Add condition to execute the module and update snaps

nf-core · Dec 20, 2024 · 6dafd95 · 6dafd95
1 parent 3834865
commit 6dafd95
Show file tree

Hide file tree

Showing 7 changed files with 64 additions and 21 deletions.
diff --git a/conf/modules.config b/conf/modules.config
@@ -43,7 +43,13 @@ process {
     }
 
     withName: VALIDATE_MODEL {
-        ext.args = { params.observations_id_col ? "--sample_id_col ${params.observations_id_col}" : '' }
+        ext.args = {
+            params.observations_name_col ?
+            "--sample_id_col ${params.observations_name_col}" :
+            params.observations_id_col ?
+            "--sample_id_col ${params.observations_id_col}" :
+            ''
+        }
         publishDir = [
             path: { "${params.outdir}/validate" },
             mode: params.publish_dir_mode,

diff --git a/modules/local/validatemodel/main.nf b/modules/local/validatemodel/main.nf
@@ -8,8 +8,8 @@ process VALIDATE_MODEL {
         'community.wave.seqera.io/library/r-jsonlite_r-optparse_r-tidyverse_r-yaml:18dc3fc2d990206d' }"
 
     input:
-    path samplesheet
-    tuple val(meta), path(models_yml)
+    tuple val(meta) , path(samplesheet)
+    tuple val(meta2), path(models_yml)
 
     output:
     tuple val(meta), path("pheno_table.csv"), emit: pheno_table

diff --git a/modules/local/validatemodel/resources/usr/bin/validate_model.R b/modules/local/validatemodel/resources/usr/bin/validate_model.R
@@ -49,15 +49,31 @@ sample_column    <- opt$sample_id_col   # "sample" #
 # LOAD FILES --------------------------------------------------------
 ## Load models.yml file
 tryCatch({
-    models <- read_yaml(path_yml)
+    if (!file.exists(path_yml)) {
+        stop(sprintf("File '%s' does not exist.", path_yml), call. = FALSE)
+    }
+    if (!grepl("\\.(yaml|yml)$", path_yml, ignore.case = TRUE)) {
+        stop(sprintf("File '%s' is not a YAML file (expected .yaml or .yml extension).", path_yml), call. = FALSE)
+    }
+    models <- yaml::read_yaml(path_yml)
     cat("Loaded YML file successfully.\n")
 }, error = function(e) {
-    stop("Error loading YML file: ", e$message)
+    stop(sprintf("Error loading YML file '%s': %s", path_yml, e$message), call. = FALSE)
 })
 
 ## Load samplesheet CSV file
 tryCatch({
-    samplesheet <- readr::read_csv(path_samplesheet, show_col_types = FALSE)
+    # Set the separator based on the file extension
+    sep <- if (str_detect(path_samplesheet, "\\.(csv|CSV)$")) {
+        ","
+    } else if (str_detect(path_samplesheet, "\\.(tsv|TSV)$")) {
+        "\t"
+    } else {
+        stop("Unsupported file extension. Please provide a .csv or .tsv file.")
+    }
+
+    # Read the file using the determined separator
+    samplesheet <- read_delim(path_samplesheet, delim = sep, show_col_types = FALSE)
     if ( !sample_column %in% colnames(samplesheet) ) {
         stop(paste0("The sample identificator column '", sample_column, "' is not present in the samplesheet file") )
     }

diff --git a/nextflow.config b/nextflow.config
@@ -377,6 +377,9 @@ set -C # No clobber - prevent output redirection from overwriting files.
 // Disable process selector warnings by default. Use debug profile to enable warnings.
 nextflow.enable.configProcessNamesValidation = false
 
+// Enable loading modules bin files
+nextflow.enable.moduleBinaries = true
+
 def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss')
 timeline {
     enabled = true

