator/1_metadata.tsv").exists()
+            assert path("$launchDir/results/arborator/1_outliers.tsv").exists()
+            assert path("$launchDir/results/arborator/1_profile.tsv").exists()
+            assert path("$launchDir/results/arborator/1_tree.nwk").exists()
+
+            // Since all samples in same partition, 1, should be no output files prefixed with 2
+            assert !path("$launchDir/results/arborator/2_clusters.tsv").exists()
+            assert !path("$launchDir/results/arborator/2_loci.summary.tsv").exists()
+            assert !path("$launchDir/results/arborator/2_matrix.pq").exists()
+            assert !path("$launchDir/results/arborator/2_matrix.tsv").exists()
+            assert !path("$launchDir/results/arborator/2_metadata.tsv").exists()
+            assert !path("$launchDir/results/arborator/2_outliers.tsv").exists()
+            assert !path("$launchDir/results/arborator/2_profile.tsv").exists()
+            assert !path("$launchDir/results/arborator/2_tree.nwk").exists()
+
+            // compare IRIDA Next JSON output
+            def iridanext_json = path("$launchDir/results/iridanext.output.json").json
+            def iridanext_global = iridanext_json.files.global
+            def iridanext_samples = iridanext_json.files.samples
+            def iridanext_metadata = iridanext_json.metadata.samples
+
+            assert iridanext_global.findAll { it.path == "arborator/1_clusters.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/1_loci.summary.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/1_matrix.pq" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/1_matrix.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/1_metadata.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/1_outliers.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/1_profile.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/1_tree.nwk" }.size() == 1
+
+            // Since all samples in same partition, 1, should be no output files prefixed with 2
+            assert iridanext_global.findAll { it.path == "arborator/2_clusters.tsv" }.size() == 0
+            assert iridanext_global.findAll { it.path == "arborator/2_loci.summary.tsv" }.size() == 0
+            assert iridanext_global.findAll { it.path == "arborator/2_matrix.pq" }.size() == 0
+            assert iridanext_global.findAll { it.path == "arborator/2_matrix.tsv" }.size() == 0
+            assert iridanext_global.findAll { it.path == "arborator/2_metadata.tsv" }.size() == 0
+            assert iridanext_global.findAll { it.path == "arborator/2_outliers.tsv" }.size() == 0
+            assert iridanext_global.findAll { it.path == "arborator/2_profile.tsv" }.size() == 0
+            assert iridanext_global.findAll { it.path == "arborator/2_tree.nwk" }.size() == 0
+
+            assert iridanext_global.findAll { it.path == "arborator/cluster_summary.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/metadata.excluded.tsv" }.size() == 1
+            assert iridanext_global.findAll { it.path == "arborator/metadata.included.tsv" }.size() == 1
+
+            assert iridanext_samples.isEmpty()
+            assert iridanext_metadata.isEmpty()
+        }
+    }
+
     test("Small-scale test of full pipeline, missing metadata"){
         tag "pipeline"
         when {