quantms-rescoring 0.0.1__py3-none-any.whl

quantms_rescoring-0.0.1.dist-info/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

quantms_rescoring-0.0.1.dist-info/METADATA

@@ -0,0 +1,67 @@
+Metadata-Version: 2.1
+Name: quantms-rescoring
+Version: 0.0.1
+Summary: quantms-rescoring: Python scripts and helpers for the quantMS workflow
+License: MIT
+Keywords: quantms,proteomics,mass-spectrometry,data-analysis,big data
+Author: Yasset Perez-Riverol
+Author-email: ypriverol@gmail.com
+Requires-Python: >=3.8,<3.11
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Dist: click
+Requires-Dist: deepLC (==2.2.38)
+Requires-Dist: ms2rescore (==3.0.3)
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: protobuf (==3.19.6)
+Requires-Dist: psm-utils (==0.8.3)
+Requires-Dist: pygam
+Requires-Dist: pyopenms
+Requires-Dist: scipy (==1.13.1)
+Project-URL: GitHub, https://github.com/bigbio/quantms-rescoring
+Project-URL: LICENSE, https://github.com/bigbio/quantms-rescoring/blob/main/LICENSE
+Project-URL: PyPi, https://pypi.org/project/quantms-rescoring/
+Project-URL: Quantms, https://quantms.org
+Description-Content-Type: text/markdown
+
+# quantms-rescoring
+    
+[![Python package](https://github.com/bigbio/quantms-rescoring/actions/workflows/python-package.yml/badge.svg)](https://github.com/bigbio/quantms-rescoring/actions/workflows/python-package.yml)
+[![codecov](https://codecov.io/gh/bigbio/quantms-rescoring/branch/main/graph/badge.svg?token=3ZQZQ2ZQ2D)](https://codecov.io/gh/bigbio/quantms-rescoring)
+[![PyPI version](https://badge.fury.io/py/quantms-rescoring.svg)](https://badge.fury.io/py/quantms-rescoring)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+quantms-rescoring is a Python tool for rescoring peptide-spectrum matches (PSMs) in idXML files. It is part of the quantms ecosystem package and leverages the MS²Rescore framework to improve identification confidence in proteomics data analysis.
+
+## Features
+
+- Enhanced Rescoring: Utilizes advanced rescoring engines like Percolator to refine PSM scores.
+- Flexible Feature Generators: Supports feature extraction using tools like MS²PIP, DeepLC, and custom generators.
+- Metadata Retention: Preserves essential metadata from the input idXML files.
+- Error Handling: Skips invalid PSMs and logs issues for transparent processing.
+- Seamless Integration: Built to integrate into proteomics workflows.
+
+## Installation
+
+To use quantms-rescoring, ensure the following dependencies are installed:
+
+- Python 3.8+
+- click
+- pyopenms
+- ms2rescore
+- psm_utils
+
+### Issues and Contributions
+
+For any issues or contributions, please open an issue in the [GitHub repository](https://github.com/bigbio/quantms/issues) - we use the quantms repo to control all issues—or PR in the [GitHub repository](https://github.com/bigbio/quantms-rescoring/pulls). 
+
+

quantms_rescoring-0.0.1.dist-info/RECORD

@@ -0,0 +1,8 @@
+quantmsrescore/__init__.py,sha256=sXLh7g3KC4QCFxcZGBTpG2scR7hmmBsMjq6LqRptkRg,22
+quantmsrescore/ms2rescore.py,sha256=bhlKs0n-pdzB4aZLvgnQW9XgvsuT8RTYTeC0wVnUMSk,17585
+quantmsrescore/rescoring.py,sha256=G83vA3ZBYww6SVmAHiiCiKNkZ4jJ5G5SiKWP_PaVIE4,525
+quantms_rescoring-0.0.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+quantms_rescoring-0.0.1.dist-info/METADATA,sha256=c-z4KXtoDy7-kU7xhbq0Mp4bC_T9amcfcj4laX0Iz3U,3161
+quantms_rescoring-0.0.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+quantms_rescoring-0.0.1.dist-info/entry_points.txt,sha256=0U63u4e67WvRJDI0oWNR5uqxQCc8BHKnbtwW422jioo,59
+quantms_rescoring-0.0.1.dist-info/RECORD,,