diff --git a/tests/test.nf.test.snap b/tests/test.nf.test.snap
@@ -190,7 +190,7 @@
     },
     "Test profile with yaml contrasts": {
         "content": [
-            21,
+            22,
             {
                 "DESEQ2_DIFFERENTIAL": {
                     "r-base": "4.1.3",
@@ -321,7 +321,11 @@
                 "tables/differential/treatment_mCherry_hND6_sample_number.deseq2.results_filtered.tsv",
                 "tables/processed_abundance",
                 "tables/processed_abundance/all.normalised_counts.tsv",
-                "tables/processed_abundance/all.vst.tsv"
+                "tables/processed_abundance/all.vst.tsv",
+                "validate",
+                "validate/designs.json",
+                "validate/pheno_table.csv",
+                "validate/versions.yml"
             ],
             [
                 "treatment_mCherry_hND6_.dds.rld.rds:md5,dfe51910e230ae9cc2bc9fa5651666ba",
@@ -368,13 +372,16 @@
                 "treatment_mCherry_hND6_sample_number.deseq2.results.tsv:md5,b41cbaacd04a25b45295f3f987ff7500",
                 "treatment_mCherry_hND6_sample_number.deseq2.results_filtered.tsv:md5,98fa3ec0992859d2a524ecce1259f0ed",
                 "all.normalised_counts.tsv:md5,1d7ad0c02b483f2eff1a5b357a74d011",
-                "all.vst.tsv:md5,a08d06d3c3218619b7bd85beead467bd"
+                "all.vst.tsv:md5,a08d06d3c3218619b7bd85beead467bd",
+                "designs.json:md5,088d536fdff430dc12f4f8b0395a9636",
+                "pheno_table.csv:md5,4969fce19ad1ea5b3cf124f4dcc6a403",
+                "versions.yml:md5,592a22e359ab942c2d315ef0c6ed3fb1"
             ]
         ],
         "meta": {
-            "nf-test": "0.9.0",
+            "nf-test": "0.9.2",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2024-12-20T13:41:10.4647836"
+        "timestamp": "2024-12-20T19:25:36.541448998"
     }
 }
diff --git a/tests/test_maxquant.nf.test.snap b/tests/test_maxquant.nf.test.snap
@@ -177,7 +177,7 @@
     },
     "Test maxquant profile with yaml contrasts": {
         "content": [
-            20,
+            21,
             {
                 "LIMMA_DIFFERENTIAL": {
                     "r-base": "4.3.3",
@@ -289,7 +289,11 @@
                 "tables/proteus/Celltype/raw_proteingroups_tab.tsv",
                 "tables/proteus/fakeBatch",
                 "tables/proteus/fakeBatch/normalizeMedian.normalized_proteingroups_tab.tsv",
-                "tables/proteus/fakeBatch/raw_proteingroups_tab.tsv"
+                "tables/proteus/fakeBatch/raw_proteingroups_tab.tsv",
+                "validate",
+                "validate/designs.json",
+                "validate/pheno_table.csv",
+                "validate/versions.yml"
             ],
             [
                 "fakebatch_fakeBatch_b1_b2.MArrayLM.limma.rds:md5,f321bf1e4fd44827810df9a9c38776d6",
@@ -342,13 +346,16 @@
                 "normalizeMedian.normalized_proteingroups_tab.tsv:md5,154fcd8d23409981b897d153e7b7e34e",
                 "raw_proteingroups_tab.tsv:md5,33a8791f84c676ea1aea4842231acb6a",
                 "normalizeMedian.normalized_proteingroups_tab.tsv:md5,154fcd8d23409981b897d153e7b7e34e",
-                "raw_proteingroups_tab.tsv:md5,33a8791f84c676ea1aea4842231acb6a"
+                "raw_proteingroups_tab.tsv:md5,33a8791f84c676ea1aea4842231acb6a",
+                "designs.json:md5,4ef011dc27b01e863483eb06f0bc4006",
+                "pheno_table.csv:md5,e42e42e88a3f71959fd0750dfe93417a",
+                "versions.yml:md5,592a22e359ab942c2d315ef0c6ed3fb1"
             ]
         ],
         "meta": {
-            "nf-test": "0.9.0",
+            "nf-test": "0.9.2",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2024-12-20T13:45:34.62418232"
+        "timestamp": "2024-12-20T20:09:08.805617631"
     }
 }
diff --git a/workflows/differentialabundance.nf b/workflows/differentialabundance.nf
@@ -150,11 +150,15 @@ workflow DIFFERENTIALABUNDANCE {
     ch_contrasts_file = Channel.from([[exp_meta, file(params.contrasts)]])
 
 
-    // Run module to validate models
-    VALIDATE_MODEL(
-        ch_input,
-        ch_contrasts_file
-    )
+    // Run module to validate models from yml file
+    if ( params.contrasts.endsWith(".yaml") || params.contrasts.endsWith(".yml") ) {
+
+        VALIDATE_MODEL (
+            ch_input,
+            ch_contrasts_file
+        )
+
+    }
 
     // If we have affy array data in the form of CEL files we'll be deriving
     // matrix and annotation from them