Merge branch 'timsRescore' of https://github.com/compomics/ms2rescore …

…into peptide-num-fix

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.10
+FROM python:3.11
 
 # ARG DEBIAN_FRONTEND=noninteractive
 
@@ -13,7 +13,7 @@ ADD MANIFEST.in /ms2rescore/MANIFEST.in
 ADD ms2rescore /ms2rescore/ms2rescore
 
 RUN apt-get update \
-    && apt install -y procps git-lfs \
+    && apt install -y procps \
     && pip install /ms2rescore
 
 ENTRYPOINT [""]

ms2rescore/__init__.py

@@ -1,6 +1,6 @@
 """MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and RTs."""
 
-__version__ = "3.0.3"
+__version__ = "3.1.0-dev1"
 
 from warnings import filterwarnings
 

ms2rescore/__main__.py

@@ -1,6 +1,8 @@
 """MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and RTs."""
 
 import argparse
+import importlib.resources
+import json
 import logging
 import sys
 from pathlib import Path
@@ -10,7 +12,7 @@
 from rich.logging import RichHandler
 from rich.text import Text
 
-from ms2rescore import __version__
+from ms2rescore import __version__, package_data
 from ms2rescore.config_parser import parse_configurations
 from ms2rescore.core import rescore
 from ms2rescore.exceptions import MS2RescoreConfigurationError
@@ -33,19 +35,26 @@
 CONSOLE = Console(record=True)
 
 
-def _print_credits():
+def _print_credits(tims=False):
     """Print software credits to terminal."""
     text = Text()
     text.append("\n")
-    text.append("MS²Rescore", style="bold link https://github.com/compomics/ms2rescore")
+    if tims:
+        text.append("TIMS²Rescore", style="bold link https://github.com/compomics/ms2rescore")
+    else:
+        text.append("MS²Rescore", style="bold link https://github.com/compomics/ms2rescore")
     text.append(f" (v{__version__})\n", style="bold")
+    if tims:
+        text.append("MS²Rescore tuned for Bruker timsTOF instruments.\n", style="italic")
     text.append("Developed at CompOmics, VIB / Ghent University, Belgium.\n")
     text.append("Please cite: ")
     text.append(
-        "Declercq et al. MCP (2022)", style="link https://doi.org/10.1016/j.mcpro.2022.100266"
+        "Buur & Declercq et al. JPR (2024)",
+        style="link https://doi.org/10.1021/acs.jproteome.3c00785",
     )
     text.append("\n")
-    text.stylize("cyan")
+    if tims:
+        text.stylize("#006cb5")
     CONSOLE.print(text)
 
 
@@ -152,18 +161,30 @@ def _setup_logging(passed_level: str, log_file: Union[str, Path]):
     )
 
 
-def main():
+def main_tims():
+    """Run MS²Rescore command-line interface in TIMS²Rescore mode."""
+    main(tims=True)
+
+
+def main(tims=False):
     """Run MS²Rescore command-line interface."""
-    _print_credits()
+    _print_credits(tims)
 
     # Parse CLI arguments and configuration file
     parser = _argument_parser()
     cli_args = parser.parse_args()
+
+    configurations = []
+    if cli_args.config_file:
+        configurations.append(cli_args.config_file)
+    if tims:
+        configurations.append(
+            json.load(importlib.resources.open_text(package_data, "config_default_tims.json"))
+        )
+    configurations.append(cli_args)
+
     try:
-        if cli_args.config_file:
-            config = parse_configurations([cli_args.config_file, cli_args])
-        else:
-            config = parse_configurations(cli_args)
+        config = parse_configurations(configurations)
     except MS2RescoreConfigurationError as e:
         LOGGER.critical(e)
         sys.exit(1)

ms2rescore/core.py

@@ -3,15 +3,16 @@
 from multiprocessing import cpu_count
 from typing import Dict, Optional
 