quantms_rescoring-0.0.1.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 1.9.1
+Root-Is-Purelib: true
+Tag: py3-none-any

quantms_rescoring-0.0.1.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+rescoring=quantmsrescore.rescoring:main
+

quantmsrescore/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1"

quantmsrescore/ms2rescore.py

@@ -0,0 +1,496 @@
+# Written by Jonas Scheid under the MIT license
+# Contributions by Yasset Perez-Riverol and Dai Chengxin
+# This script is part of the quantmsutils package
+
+import importlib.resources
+import json
+import logging
+
+import click
+import pyopenms as oms
+from ms2rescore import package_data, rescore
+from psm_utils import PSMList
+from psm_utils.io.idxml import IdXMLReader, IdXMLWriter
+from typing import Iterable, List, Union
+from pathlib import Path
+from psm_utils.psm import PSM
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+
+
+class IDXMLReaderPatch(IdXMLReader):
+    def __init__(self, filename: Union[Path, str], *args, **kwargs) -> None:
+        """
+        Patch Reader for idXML files based on IDXMLReader.
+
+        Parameters
+        ----------
+        filename: str, pathlib.Path
+            Path to idXML file.
+
+        Examples
+        --------
+        """
+        super().__init__(filename, *args, **kwargs)
+        self.protein_ids, self.peptide_ids = self._parse_idxml()
+        self.user_params_metadata = self._get_userparams_metadata(self.peptide_ids[0].getHits()[0])
+        self.rescoring_features = self._get_rescoring_features(self.peptide_ids[0].getHits()[0])
+        self.skip_invalid_psm = 0
+
+    def __iter__(self) -> Iterable[PSM]:
+        """
+        Iterate over file and return PSMs one-by-one.
+                Test cases will:
+
+        Input PSM 1: PeptideHit	with metavalue
+            "MSGF:ScoreRatio" value="0.212121212121212"/>
+            "MSGF:Energy" value="130.0"/>
+            "MSGF:lnEValue" value="-3.603969939390662"/>
+            "MSGF:lnExplainedIonCurrentRatio" value="-0.881402756873971"/>
+            "MSGF:lnNTermIonCurrentRatio" value="-1.931878317286471"/>
+            "MSGF:lnCTermIonCurrentRatio" value="-1.311462733724937"/>
+            "MSGF:lnMS2IonCurrent" value="9.702930189540499"/>
+            "MSGF:MeanErrorTop7" value="259.986879999999985"/>
+            "MSGF:sqMeanErrorTop7" value="6.75931777721344e04"/>
+            "MSGF:StdevErrorTop7" value="143.678020000000004"/>
+        PSM2: PeptideHit No above metaValue
+
+        Run:
+        reader = IDXMLReaderPatch(input_file)
+        psm_list = reader.read_file()
+
+        psm_list: return [PSM 1]
+
+        """
+        for peptide_id in self.peptide_ids:
+            for peptide_hit in peptide_id.getHits():
+                psm = self._parse_psm(self.protein_ids, peptide_id, peptide_hit)
+                if psm is not None:
+                    yield psm
+                else:
+                    self.skip_invalid_psm += 1
+
+    def _parse_psm(
+            self,
+            protein_ids: oms.ProteinIdentification,
+            peptide_id: oms.PeptideIdentification,
+            peptide_hit: oms.PeptideHit,
+    ) -> PSM:
+        """
+        Parse idXML :py:class:`~pyopenms.PeptideHit` to :py:class:`~psm_utils.psm.PSM`.
+
+        Uses additional information from :py:class:`~pyopenms.ProteinIdentification` and
+        :py:class:`~pyopenms.PeptideIdentification` to annotate parameters of the
+        :py:class:`~psm_utils.psm.PSM` object.
+        """
+        peptidoform = self._parse_peptidoform(
+            peptide_hit.getSequence().toString(), peptide_hit.getCharge()
+        )
+        # This is needed to calculate a qvalue before rescoring the PSMList
+        peptide_id_metadata = {
+            "idxml:score_type": str(peptide_id.getScoreType()),
