major refactoring of PLFQ to a probabilistic approach

modules/local/openms/proteomicslfq/main.nf

@@ -31,11 +31,12 @@ process PROTEOMICSLFQ {
     script:
     def args = task.ext.args ?: ''
     def msstats_present = params.quantification_method == "feature_intensity" ? "-out_msstats ${expdes.baseName}_msstats_in.csv" : ""
-    def id_transfer_threshold = (params.quantification_method == "feature_intensity") && (params.transfer_ids != "off") ? "-id_transfer_threshold ${params.id_transfer_threshold}" : ""
     def triqler_present = (params.quantification_method == "feature_intensity") && (params.add_triqler_output) ? "-out_triqler ${expdes.baseName}_triqler_in.tsv" : ""
     def decoys_present = (params.quantify_decoys || ((params.quantification_method == "feature_intensity") && params.add_triqler_output)) ? '-PeptideQuantification:quantify_decoys' : ''
     def mzml_sorted = mzmls.collect().sort{ a, b -> a.name <=> b.name}
     def id_sorted = id_files.collect().sort{ a, b -> a.name <=> b.name}
+    def feature_with_id_min_score =  "-feature_with_id_min_score ${params.feature_with_id_min_score}"
+    def feature_without_id_min_score = params.targeted_only == false ? "-feature_without_id_min_score ${params.feature_without_id_min_score}" : ""
 
     """
     ProteomicsLFQ \\
@@ -47,9 +48,10 @@ process PROTEOMICSLFQ {
         -protein_inference ${params.protein_inference_method} \\
         -quantification_method ${params.quantification_method} \\
         -targeted_only ${params.targeted_only} \\
+        ${feature_with_id_min_score} \\
+        ${feature_without_id_min_score} \\
         -mass_recalibration ${params.mass_recalibration} \\
-        -transfer_ids ${params.transfer_ids == 'off' ? 'false' : params.transfer_ids} \\
-        ${id_transfer_threshold} \\
+        -Seeding:intThreshold ${params.lfq_intensity_threshold} \\
         -protein_quantification ${params.protein_quant} \\
         -alignment_order ${params.alignment_order} \\
         ${decoys_present} \\

nextflow.config

@@ -148,13 +148,16 @@ params {
     protein_inference_method = 'aggregation'
     protein_quant            = 'unique_peptides'
     quantification_method    = 'feature_intensity'
-    targeted_only            = true
     mass_recalibration       = false
-    transfer_ids             = 'off'
     alignment_order          = 'star'
     add_triqler_output       = false
     quantify_decoys          = false
-    id_transfer_threshold    = 0.50 // only used if targeted_only is set to false (default)
+
+    // ProteomicsLFQ MBR parameters
+    targeted_only            = true // If false MBR will be applied for quantification of all proteins
+    feature_with_id_min_score = 0.10
+    feature_without_id_min_score = 0.75
+    lfq_intensity_threshold = 1000
 
     // Bruker data
     convert_dotd            = false
@@ -170,7 +173,7 @@ params {
     pg_level                = 2
     species_genes           = false
     diann_normalize         = true
-    diann_speclib           = ''
+    diann_speclib           = null
 
     // MSstats general options
     msstats_remove_one_feat_prot    = true

nextflow_schema.json

@@ -827,24 +827,32 @@
                     "description": "Recalibrates masses based on precursor mass deviations to correct for instrument biases. (default: 'false')",
                     "fa_icon": "far fa-check-square"
                 },
-                "transfer_ids": {
-                    "type": "string",
-                    "description": "Tries a targeted requantification in files where an ID is missing, based on aggregate properties (i.e. RT) of the features in other aligned files (e.g. 'mean' of RT). (**WARNING:** increased memory consumption and runtime). 'off' turns this feature off. (default: 'off')",
-                    "default": "off",
-                    "enum": ["off", "mean"],
-                    "fa_icon": "fas fa-list-ol"
-                },
                 "targeted_only": {
                     "type": "boolean",
                     "description": "Only looks for quantifiable features at locations with an identified spectrum. Set to false to include unidentified features so they can be linked and matched to identified ones (= match between runs). (default: 'true')",
                     "default": true,
                     "fa_icon": "far fa-check-square"
                 },
-                "id_transfer_threshold": {
+                "feature_with_id_min_score": {
                     "type": "number",
-                    "description": "The maximum percentage of samples that will be accepted for matching between runs (default: 0.5)",
-                    "default": 0.5,
-                    "fa_icon": "fas fa-filter"
+                    "description": "The minimum probability (e.g.: 0.25) an identified (=id targeted) feature must have to be kept for alignment and linking (0=no filter).",
+                    "default": 0.0,
+                    "fa_icon": "fas fa-filter",
+                    "help_text": "The minimum probability (e.g.: 0.25) an identified (=id targeted) feature must have to be kept for alignment and linking (0=no filter). (default: '0.0') (min: '0.0' max: '1.0')"
+                },
+                "feature_without_id_min_score": {
+                    "type": "number",
+                    "description": "The minimum probability (e.g.: 0.75) an unidentified feature must have to be kept for alignment and linking (0=no filter).",
+                    "default": 0.0,
+                    "fa_icon": "fas fa-filter",
+                    "help_text": "The minimum probability (e.g.: 0.75) an unidentified feature must have to be kept for alignment and linking (0=no filter). (default: '0.0') (min: '0.0' max: '1.0')"
+                },
+                "lfq_intensity_threshold": {
+                    "type": "number",
+                    "description": "The minimum intensity for a feature to be considered for quantification. (default: '10000')",
+                    "default": 10000,
+                    "fa_icon": "fas fa-filter",
+                    "help_text": "The minimum intensity for a feature to be considered for quantification. (default: '10000')"
                 },
                 "alignment_order": {
                     "type": "string",

workflows/dia.nf

@@ -55,7 +55,7 @@ workflow DIA {
     //
     // MODULE: SILICOLIBRARYGENERATION
     //
-    if (params.diann_speclib) {
+    if (params.diann_speclib != null) {
         speclib = Channel.fromPath(params.diann_speclib)
     } else {
         SILICOLIBRARYGENERATION(ch_searchdb, DIANNCFG.out.diann_cfg)