Merge pull request nf-core#114 from nf-core/input_params_patch

Check conflicting input parameters for stats and eval
alessiovignoli · Mar 20, 2024 · 2e87c59 · 2e87c59
2 parents 83de935 + 6521ea2
commit 2e87c59
Show file tree

Hide file tree

Showing 8 changed files with 56 additions and 475 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -21,6 +21,7 @@ Initial release of nf-core/multiplesequencealign, created with the [nf-core](htt
 [#100](https://github.com/nf-core/multiplesequencealign/pull/100) - Add support for optional stats and evals. Clean tests.
 [#110](https://github.com/nf-core/multiplesequencealign/issues/110) - Add Readme documentation. Add nf-test for the pipeline.
 [#76](https://github.com/nf-core/multiplesequencealign/issues/76) - Add reading of trace files for shiny app.
+[#99](https://github.com/nf-core/multiplesequencealign/issues/99) - Add check for conflicting input parameters for stats and eval.
 
 ### `Fixed`
 

diff --git a/conf/igenomes.config b/conf/igenomes.config
diff --git a/main.nf b/main.nf
@@ -21,17 +21,6 @@ include { MULTIPLESEQUENCEALIGN  } from './workflows/multiplesequencealign'
 include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_multiplesequencealign_pipeline'
 include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_multiplesequencealign_pipeline'
 
-include { getGenomeAttribute      } from './subworkflows/local/utils_nfcore_multiplesequencealign_pipeline'
-
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    GENOME PARAMETER VALUES
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-//   This is an example of how to use getGenomeAttribute() to fetch parameters
-//   from igenomes.config using `--genome`
-
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     NAMED WORKFLOWS FOR PIPELINE

diff --git a/nextflow.config b/nextflow.config
@@ -25,8 +25,8 @@ params {
     // Evaluation
     skip_eval                   = false
     calc_sp                     = true
-    calc_tc                     = true
-    calc_irmsd                  = true
+    calc_tc                     = false
+    calc_irmsd                  = false
 
     skip_compress               = false
 
@@ -71,7 +71,7 @@ params {
     // Schema validation default options
     validationFailUnrecognisedParams = false
     validationLenientMode            = false
-    validationSchemaIgnoreParams     = 'genomes,igenomes_base'
+    validationSchemaIgnoreParams     = ''
     validationShowHiddenParams       = false
     validate_params                  = true
 

diff --git a/subworkflows/local/evaluate.nf b/subworkflows/local/evaluate.nf
@@ -108,7 +108,7 @@ workflow EVALUATE {
     tc      = tc_csv.map{ meta, csv -> csv }
     irmsd   = irmsd_csv.map{ meta, csv -> csv }
 
-    def number_of_evals = [params.calc_sp, params.calc_tc, params.calc_irmsd].count{ it == true }
+    def number_of_evals = [params.calc_sp, params.calc_tc, params.calc_irmsd].count(true)
     csvs_stats = sp.mix(tc).mix(irmsd).collect().map{ csvs -> [[id:"summary_eval"], csvs] }
     if(number_of_evals >= 2){
         MERGE_EVAL(csvs_stats)

diff --git a/subworkflows/local/stats.nf b/subworkflows/local/stats.nf
@@ -18,6 +18,7 @@ workflow STATS {
     ch_versions = Channel.empty()
     sim_csv = Channel.empty()
     seqstats_csv = Channel.empty()
+    stats_summary = Channel.empty()
 
     // // -------------------------------------------
     // //      SEQUENCE SIMILARITY
@@ -67,7 +68,7 @@ workflow STATS {
     seqstats = seqstats_csv.map{ meta, csv -> csv }
 
     csvs_stats = sim.mix(seqstats).collect().map{ csvs -> [[id:"summary_stats"], csvs] }
-    def number_of_stats = [params.calc_sim, params.calc_seq_stats].count{ it == true }
+    def number_of_stats = [params.calc_sim, params.calc_seq_stats].count(true)
     if(number_of_stats >= 2){
         MERGE_STATS(csvs_stats)
         ch_versions = ch_versions.mix(MERGE_STATS.out.versions)

diff --git a/subworkflows/local/utils_nfcore_multiplesequencealign_pipeline/main.nf b/subworkflows/local/utils_nfcore_multiplesequencealign_pipeline/main.nf
@@ -161,7 +161,8 @@ workflow PIPELINE_COMPLETION {
 // Check and validate pipeline parameters
 //
 def validateInputParameters() {
-    genomeExistsError()
+    statsParamsWarning()
+    evalParamsWarning()
 }
 