+import numpy as np
 import psm_utils.io
 from psm_utils import PSMList
 
+from ms2rescore import exceptions
 from ms2rescore.feature_generators import FEATURE_GENERATORS
 from ms2rescore.parse_psms import parse_psms
 from ms2rescore.parse_spectra import get_missing_values
 from ms2rescore.report import generate
 from ms2rescore.rescoring_engines import mokapot, percolator
-from ms2rescore import exceptions
 
 logger = logging.getLogger(__name__)
 
@@ -58,18 +59,8 @@ def rescore(configuration: Dict, psm_list: Optional[PSMList] = None) -> None:
         f"PSMs already contain the following rescoring features: {psm_list_feature_names}"
     )
 
-    # TODO: avoid hard coding feature generators in some way
-    rt_required = ("deeplc" in config["feature_generators"]) and (
-        None in psm_list["retention_time"]
-    )
-    im_required = (
-        "ionmob" in config["feature_generators"] or "im2deep" in config["feature_generators"]
-    ) and (None in psm_list["ion_mobility"])
-    logger.debug(f"RT required: {rt_required}, IM required: {im_required}")
-
-    if rt_required or im_required:
-        logger.info("Parsing missing retention time and/or ion mobility values from spectra...")
-        get_missing_values(psm_list, config, rt_required=rt_required, im_required=im_required)
+    # Add missing precursor info from spectrum file if needed
+    _fill_missing_precursor_info(psm_list, config)
 
     # Add rescoring features
     for fgen_name, fgen_config in config["feature_generators"].items():
@@ -166,6 +157,49 @@ def rescore(configuration: Dict, psm_list: Optional[PSMList] = None) -> None:
             logger.exception(e)
 
 
+def _fill_missing_precursor_info(psm_list, config):
+    """Fill missing precursor info from spectrum file if needed."""
+    # Check if required
+    # TODO: avoid hard coding feature generators in some way
+    rt_required = ("deeplc" in config["feature_generators"]) and any(
+        v is None or v == 0 or np.isnan(v) for v in psm_list["retention_time"]
+    )
+    im_required = (
+        "ionmob" in config["feature_generators"] or "im2deep" in config["feature_generators"]
+    ) and any(v is None or v == 0 or np.isnan(v) for v in psm_list["ion_mobility"])
+    logger.debug(f"RT required: {rt_required}, IM required: {im_required}")
+
+    # Add missing values
+    if rt_required or im_required:
+        logger.info("Parsing missing retention time and/or ion mobility values from spectra...")
+        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 (
+            0.0 in psm_list[value_name]
+            or None in psm_list[value_name]
+            or np.isnan(psm_list[value_name]).any()
+        ):
+            if all(v is None or v == 0.0 or np.isnan(v) for v in psm_list[value_name]):
+                raise exceptions.MissingValuesError(
+                    f"Could not find any '{value_name}' values in PSM or spectrum files. Disable "
+                    f"feature generators that require '{value_name}' or ensure that the values are "
+                    "present in the input files."
+                )
+            else:
+                missing_value_psms = psm_list[
+                    [v is None or np.isnan(v) for v in psm_list[value_name]]
+                ]
+                logger.warning(
+                    f"Found {len(missing_value_psms)} PSMs with missing '{value_name}' values. "
+                    "These PSMs will be removed."
+                )
+                psm_list = psm_list[
+                    [v is not None and not np.isnan(v) for v in psm_list[value_name]]
+                ]
+
+
 def _write_feature_names(feature_names, output_file_root):
     """Write feature names to file."""
     with open(output_file_root + ".feature_names.tsv", "w") as f:

ms2rescore/exceptions.py

@@ -25,6 +25,12 @@ class ModificationParsingError(IDFileParsingError):
     pass
 
 
+class MissingValuesError(MS2RescoreError):
+    """Missing values in PSMs and/or spectra."""
+
+    pass
+
+
 class ReportGenerationError(MS2RescoreError):
     """Error while generating report."""
 

