remove posterior_probabilities parameter.

bigbio · Nov 28, 2024 · c23d530 · c23d530
1 parent 2120212
commit c23d530
Show file tree

Hide file tree

Showing 15 changed files with 247 additions and 427 deletions.
diff --git a/conf/modules.config b/conf/modules.config
@@ -65,45 +65,6 @@ if (params.add_decoys) {
     }
 }
 
-if (params.posterior_probabilities == "percolator") {
-    process {
-        // EXTRACTPSMFEATURE
-        withName: '.*:EXTRACTPSMFEATURES' {
-            ext.args    = "-debug $params.extractpsmfeature_debug"
-            publishDir  = [
-                path: { "${params.outdir}/extractpsmfeature" },
-                mode: params.publish_dir_mode,
-                pattern: '*.log',
-                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-            ]
-        }
-
-        //PERCOLATOR
-        withName: '.*:PERCOLATOR' {
-            ext.args    = [
-                "-debug $params.percolator_debug",
-                (params.fdr_level != 'psm_level_fdrs') ? "-" + params.fdr_level : ""
-            ].join(' ').trim()
-        }
-    }
-} else {
-    process {
-        // IDPEP
-        withName: '.*:IDPEP' {
-            ext.args    = "-debug $params.idpep_debug"
-        }
-    }
-
-    if (params.search_engines.split(",").size() == 1) {
-        process {
-            // FDRIDPEP
-            withName: '.*:FDRIDPEP' {
-                ext.args    = "-PSM true -protein false"
-            }
-        }
-    }
-}
-
 if (params.search_engines.split(",").size() == 1) {
     process {
 
@@ -206,6 +167,25 @@ process {
     withName: '.*:TMT:PROTEINQUANT:MSSTATSCONVERTER' {
         ext.args    = "-debug $params.protein_quant_debug"
     }
+
+    // EXTRACTPSMFEATURE
+    withName: '.*:EXTRACTPSMFEATURES' {
+        ext.args    = "-debug $params.extractpsmfeature_debug"
+        publishDir  = [
+            path: { "${params.outdir}/extractpsmfeature" },
+            mode: params.publish_dir_mode,
+            pattern: '*.log',
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    //PERCOLATOR
+    withName: '.*:PERCOLATOR' {
+        ext.args    = [
+            "-debug $params.percolator_debug",
+            (params.fdr_level != 'psm_level_fdrs') ? "-" + params.fdr_level : ""
+        ].join(' ').trim()
+    }
 }
 
 if (params.protein_inference_method.equals("bayesian")) {
@@ -278,7 +258,7 @@ process {
     withName: 'MS2RESCORE' {
         ext.args   = [
             "--ms2pip_model ${params.ms2pip_model}",
-            "--rescoring_engine ${params.posterior_probabilities}",
+            "--rescoring_engine 'percolator'",
             "--calibration_set_size ${params.calibration_set_size}",
             "--test_fdr ${params.test_FDR}",
             params.feature_generators.trim() ? "--feature_generators ${params.feature_generators}" : ''

diff --git a/conf/test_dda_id.config b/conf/test_dda_id.config
@@ -27,7 +27,6 @@ params {
     // Input data
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/tmt_ci/PXD000001.sdrf.tsv'
     database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/tmt_ci/erwinia_carotovora.fasta'
-    posterior_probabilities = "percolator"
     search_engines = "msgf,comet"
     add_decoys = true
     decoy_string = "rev"

diff --git a/conf/test_full_lfq.config b/conf/test_full_lfq.config
@@ -27,7 +27,6 @@ params {
     // Input data
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/lfq_full/PXD001819.sdrf.tsv'
     database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/lfq_full/yeast_2021_04_reviewed.fasta'
-    posterior_probabilities = "percolator"
     search_engines = "msgf,comet"
     add_decoys = true
     add_triqler_output = true