 //
@@ -178,29 +179,54 @@ def validateInputSamplesheet(input) {
 
     return [ metas[0], fastqs ]
 }
+
 //
-// Get attribute from genome config file e.g. fasta
+// Warning if incorrect combination of stats parameters are used
 //
-def getGenomeAttribute(attribute) {
-    if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) {
-        if (params.genomes[ params.genome ].containsKey(attribute)) {
-            return params.genomes[ params.genome ][ attribute ]
+def statsParamsWarning() {
+    if (params.skip_stats){
+        if(params.calc_sim || params.calc_seq_stats) {
+            def warning_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
+                "  WARNING: The param skip_stats is set to '${params.skip_stats}'.\n" +
+                "  The following params have values calc_sim: ${params.calc_sim} and calc_seq_stats: ${params.calc_seq_stats} \n" +
+                "  As skip_stats is set to true, the params.calc_sim and params.calc_seq_stats will be set by default to false. \n" +
+                "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
+            println(warning_string)
         }
     }
-    return null
+    if (!params.skip_stats && !params.calc_sim && !params.calc_seq_stats){
+        params.skip_stats = true
+        def warning_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
+                "  WARNING: The param skip_stats has been changed from false to true'.\n" +
+                "  None of the modules withing the stats subworkflow was activated.  \n" +
+                "  To activate them you can use param.calc_sim, params.calc_seq_stats.  \n" +
+                "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
+        println(warning_string)
+    }
 }
 
 //
-// Exit pipeline if incorrect --genome key provided
+// Warning if incorrect combination of eval parameters are used
 //
-def genomeExistsError() {
-    if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) {
-        def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
-            "  Genome '${params.genome}' not found in any config files provided to the pipeline.\n" +
-            "  Currently, the available genome keys are:\n" +
-            "  ${params.genomes.keySet().join(", ")}\n" +
-            "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
-        error(error_string)
+def evalParamsWarning() {
+    if (params.skip_eval){
+        if(params.calc_sp || params.calc_tc || params.calc_irmsd) {
+            def warning_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
+                "  WARNING: The param skip_eval is set to '${params.skip_eval}'.\n" +
+                "  The following params have values params.calc_sp: ${params.calc_sp}, params.calc_tc: ${params.calc_tc} and params.calc_irms: ${params.calc_irmsd} \n" +
+                "  As skip_eval is set to true, the params.calc_sp, params.calc_tc and params.calc_irmsd are set by default to false. \n" +
+                "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
+            println(warning_string)
+        }
+    }
+    if (!params.skip_eval && !params.calc_sp && !params.calc_tc && !params.calc_irmsd ){
+            params.skip_eval = true
+            def warning_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
+                    "  WARNING: The param skip_eval has been changed from false to true'.\n" +
+                    "  None of the modules withing the stats subworkflow was activated.  \n" +
+                    "  To activate them you can use param.calc_sp, params.calc_tc, params.calc_irmsd.  \n" +
+                    "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
+            println(warning_string)
     }
 }
 

diff --git a/workflows/multiplesequencealign.nf b/workflows/multiplesequencealign.nf
@@ -205,9 +205,13 @@ workflow MULTIPLESEQUENCEALIGN {
         .set { stats_and_evaluation }
 
     if( !params.skip_stats && !params.skip_eval ){
-        MERGE_STATS_EVAL(stats_and_evaluation)
-        stats_and_evaluation_summary = MERGE_STATS_EVAL.out.csv
-        ch_versions                  = ch_versions.mix(MERGE_STATS_EVAL.out.versions)
+        def number_of_stats = [params.calc_sim, params.calc_seq_stats].count(true)
+        def number_of_evals = [params.calc_sp, params.calc_tc, params.calc_irmsd].count(true)
+        if (number_of_evals > 0 && number_of_stats > 0 ){
+            MERGE_STATS_EVAL(stats_and_evaluation)
+            stats_and_evaluation_summary = MERGE_STATS_EVAL.out.csv
+            ch_versions                  = ch_versions.mix(MERGE_STATS_EVAL.out.versions)
+        }
     }else{
         stats_and_evaluation_summary = stats_and_evaluation
     }