[functional_analysis] add test for limmavoom+gsea

nf-core · Dec 20, 2024 · e8f105c · e8f105c
1 parent 6c3df56
commit e8f105c
Show file tree

Hide file tree

Showing 3 changed files with 165 additions and 0 deletions.
diff --git a/subworkflows/nf-core/differential_functional_enrichment/tests/limmavoom_gsea.config b/subworkflows/nf-core/differential_functional_enrichment/tests/limmavoom_gsea.config
@@ -0,0 +1,24 @@
+process {
+    withName: 'LIMMA_DIFFERENTIAL' {
+        ext.args = { [
+            "--blocking_variables $meta.blocking",
+            "--sample_id_col sample",
+            "--probe_id_col gene_id",
+            "--use_voom TRUE"
+        ].join(' ').trim() }
+
+        ext.prefix = { "${meta.id}_${meta.method}_voom" }
+    }
+
+    withName: 'LIMMA_NORM' {
+        ext.prefix = { "${meta.id}_${meta.method}_voom_norm" }
+    }
+
+    withName: 'CUSTOM_TABULARTOGSEACLS' {
+        ext.args = { [ "variable": "$meta.variable" ] }
+    }
+
+    withName: 'GSEA_GSEA' {
+        ext.args = { "-rnd_seed 1234" }
+    }
+}
diff --git a/subworkflows/nf-core/differential_functional_enrichment/tests/main.nf.test b/subworkflows/nf-core/differential_functional_enrichment/tests/main.nf.test
@@ -283,4 +283,110 @@ nextflow_workflow {
             )
         }
     }
+
+    test("limmavoom + gsea - mouse - basic") {
+
+        tag "limmavoom+gsea"
+        config "./limmavoom_gsea.config"
+
+        setup {
+            run("ABUNDANCE_DIFFERENTIAL_FILTER") {
+                script "../../abundance_differential_filter/main.nf"
+                workflow {
+                """
+                // Define test data
+                def testData = [
+                    expression_test_data_dir: params.modules_testdata_base_path + 'genomics/mus_musculus/rnaseq_expression/',
+                    contrasts_file: 'SRP254919.contrasts.csv',
+                    abundance_file: 'SRP254919.salmon.merged.gene_counts.top1000cov.tsv',
+                    samplesheet_file: 'SRP254919.samplesheet.csv'
+                ]
+
+                // Define inputs
+                ch_samplesheet = Channel.of([
+                    [ id:'test' ],
+                    file(testData.expression_test_data_dir + testData.samplesheet_file)
+                ])
+                ch_transcript_lengths = Channel.of([ [], [] ])
+                ch_control_features = Channel.of([ [], [] ])
+                ch_contrasts = Channel.fromPath(file(testData.expression_test_data_dir + testData.contrasts_file))
+                    .splitCsv ( header:true, sep:',' )
+                    .map{
+                        tuple(it, it.variable, it.reference, it.target)
+                    }
+                ch_input = Channel.of([
+                    [ id:'test' ],
+                    file(testData.expression_test_data_dir + testData.abundance_file),
+                    'limma',   // analysis method
+                    1.5,       // FC threshold
+                    0.05       // padj threshold
+                ])
+
+                input[0] = ch_input
+                input[1] = ch_samplesheet
+                input[2] = ch_transcript_lengths
+                input[3] = ch_control_features
+                input[4] = ch_contrasts
+                """
+                }
+            }
+        }
+
+        when {
+            workflow {
+                """
+                // Define test data
+                def test_data_dir = params.modules_testdata_base_path + 'genomics/mus_musculus/'
+                def testData = [
+                    contrasts_file: test_data_dir + 'rnaseq_expression/SRP254919.contrasts.csv',
+                    abundance_file: test_data_dir + 'rnaseq_expression/SRP254919.salmon.merged.gene_counts.top1000cov.tsv',
+                    samplesheet_file: test_data_dir + 'rnaseq_expression/SRP254919.samplesheet.csv',
+                    genesets_file: test_data_dir + 'gene_set_analysis/mh.all.v2022.1.Mm.symbols.gmt'
+                ]
+
+                ch_input = ABUNDANCE_DIFFERENTIAL_FILTER.out.normalised_matrix
+                    .map { meta, matrix ->
+                        meta['method_de'] = meta['method']
+                        [meta, matrix, 'gsea']
+                    }
+                ch_gene_sets = Channel.of([
+                    [ id:'test' ],
+                    file(testData.genesets_file)
+                ])
+                ch_contrasts = Channel.fromPath(file(testData.contrasts_file))
+                    .splitCsv ( header:true, sep:',' )
+                    .map{
+                        tuple(it, it.variable, it.reference, it.target)
+                    }
+                ch_samplesheet = Channel.of([
+                    [ id:'test' ],
+                    file(testData.samplesheet_file)
+                ])
+                ch_featuresheet = Channel.of([
+                    [ id:'test' ],
+                    file(testData.abundance_file),
+                    'gene_id',
+                    'gene_name'
+                ])
+
+                input[0] = ch_input
+                input[1] = ch_gene_sets
+                input[2] = [[], []]
+                input[3] = ch_contrasts
+                input[4] = ch_samplesheet
+                input[5] = ch_featuresheet
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success},
+                { assert snapshot(
+                    workflow.out.report_gsea
+                ).match()}
+                // { assert path(workflow.out.versions[0]).readLines().contains('gsea: 4.3.2')}
+            )
+        }
+    }
 }
diff --git a/subworkflows/nf-core/differential_functional_enrichment/tests/main.nf.test.snap b/subworkflows/nf-core/differential_functional_enrichment/tests/main.nf.test.snap
@@ -42,6 +42,41 @@
         },
         "timestamp": "2024-12-18T14:24:29.543380157"
     },
+    "limmavoom + gsea - mouse - basic": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "treatment_mCherry_hND6__test",
+                        "variable": "treatment",
+                        "reference": "mCherry",
+                        "target": "hND6",
+                        "blocking": "",
+                        "method": "gsea"
+                    },
+                    "treatment_mCherry_hND6__testgsea_report_for_mCherry.tsv:md5,ce8792382ae299749445767ff16aaecc",
+                    "treatment_mCherry_hND6__testgsea_report_for_hND6.tsv:md5,a76d06ccbd445134408a70d3344a01e2"
+                ],
+                [
+                    {
+                        "id": "treatment_mCherry_hND6_sample_number_test",
+                        "variable": "treatment",
+                        "reference": "mCherry",
+                        "target": "hND6",
+                        "blocking": "sample_number",
+                        "method": "gsea"
+                    },
+                    "treatment_mCherry_hND6_sample_number_testgsea_report_for_mCherry.tsv:md5,ce8792382ae299749445767ff16aaecc",
+                    "treatment_mCherry_hND6_sample_number_testgsea_report_for_hND6.tsv:md5,a76d06ccbd445134408a70d3344a01e2"
+                ]
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.3"
+        },
+        "timestamp": "2024-12-20T10:40:56.08836273"
+    },
     "deseq2 + gprofiler2 - mouse - basic": {
         "content": [
             [