+            "idxml:higher_score_better": str(peptide_id.isHigherScoreBetter()),
+            "idxml:significance_threshold": str(peptide_id.getSignificanceThreshold()),
+        }
+        peptide_hit_metadata = {
+            key: peptide_hit.getMetaValue(key) for key in self.user_params_metadata
+        }
+
+        # Get search engines score features and check valueExits
+        rescoring_features = {}
+        for key in self.rescoring_features:
+            feature = peptide_hit.metaValueExists(key)
+            if not feature:
+                return None
+            else:
+                rescoring_features[key] = float(peptide_hit.getMetaValue(key))
+
+        return PSM(
+            peptidoform=peptidoform,
+            spectrum_id=peptide_id.getMetaValue("spectrum_reference"),
+            run=self._get_run(protein_ids, peptide_id),
+            is_decoy=self._is_decoy(peptide_hit),
+            score=peptide_hit.getScore(),
+            precursor_mz=peptide_id.getMZ(),
+            retention_time=peptide_id.getRT(),
+            # NOTE: ion mobility will be supported by OpenMS in the future
+            protein_list=[
+                accession.decode() for accession in peptide_hit.extractProteinAccessionsSet()
+            ],
+            rank=peptide_hit.getRank() + 1,  # 0-based to 1-based
+            source="idXML",
+            # Storing proforma notation of peptidoform and UNIMOD peptide sequence for mapping back
+            # to original sequence in writer
+            provenance_data={str(peptidoform): peptide_hit.getSequence().toString()},
+            # Store metadata of PeptideIdentification and PeptideHit objects
+            metadata={**peptide_id_metadata, **peptide_hit_metadata},
+
+            rescoring_features=rescoring_features,
+        )
+
+
+def parse_cli_arguments_to_config(
+    config_file: str = None,
+    feature_generators: str = None,
+    ms2pip_model_dir: str = None,
+    ms2pip_model: str = None,
+    ms2_tolerance: float = None,
+    calibration_set_size: float = None,
+    rescoring_engine: str = None,
+    rng: int = None,
+    test_fdr: float = None,
+    processes: int = None,
+    spectrum_path: str = None,
+    fasta_file: str = None,
+    id_decoy_pattern: str = None,
+    lower_score_is_better: bool = None,
+    output_path: str = None,
+    log_level: str = None,
+    spectrum_id_pattern: str = None,
+    psm_id_pattern: str = None
+) -> dict:
+    if config_file is None:
+        config = json.load(
+            importlib.resources.open_text(package_data, "config_default.json")
+        )
+    else:
+        with open(config_file) as f:
+            config = json.load(f)
+    if feature_generators is not None:
+        feature_generators_list = feature_generators.split(",")
+        config["ms2rescore"]["feature_generators"] = {}
+        if "basic" in feature_generators_list:
+            config["ms2rescore"]["feature_generators"]["basic"] = {}
+        if "ms2pip" in feature_generators_list:
+            config["ms2rescore"]["feature_generators"]["ms2pip"] = {
+                "model_dir": ms2pip_model_dir,
+                "model": ms2pip_model,
+                "ms2_tolerance": ms2_tolerance,
+            }
+        if "deeplc" in feature_generators_list:
+            config["ms2rescore"]["feature_generators"]["deeplc"] = {
+                "deeplc_retrain": False,
+                "calibration_set_size": calibration_set_size,
+            }
+        if "maxquant" in feature_generators_list:
+            config["ms2rescore"]["feature_generators"]["maxquant"] = {}
+        if "ionmob" in feature_generators:
+            config["ms2rescore"]["feature_generators"]["ionmob"] = {}
+
+    if rescoring_engine is not None:
+        # Reset rescoring engine dict we want to allow only computing features
+        config["ms2rescore"]["rescoring_engine"] = {}
+        if rescoring_engine == "mokapot":
+            config["ms2rescore"]["rescoring_engine"]["mokapot"] = {
+                "write_weights": True,
+                "write_txt": False,
+                "write_flashlfq": False,
+                "rng": rng,
+                "test_fdr": test_fdr,
+                "max_workers": processes,
+            }
+        if rescoring_engine == "percolator":
+            logging.info(
+                "Percolator rescoring engine has been specified. Use the idXML containing rescoring features and run Percolator in a separate step."
+            )
+
+    if ms2pip_model_dir is not None:
+        config["ms2rescore"]["ms2pip_model_dir"] = ms2pip_model_dir
+    if ms2pip_model is not None:
+        config["ms2rescore"]["ms2pip_model"] = ms2pip_model
+    if ms2_tolerance is not None:
+        config["ms2rescore"]["ms2_tolerance"] = ms2_tolerance
+    if calibration_set_size is not None:
+        config["ms2rescore"]["calibration_set_size"] = calibration_set_size
+    if rng is not None:
+        config["ms2rescore"]["rng"] = rng
+    if spectrum_path is not None:
+        config["ms2rescore"]["spectrum_path"] = spectrum_path
+    if fasta_file is not None:
+        config["ms2rescore"]["fasta_file"] = fasta_file
+    if id_decoy_pattern is not None:
+        config["ms2rescore"]["id_decoy_pattern"] = id_decoy_pattern
+    if lower_score_is_better is not None:
+        config["ms2rescore"]["lower_score_is_better"] = lower_score_is_better
+    if processes is None:
+        processes = 1  # Default to single process
+    config["ms2rescore"]["processes"] = processes
+    if output_path is not None:
+        config["ms2rescore"]["output_path"] = output_path
+    else:
+        raise ValueError("Output path must be specified.")
+    if log_level is not None:
+        config["ms2rescore"]["log_level"] = log_level
+    if spectrum_id_pattern is not None:
+        config["ms2rescore"]["spectrum_id_pattern"] = spectrum_id_pattern
+    if psm_id_pattern is not None:
+        config["ms2rescore"]["psm_id_pattern"] = psm_id_pattern
+
+    return config
+
+
+def rescore_idxml(input_file, output_file, config) -> None:
+    """Rescore PSMs in an idXML file and keep other information unchanged."""
+    # Read PSMs
+    reader = IDXMLReaderPatch(input_file)
+    psm_list = reader.read_file()
+
+    if reader.skip_invalid_psm != 0:
+        logging.warning(
+            f"Removed {reader.skip_invalid_psm} PSMs without search engine features!"
+        )
+
+    # Rescore
+    rescore(config, psm_list)
+
+    # Filter out PeptideHits within PeptideIdentification(s) that could not be processed by all feature generators
+    peptide_ids_filtered = filter_out_artifact_psms(psm_list, reader.peptide_ids)
+
+    # Write
+    writer = IdXMLWriter(output_file, reader.protein_ids, peptide_ids_filtered)
+    writer.write_file(psm_list)
+
+
+def filter_out_artifact_psms(
+    psm_list: PSMList, peptide_ids: List[oms.PeptideIdentification]
+) -> List[oms.PeptideIdentification]:
+    """Filter out PeptideHits that could not be processed by all feature generators"""
+    num_mandatory_features = max([len(psm.rescoring_features) for psm in psm_list])
+    new_psm_list = PSMList(
+        psm_list=[
+            psm
+            for psm in psm_list
+            if len(psm.rescoring_features) == num_mandatory_features
+        ]
+    )
+
+    # get differing peptidoforms of both psm lists
+    psm_list_peptides = set(
+        [next(iter(psm.provenance_data.items()))[1] for psm in psm_list]
+    )
+    new_psm_list_peptides = set(
+        [next(iter(psm.provenance_data.items()))[1] for psm in new_psm_list]
+    )