diff --git a/conf/test_full_tmt.config b/conf/test_full_tmt.config
@@ -28,7 +28,6 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/tmt_full/PXD005486.sdrf.tsv'
 
     database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata-aws/tmt_full/uniprot_E_coli_13spiked_reviewed_2021_04.fasta'
-    posterior_probabilities = "percolator"
     search_engines = "comet,msgf"
     protein_level_fdr_cutoff = 0.01
     psm_level_fdr_cutoff = 0.01

diff --git a/conf/test_lfq.config b/conf/test_lfq.config
@@ -28,7 +28,6 @@ params {
     labelling_type = "label free sample"
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/lfq_ci/BSA/BSA_design_urls.tsv'
     database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/lfq_ci/BSA/18Protein_SoCe_Tr_detergents_trace_target_decoy.fasta'
-    posterior_probabilities = "fit_distributions"
     search_engines = "comet"
     decoy_string= "rev"
     add_triqler_output = true

diff --git a/conf/test_lfq_sage.config b/conf/test_lfq_sage.config
@@ -30,7 +30,6 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/lfq_ci/BSA/BSA_design_urls.tsv'
     database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/lfq_ci/BSA/18Protein_SoCe_Tr_detergents_trace.fasta'
     add_decoys = true
-    posterior_probabilities = "fit_distributions"
     search_engines = "sage,comet"
     precursor_mass_tolerance = 20
     fragment_mass_tolerance = 0.1

diff --git a/conf/test_tmt.config b/conf/test_tmt.config
@@ -28,7 +28,6 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/tmt_ci/PXD000001.sdrf.tsv'
 
     database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/tmt_ci/erwinia_carotovora.fasta'
-    posterior_probabilities = "percolator"
     search_engines = "comet,msgf"
     psm_level_fdr_cutoff = 1.0
     decoy_string = "rev"

diff --git a/conf/test_tmt_corr.config b/conf/test_tmt_corr.config
@@ -28,7 +28,6 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/tmt_ci/PXD000001.sdrf.tsv'
 
     database = 'https://raw.githubusercontent.com/nf-core/test-datasets/quantms/testdata/tmt_ci/erwinia_carotovora.fasta'
-    posterior_probabilities = "percolator"
     search_engines = "comet,msgf"
     psm_level_fdr_cutoff = 1.0
     decoy_string = "rev"

diff --git a/modules/local/openms/extractpsmfeatures/main.nf b/modules/local/openms/extractpsmfeatures/main.nf
diff --git a/modules/local/openms/extractpsmfeatures/meta.yml b/modules/local/openms/extractpsmfeatures/meta.yml
diff --git a/nextflow.config b/nextflow.config
@@ -26,7 +26,6 @@ params {
     use_ols_cache_only         = true // Use only the OLS cache for ontology validation (no network requests)
 
     // Tools flags
-    posterior_probabilities  = 'percolator'
     add_decoys               = false
     skip_rescoring           = false
     search_engines           = 'comet'

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -521,13 +521,6 @@
                     "default": 0.15,
                     "fa_icon": "fas fa-filter"
                 },
-                "posterior_probabilities": {
-                    "type": "string",
-                    "description": "How to calculate posterior probabilities for PSMs:\n\n* 'percolator' = Re-score based on PSM-feature-based SVM and transform distance\n    to hyperplane for posteriors\n* 'fit_distributions' = Fit positive and negative distributions to scores\n    (similar to PeptideProphet)\n\n* 'mokapot' = Re-score based on PSM-feature-based semi-supervised learning algorithm introduced by Percolator",
-                    "fa_icon": "fas fa-list-ol",
-                    "default": "percolator",
-                    "enum": ["percolator", "fit_distributions", "mokapot"]
-                },
                 "run_fdr_cutoff": {
                     "type": "number",
                     "description": "FDR cutoff on PSM level (or peptide level; see Percolator options) *per run* before going into feature finding, map alignment and inference. This can be seen as a pre-filter. See ",