Refactoring

ms2rescore/__main__.py

@@ -6,6 +6,7 @@
 import json
 import logging
 import sys
+from datetime import datetime
 from pathlib import Path
 from typing import Union
 
@@ -196,7 +197,13 @@ def profile(fnc, filepath):
     def inner(*args, **kwargs):
         with cProfile.Profile() as profiler:
             return_value = fnc(*args, **kwargs)
-        profiler.dump_stats(filepath + ".profile.prof")
+
+        # Add timestamp to profiler output filename
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        profile_filename = f"{filepath}.profile_{timestamp}.prof"
+        profiler.dump_stats(profile_filename)
+        LOGGER.info(f"Profile data written to: {profile_filename}")
+
         return return_value
 
     return inner
@@ -248,6 +255,7 @@ def main(tims=False):
     # Run MS²Rescore
     try:
         if config["ms2rescore"]["profile"]:
+            LOGGER.info("Profiling enabled")
             profiled_rescore = profile(rescore, config["ms2rescore"]["output_path"])
             profiled_rescore(configuration=config)
         else:

ms2rescore/core.py

@@ -13,7 +13,11 @@
 from ms2rescore.parse_spectra import add_precursor_values
 from ms2rescore.report import generate
 from ms2rescore.rescoring_engines import mokapot, percolator
-from ms2rescore.rescoring_engines.mokapot import add_peptide_confidence, add_psm_confidence
+from ms2rescore.rescoring_engines.mokapot import (
+    add_peptide_confidence,
+    add_psm_confidence,
+)
+from ms2rescore.utils import filter_mumble_psms
 
 logger = logging.getLogger(__name__)
 
@@ -114,6 +118,10 @@ def rescore(configuration: Dict, psm_list: Optional[PSMList] = None) -> None:
         )
     psm_list = psm_list[psms_with_features]
 
+    if "mumble" in config["psm_generator"]:
+        # Remove PSMs where matched_ions_pct drops 25% below the original hit
+        psm_list = filter_mumble_psms(psm_list, threshold=0.75)
+
     # Write feature names to file
     _write_feature_names(feature_names, output_file_root)
 
@@ -219,7 +227,10 @@ def _write_feature_names(feature_names, output_file_root):
 def _log_id_psms_before(psm_list: PSMList, fdr: float = 0.01, max_rank: int = 1) -> int:
     """Log #PSMs identified before rescoring."""
     id_psms_before = (
-        (psm_list["qvalue"] <= 0.01) & (psm_list["rank"] <= max_rank) & (~psm_list["is_decoy"])
+        (psm_list["qvalue"] <= 0.01)
+        & (psm_list["rank"] <= max_rank)
+        & (~psm_list["is_decoy"])
+        & ([metadata.get("original_psm", True) for metadata in psm_list["metadata"]])
     ).sum()
     logger.info(
         f"Found {id_psms_before} identified PSMs with rank <= {max_rank} at {fdr} FDR before "
@@ -285,7 +296,9 @@ def _calculate_confidence(psm_list: PSMList) -> PSMList:
     )
 
     # Recalculate confidence
-    new_confidence = lin_psm_data.assign_confidence(scores=psm_list["score"])
+    new_confidence = lin_psm_data.assign_confidence(
+        scores=list(psm_list["score"])
+    )  # explicity make it a list to avoid TypingError: Failed in nopython mode pipeline (step: nopython frontend) in mokapot
 
     # Add new confidence estimations to PSMList
     add_psm_confidence(psm_list, new_confidence)

ms2rescore/exceptions.py

@@ -41,3 +41,9 @@ class RescoringError(MS2RescoreError):
     """Error while rescoring PSMs."""
 
     pass
+
+
+class ParseSpectrumError(MS2RescoreError):
+    """Error while rescoring PSMs."""
+
+    pass

ms2rescore/feature_generators/__init__.py

@@ -7,14 +7,14 @@
 from ms2rescore.feature_generators.deeplc import DeepLCFeatureGenerator
 from ms2rescore.feature_generators.im2deep import IM2DeepFeatureGenerator
 from ms2rescore.feature_generators.ionmob import IonMobFeatureGenerator
-from ms2rescore.feature_generators.maxquant import MaxQuantFeatureGenerator
+from ms2rescore.feature_generators.ms2 import MS2FeatureGenerator
 from ms2rescore.feature_generators.ms2pip import MS2PIPFeatureGenerator
 
 FEATURE_GENERATORS: dict[str, type[FeatureGeneratorBase]] = {
     "basic": BasicFeatureGenerator,
     "ms2pip": MS2PIPFeatureGenerator,
     "deeplc": DeepLCFeatureGenerator,
-    "maxquant": MaxQuantFeatureGenerator,
     "ionmob": IonMobFeatureGenerator,
     "im2deep": IM2DeepFeatureGenerator,
+    "ms2": MS2FeatureGenerator,
 }

ms2rescore/feature_generators/basic.py

@@ -56,6 +56,7 @@ def add_features(self, psm_list: PSMList) -> None:
         charge_states = np.array([psm.peptidoform.precursor_charge for psm in psm_list])
         precursor_mzs = psm_list["precursor_mz"]
         scores = psm_list["score"]
+        peptide_lengths = np.array([len(psm.peptidoform.sequence) for psm in psm_list])
 
         has_charge = None not in charge_states
         has_mz = None not in precursor_mzs and has_charge
@@ -74,13 +75,25 @@ def add_features(self, psm_list: PSMList) -> None:
         if has_score:
             self._feature_names.append("search_engine_score")
 
+        if has_mz and has_charge:
+            experimental_mass = (precursor_mzs * charge_n) - (charge_n * 1.007276466812)
+            theoretical_mass = (theo_mz * charge_n) - (charge_n * 1.007276466812)
+            mass_error = experimental_mass - theoretical_mass
+            self._feature_names.extend(["theoretical_mass", "experimental_mass", "mass_error"])
+
+        self._feature_names.append("pep_len")
+
         for i, psm in enumerate(psm_list):
             psm.rescoring_features.update(
                 dict(
                     **{"charge_n": charge_n[i]} if has_charge else {},
                     **charge_one_hot[i] if has_charge else {},
                     **{"abs_ms1_error_ppm": abs_ms1_error_ppm[i]} if has_mz else {},
                     **{"search_engine_score": scores[i]} if has_score else {},
+                    **{"theoretical_mass": theoretical_mass[i]} if has_mz and has_charge else {},
+                    **{"experimental_mass": experimental_mass[i]} if has_mz and has_charge else {},
+                    **{"mass_error": mass_error[i]} if has_mz and has_charge else {},
+                    **{"pep_len": peptide_lengths[i]},
                 )
             )