+    not_supported_peptides = psm_list_peptides - new_psm_list_peptides
+
+    # no need to filter if all peptides are supported
+    if len(not_supported_peptides) == 0:
+        return peptide_ids
+    # Create new peptide ids and filter out not supported peptides
+    new_peptide_ids = []
+    for peptide_id in peptide_ids:
+        new_hits = []
+        for hit in peptide_id.getHits():
+            if hit.getSequence().toString() in not_supported_peptides:
+                continue
+            new_hits.append(hit)
+        if len(new_hits) == 0:
+            continue
+        peptide_id.setHits(new_hits)
+        new_peptide_ids.append(peptide_id)
+    logging.info(
+        f"Removed {len(psm_list_peptides) - len(new_psm_list_peptides)} PSMs. Peptides not supported: {not_supported_peptides}"
+    )
+    return new_peptide_ids
+
+
+@click.command(
+    "ms2rescore",
+    short_help="Rescore PSMs in an idXML file and keep other information unchanged.",
+)
+@click.option(
+    "-p",
+    "--psm_file",
+    help="Path to PSM file (idXML)",
+    required=True,
+    type=click.Path(exists=True),
+)
+@click.option(
+    "-s",
+    "--spectrum_path",
+    help="Path to MGF/mzML spectrum file or directory with spectrum files (default: derived from identification file)",
+    required=True,
+    type=click.Path(exists=True),
+)
+@click.option(
+    "-o",
+    "--output_path",
+    help="Path and stem for output file names (default: derive from identification file)",
+)
+@click.option(
+    "-l", "--log_level", help="Logging level (default: `info`)", default="info"
+)
+@click.option(
+    "-n",
+    "--processes",
+    help="Number of parallel processes available to MS²Rescore",
+    type=int,
+    default=16,
+)
+@click.option("-f", "--fasta_file", help="Path to FASTA file")
+@click.option(
+    "-t",
+    "--test_fdr",
+    help="The false-discovery rate threshold at which to evaluate the learned models. (default: 0.05)",
+    default=0.05,
+)
+@click.option(
+    "-fg",
+    "--feature_generators",
+    help="Comma-separated list of feature generators to use (default: `ms2pip,deeplc`). See rescoring doc for further information",
+    default="",
+)
+@click.option(
+    "-pipm",
+    "--ms2pip_model",
+    help="MS²PIP model (default: `Immuno-HCD`)",
+    type=str,
+    default="Immuno-HCD",
+)
+@click.option(
+    "-md",
+    "--ms2pip_model_dir",
+    help="The path of MS²PIP model (default: `./`)",
+    type=str,
+    default="./",
+)
+@click.option(
+    "-ms2tol",
+    "--ms2_tolerance",
+    help="Fragment mass tolerance [Da](default: `0.02`)",
+    type=float,
+    default=0.02,
+)
+@click.option(
+    "-cs",
+    "--calibration_set_size",
+    help="Percentage of number of calibration set for DeepLC (default: `0.15`)",
+    default=0.15,
+)
+@click.option(
+    "-re",
+    "--rescoring_engine",
+    help="Either mokapot or percolator (default: `percolator`)",
+    default="percolator",
+    type=click.Choice(["mokapot", "percolator"]),
+)
+@click.option(
+    "-rng",
+    "--rng",
+    help="Seed for mokapot's random number generator (default: `4711`)",
+    type=int,
+    default=4711,
+)
+@click.option(
+    "-d",
+    "--id_decoy_pattern",
+    help="Regex decoy pattern (default: `DECOY_`)",
+    default="^DECOY_",
+)
+@click.option(
+    "-lsb",
+    "--lower_score_is_better",
+    help="Interpretation of primary search engine score (default: True)",
+    default=True,
+)
+@click.option(
+    "--config_file",
+    help="Path to MS²Rescore config file (default: `config_default.json`)",
+    default=None,
+)
+@click.option(
+    "--spectrum_id_pattern",
+    help="Regex pattern to extract index or scan number from spectrum file. Requires at least one capturing group.",
+    default="(.*)",
+)
+@click.option(
+    "--psm_id_pattern",
