ms2rescore 3.1.0.dev2__tar.gz → 3.1.0.dev4__tar.gz

{ms2rescore-3.1.0.dev2 → ms2rescore-3.1.0.dev4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ms2rescore
-Version: 3.1.0.dev2
+Version: 3.1.0.dev4
 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.dev2 → ms2rescore-3.1.0.dev4}/ms2rescore/__init__.py

@@ -1,6 +1,6 @@
 """MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and RTs."""
 
-__version__ = "3.1.0-dev2"
+__version__ = "3.1.0-dev4"
 
 from warnings import filterwarnings
 

{ms2rescore-3.1.0.dev2 → ms2rescore-3.1.0.dev4}/ms2rescore/__main__.py

@@ -1,6 +1,7 @@
 """MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and RTs."""
 
 import argparse
+import cProfile
 import importlib.resources
 import json
 import logging
@@ -139,6 +140,14 @@ def _argument_parser() -> argparse.ArgumentParser:
         dest="fasta_file",
         help="path to FASTA file",
     )
+    parser.add_argument(
+        "--profile",
+        # metavar="BOOL",
+        action="store_true",
+        # type=bool,
+        # dest="profile",
+        help="boolean to enable profiling with cProfile",
+    )
 
     return parser
 
@@ -161,6 +170,18 @@ def _setup_logging(passed_level: str, log_file: Union[str, Path]):
     )
 
 
+def profile(fnc, filepath):
+    """A decorator that uses cProfile to profile a function"""
+
+    def inner(*args, **kwargs):
+        with cProfile.Profile() as profiler:
+            return_value = fnc(*args, **kwargs)
+        profiler.dump_stats(filepath + ".profile.prof")
+        return return_value
+
+    return inner
+
+
 def main_tims():
     """Run MS²Rescore command-line interface in TIMS²Rescore mode."""
     main(tims=True)
@@ -196,7 +217,11 @@ def main(tims=False):
 
     # Run MS²Rescore
     try:
-        rescore(configuration=config)
+        if cli_args.profile:
+            profiled_rescore = profile(rescore, config["ms2rescore"]["output_path"])
+            profiled_rescore(configuration=config)
+        else:
+            rescore(configuration=config)
     except Exception as e:
         LOGGER.exception(e)
         sys.exit(1)

{ms2rescore-3.1.0.dev2 → ms2rescore-3.1.0.dev4}/ms2rescore/package_data/config_schema.json

@@ -157,6 +157,11 @@
                     "description": "Write an HTML report with various QC metrics and charts",
                     "type": "boolean",
                     "default": false
+                },
+                "profile": {
+                    "description": "Write an txt report using cProfile for profiling",
+                    "type": "boolean",
+                    "default": false
                 }
             }
         }

{ms2rescore-3.1.0.dev2 → ms2rescore-3.1.0.dev4}/ms2rescore/rescoring_engines/mokapot.py

@@ -20,7 +20,8 @@ If you use Mokapot through MS²Rescore, please cite:
 """
 
 import logging
-from typing import Any, List, Optional, Tuple, Dict
+import re
+from typing import Any, Dict, List, Optional, Tuple
 
 import mokapot
 import numpy as np
@@ -93,15 +94,12 @@ def rescore(
     confidence_results, models = brew(lin_psm_data, rng=8, **kwargs)
 
     # Reshape confidence estimates to match PSMList
+    keys = ["mokapot score", "mokapot q-value", "mokapot PEP"]
     mokapot_values_targets = (
-        confidence_results.confidence_estimates["psms"]
-        .set_index("index")
-        .sort_index()[["mokapot score", "mokapot q-value", "mokapot PEP"]]
+        confidence_results.confidence_estimates["psms"].set_index("index").sort_index()[keys]
     )
     mokapot_values_decoys = (
-        confidence_results.decoy_confidence_estimates["psms"]
-        .set_index("index")
-        .sort_index()[["mokapot score", "mokapot q-value", "mokapot PEP"]]
+        confidence_results.decoy_confidence_estimates["psms"].set_index("index").sort_index()[keys]
     )
     q = np.full((len(psm_list), 3), np.nan)
     q[mokapot_values_targets.index] = mokapot_values_targets.values
@@ -112,6 +110,28 @@ def rescore(
     psm_list["qvalue"] = q[:, 1]
     psm_list["pep"] = q[:, 2]
 
+    # Repeat for peptide-level scores
+    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")
+
+    peptidoform_without_charge = re.compile(r"(/\d+$)")
+    for psm in psm_list:
+        peptide_scores = peptide_info[
+            (peptidoform_without_charge.sub("", str(psm.peptidoform), 1), psm.run)
+        ]
+        psm.metadata.update(
+            {
+                "peptide_score": peptide_scores["mokapot score"],
+                "peptide_qvalue": peptide_scores["mokapot q-value"],
+                "peptide_pep": peptide_scores["mokapot PEP"],
+            }
+        )
+
     # Write results
     if write_weights:
         try:
@@ -174,7 +194,7 @@ def convert_psm_list(
 
     # Ensure filename for FlashLFQ txt output
     if not combined_df["run"].notnull().all():
-        combined_df["run"] = "ms_run"
+        combined_df["run"] = "nan"
 
     feature_names = [f"feature:{f}" for f in feature_names] if feature_names else None