ms2rescore 3.1.0.dev3__tar.gz → 3.1.0.dev5__tar.gz

{ms2rescore-3.1.0.dev3 → ms2rescore-3.1.0.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ms2rescore
-Version: 3.1.0.dev3
+Version: 3.1.0.dev5
 Summary: MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and retention times.
 Keywords: MS2Rescore,MS2PIP,DeepLC,Percolator,proteomics,mass spectrometry,peptide identification,rescoring,machine learning
 Author: Ana Sílvia C. Silva, Robbin Bouwmeester, Louise Buur

{ms2rescore-3.1.0.dev3 → ms2rescore-3.1.0.dev5}/ms2rescore/__init__.py

@@ -1,6 +1,6 @@
 """MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and RTs."""
 
-__version__ = "3.1.0-dev3"
+__version__ = "3.1.0-dev5"
 
 from warnings import filterwarnings
 

{ms2rescore-3.1.0.dev3 → ms2rescore-3.1.0.dev5}/ms2rescore/report/generate.py

@@ -82,7 +82,7 @@ def generate_report(
     # Read config
     config = json.loads(files["configuration"].read_text())
 
-    logger.info("Recalculating confidence estimates...")
+    logger.debug("Recalculating confidence estimates...")
     fasta_file = config["ms2rescore"]["fasta_file"]
     confidence_before, confidence_after = get_confidence_estimates(psm_list, fasta_file)
 
@@ -139,7 +139,7 @@ def generate_report(
 
 def _collect_files(output_path_prefix, use_txt_log=False):
     """Collect all files generated by MS²Rescore."""
-    logger.info("Collecting files...")
+    logger.debug("Collecting files...")
     files = {
         "PSMs": Path(output_path_prefix + ".psms.tsv").resolve(),
         "configuration": Path(output_path_prefix + ".full-config.json").resolve(),
@@ -153,7 +153,7 @@ def _collect_files(output_path_prefix, use_txt_log=False):
     }
     for file, path in files.items():
         if Path(path).is_file():
-            logger.info("✅ Found %s: '%s'", file, path.as_posix())
+            logger.debug("✅ Found %s: '%s'", file, path.as_posix())
         else:
             logger.warning("❌ %s: '%s'", file, path.as_posix())
             files[file] = None

{ms2rescore-3.1.0.dev3 → ms2rescore-3.1.0.dev5}/ms2rescore/rescoring_engines/mokapot.py

@@ -111,17 +111,21 @@ def rescore(
     psm_list["pep"] = q[:, 2]
 
     # Repeat for peptide-level scores
-    peptide_info = pd.concat(
-        [
-            confidence_results.confidence_estimates["peptides"].set_index(["peptide"])[keys],
-            confidence_results.decoy_confidence_estimates["peptides"].set_index(["peptide"])[keys],
-        ],
-        axis=0,
-    ).to_dict(orient="index")
-
-    peptidoform_without_charge = re.compile(r"(/\d+$)")
+    peptides_targets = confidence_results.confidence_estimates["peptides"].set_index(
+        ["peptide", "run"]
+    )[keys]
+    peptides_decoys = confidence_results.decoy_confidence_estimates["peptides"].set_index(
+        ["peptide", "run"]
+    )[keys]
+    peptide_info = pd.concat([peptides_targets, peptides_decoys], axis=0).to_dict(orient="index")
+
+    # Add peptide-level scores to PSM metadata
+    run_key = "na" if not all(psm.run for psm in psm_list) else None
+    no_charge_pattern = re.compile(r"(/\d+$)")
     for psm in psm_list:
-        peptide_scores = peptide_info[peptidoform_without_charge.sub("", str(psm.peptidoform), 1)]
+        peptide_scores = peptide_info[
+            (no_charge_pattern.sub("", str(psm.peptidoform), 1), run_key or psm.run)
+        ]
         psm.metadata.update(
             {
                 "peptide_score": peptide_scores["mokapot score"],
@@ -192,7 +196,7 @@ def convert_psm_list(
 
     # Ensure filename for FlashLFQ txt output
     if not combined_df["run"].notnull().all():
-        combined_df["run"] = "nan"
+        combined_df["run"] = "na"
 
     feature_names = [f"feature:{f}" for f in feature_names] if feature_names else None