ms2rescore 3.1.0.dev1__tar.gz → 3.1.0.dev3__tar.gz

{ms2rescore-3.1.0.dev1 → ms2rescore-3.1.0.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ms2rescore
-Version: 3.1.0.dev1
+Version: 3.1.0.dev3
 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.dev1 → ms2rescore-3.1.0.dev3}/ms2rescore/__init__.py

@@ -1,6 +1,6 @@
 """MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and RTs."""
 
-__version__ = "3.1.0-dev1"
+__version__ = "3.1.0-dev3"
 
 from warnings import filterwarnings
 

{ms2rescore-3.1.0.dev1 → ms2rescore-3.1.0.dev3}/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.dev1 → ms2rescore-3.1.0.dev3}/ms2rescore/core.py

@@ -175,8 +175,8 @@ def _fill_missing_precursor_info(psm_list, config):
         get_missing_values(psm_list, config, rt_required=rt_required, im_required=im_required)
 
     # Check if values are now present
-    for value_name in ["retention_time", "ion_mobility"]:
-        if (
+    for value_name, required in [("retention_time", rt_required), ("ion_mobility", im_required)]:
+        if required and (
             0.0 in psm_list[value_name]
             or None in psm_list[value_name]
             or np.isnan(psm_list[value_name]).any()

{ms2rescore-3.1.0.dev1 → ms2rescore-3.1.0.dev3}/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.dev1 → ms2rescore-3.1.0.dev3}/ms2rescore/report/charts.py

@@ -373,7 +373,7 @@ def identification_overlap(
         return figure
 
     levels = before.levels  # ["psms", "peptides", "proteins"] if all available
-    indexers = ["index", "index", "mokapot protein group"]
+    indexers = ["index", "peptide", "mokapot protein group"]
 
     overlap_data = defaultdict(dict)
     for level, indexer in zip(levels, indexers):
@@ -386,7 +386,7 @@ def identification_overlap(
         set_after = set(df_after[df_after["mokapot q-value"] <= 0.01][indexer])
 
         overlap_data["removed"][level] = -len(set_before - set_after)
-        overlap_data["retained"][level] = len(set_before | set_after)
+        overlap_data["retained"][level] = len(set_after.intersection(set_before))
         overlap_data["gained"][level] = len(set_after - set_before)
 
     colors = ["#953331", "#316395", "#319545"]

{ms2rescore-3.1.0.dev1 → ms2rescore-3.1.0.dev3}/ms2rescore/report/generate.py

@@ -185,7 +185,7 @@ def _get_stats_context(confidence_before, confidence_after):
                 "item": level_name,
                 "card_color": card_color,
                 "number": after,
-                "diff": f"{after - before:+}",
+                "diff": f"({after - before:+})",
                 "percentage": f"{increase:.1f}%",
                 "is_increase": increase > 0,
                 "bar_percentage": before / after * 100 if increase > 0 else after / before * 100,

{ms2rescore-3.1.0.dev1 → ms2rescore-3.1.0.dev3}/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
@@ -31,6 +32,7 @@ from mokapot.dataset import LinearPsmDataset
 from pyteomics.mass import nist_mass
 
 logger = logging.getLogger(__name__)
+logging.getLogger("numba").setLevel(logging.WARNING)
 
 
 def rescore(
@@ -89,18 +91,15 @@ def rescore(
 
     # Rescore
     logger.debug(f"Mokapot brew options: `{kwargs}`")
-    confidence_results, models = brew(lin_psm_data, **kwargs)
+    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
@@ -111,6 +110,26 @@ def rescore(
     psm_list["qvalue"] = q[:, 1]
     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+$)")
+    for psm in psm_list:
+        peptide_scores = peptide_info[peptidoform_without_charge.sub("", str(psm.peptidoform), 1)]
+        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:
@@ -173,7 +192,7 @@ 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
 

{ms2rescore-3.1.0.dev1 → ms2rescore-3.1.0.dev3}/ms2rescore/rescoring_engines/percolator.py

@@ -20,8 +20,8 @@ If you use Percolator through MS²Rescore, please cite:
 import logging
 import subprocess
 from typing import Any, Dict, Optional
+from copy import deepcopy
 
-import numpy as np
 import psm_utils
 
 from ms2rescore.exceptions import MS2RescoreError
@@ -103,8 +103,15 @@ def rescore(
     # Need to be able to link back to original PSMs, so reindex spectrum IDs, but copy PSM list
     # to avoid modifying original...
     # TODO: Better approach for this?
-    psm_list_reindexed = psm_list.copy()
-    psm_list_reindexed["spectrum_id"] = np.arange(len(psm_list_reindexed))
+
+    psm_list_reindexed = deepcopy(psm_list)
+    psm_list_reindexed.set_ranks()
+    psm_list_reindexed["spectrum_id"] = [
+        f"{psm.get_usi(as_url=False)}_{psm.rank}" for psm in psm_list_reindexed
+    ]
+    spectrum_id_index = {
+        spectrum_id: index for index, spectrum_id in enumerate(psm_list_reindexed["spectrum_id"])
+    }
 
     _write_pin_file(psm_list_reindexed, pin_filepath)
 
@@ -134,10 +141,13 @@ def rescore(
         psm_list,
         percolator_kwargs["results-psms"],
         percolator_kwargs["decoy-results-psms"],
+        spectrum_id_index,
     )
 
 
-def _update_psm_scores(psm_list: psm_utils.PSMList, target_pout: str, decoy_pout: str):
+def _update_psm_scores(
+    psm_list: psm_utils.PSMList, target_pout: str, decoy_pout: str, spectrum_id_index: list
+):
     """
     Update PSM scores with Percolator results.
 
@@ -150,7 +160,9 @@ def _update_psm_scores(psm_list: psm_utils.PSMList, target_pout: str, decoy_pout
     psm_list_percolator = psm_utils.PSMList(psm_list=target_psms.psm_list + decoy_psms.psm_list)
 
     # Sort by reindexed spectrum_id so order matches original PSM list
-    psm_list_percolator[np.argsort(psm_list_percolator["spectrum_id"])]
+    psm_list_percolator = sorted(
+        psm_list_percolator, key=lambda psm: spectrum_id_index[psm["spectrum_id"]]
+    )
 
     if not len(psm_list) == len(psm_list_percolator):
         raise MS2RescoreError(