+    help="Regex pattern to extract index or scan number from PSM file. Requires at least one capturing group.",
+    default="(.*)",
+)
+@click.pass_context
+def ms2rescore(
+    ctx,
+    psm_file: str,
+    spectrum_path,
+    output_path: str,
+    log_level,
+    processes,
+    fasta_file,
+    test_fdr,
+    feature_generators,
+    ms2pip_model_dir,
+    ms2pip_model,
+    ms2_tolerance,
+    calibration_set_size,
+    rescoring_engine,
+    rng,
+    id_decoy_pattern,
+    lower_score_is_better,
+    config_file: str,
+    spectrum_id_pattern: str,
+    psm_id_pattern: str
+):
+    """
+    Rescore PSMs in an idXML file and keep other information unchanged.
+    :param ms2pip_model_dir: Folder for models.
+    :param ctx: Click context object
+    :param psm_file: PSM file (idXML)
+    :param spectrum_path: Spectrum file or dictionary with spectrum files (MGF/mzML)
+    :param output_path: Output path for the new featured idXML file
+    :param log_level: log_level for the logger
+    :param processes: Number of parallel processes available to MS²Rescore
+    :param fasta_file: Fasta file for the database search
+    :param test_fdr: test FDR for the rescoring engine
+    :param feature_generators: feature generators to use
+    :param ms2pip_model: ms2pip model to use
+    :param ms2_tolerance: ms2 tolerance
+    :param calibration_set_size: calibration set size
+    :param rescoring_engine: rescoring engine to use (mokapot or percolator)
+    :param rng: random number generator seed
+    :param id_decoy_pattern: id decoy pattern
+    :param lower_score_is_better: lower score is better
+    :param config_file: config file
+    :param spectrum_id_pattern:egex pattern to extract index or scan number from spectrum file
+    :param psm_id_pattern: Regex pattern to extract index or scan number from PSM file
+    :return:
+    """
+    logging.getLogger().setLevel(log_level.upper())
+
+    if output_path is None:
+        output_path = psm_file.replace(".idXML", "_ms2rescore.idXML")
+
+    if rescoring_engine == "moakapot":
+        logging.warning(
+            "Mokapot rescoring engine is not supported in this version. Please use Percolator."
+        )
+        raise ValueError(
+            "Mokapot rescoring engine is not supported in this version. Please use Percolator."
+        )
+
+    config = parse_cli_arguments_to_config(
+        config_file=config_file,
+        output_path=output_path,
+        feature_generators=feature_generators,
+        ms2pip_model_dir=ms2pip_model_dir,
+        ms2pip_model=ms2pip_model,
+        processes=processes,
+        ms2_tolerance=ms2_tolerance,
+        calibration_set_size=calibration_set_size,
+        rescoring_engine=rescoring_engine,
+        rng=rng,
+        test_fdr=test_fdr,
+        spectrum_path=spectrum_path,
+        fasta_file=fasta_file,
+        id_decoy_pattern=id_decoy_pattern,
+        lower_score_is_better=lower_score_is_better,
+        log_level=log_level,
+        spectrum_id_pattern=spectrum_id_pattern,
+        psm_id_pattern=psm_id_pattern
+    )
+    logging.info("MS²Rescore config:")
+    logging.info(config)
+    rescore_idxml(psm_file, output_path, config)
+
+
+

quantmsrescore/rescoring.py

@@ -0,0 +1,29 @@
+import click
+
+
+from quantmsrescore import __version__
+from quantmsrescore.ms2rescore import ms2rescore
+
+CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
+
+
+@click.version_option(
+    version=__version__, package_name="quantmsrescore", message="%(package)s %(version)s"
+)
+@click.group(context_settings=CONTEXT_SETTINGS)
+def cli():
+    pass
+
+
+cli.add_command(ms2rescore)
+
+
+def main():
+    try:
+        cli()
+    except SystemExit as e:
+        if e.code != 0:
+            raise
+
+if __name__ == "__main__":
+    main()