ms2rescore/package_data/config_default_tims.json

@@ -0,0 +1,25 @@
+{
+    "$schema": "./config_schema.json",
+    "ms2rescore": {
+        "feature_generators": {
+            "basic": {},
+            "ms2pip": {
+                "model": "timsTOF",
+                "ms2_tolerance": 0.02
+            },
+            "deeplc": {
+                "deeplc_retrain": false
+            },
+            "im2deep": {},
+            "maxquant": {}
+        },
+        "rescoring_engine": {
+            "mokapot": {
+                "write_weights": true,
+                "write_txt": true,
+                "write_flashlfq": true
+            }
+        },
+        "psm_file": null
+    }
+}

ms2rescore/parse_spectra.py

@@ -6,7 +6,6 @@
 
 from ms2rescore_rs import get_precursor_info
 from psm_utils import PSMList
-from rich.progress import track
 
 from ms2rescore.exceptions import MS2RescoreError
 from ms2rescore.utils import infer_spectrum_path

ms2rescore/utils.py

@@ -35,46 +35,61 @@ def infer_spectrum_path(
                 "and no run name in PSM file found."
             )
 
-    # If passed path is directory, join with run name
-    elif os.path.isdir(configured_path) and not configured_path.endswith(".d"):
-        if run_name:
-            resolved_path = os.path.join(configured_path, run_name)
+    else:
+        is_bruker_dir = configured_path.endswith(".d") or _is_minitdf(configured_path)
+
+        # If passed path is directory (that is not Bruker raw), join with run name
+        if os.path.isdir(configured_path) and not is_bruker_dir:
+            if run_name:
+                resolved_path = os.path.join(configured_path, run_name)
+            else:
+                raise MS2RescoreConfigurationError(
+                    "Could not resolve spectrum file name: Spectrum path is directory "
+                    "but no run name in PSM file found."
+                )
+
+        # If passed path is file, use that, but warn if basename doesn't match expected
+        elif os.path.isfile(configured_path) or (os.path.isdir(configured_path) and is_bruker_dir):
+            if run_name and Path(configured_path).stem != Path(run_name).stem:
+                logger.warning(
+                    "Passed spectrum path (`%s`) does not match run name found in PSM "
+                    "file (`%s`). Continuing with passed spectrum path.",
+                    configured_path,
+                    run_name,
+                )
+            resolved_path = configured_path
         else:
             raise MS2RescoreConfigurationError(
-                "Could not resolve spectrum file name: Spectrum path is directory "
-                "but no run name in PSM file found."
-            )
-
-    # If passed path is file, use that, but warn if basename doesn't match expected
-    elif os.path.isfile(configured_path) or (
-        os.path.isdir(configured_path) and configured_path.endswith(".d")
-    ):
-        if run_name and Path(configured_path).stem != Path(run_name).stem:
-            logger.warning(
-                "Passed spectrum path (`%s`) does not match run name found in PSM "
-                "file (`%s`). Continuing with passed spectrum path.",
-                configured_path,
-                run_name,
+                "Configured `spectrum_path` must be `None` or a path to an existing file "
+                "or directory. If `None` or path to directory, spectrum run information "
+                "should be present in the PSM file."
             )
-        resolved_path = configured_path
-    else:
-        raise MS2RescoreConfigurationError(
-            "Configured `spectrum_path` must be `None` or a path to an existing file "
-            "or directory. If `None` or path to directory, spectrum run information "
-            "should be present in the PSM file."
-        )
 
     # Match with file extension if not in resolved_path yet
-    if not re.match(r"\.mgf$|\.mzml$|\.d$", resolved_path, flags=re.IGNORECASE):
+    if not _is_minitdf(resolved_path) and not re.match(
+        r"\.mgf$|\.mzml$|\.d$", resolved_path, flags=re.IGNORECASE
+    ):
         for filename in glob(resolved_path + "*"):
             if re.match(r".*(\.mgf$|\.mzml$|\.d)", filename, flags=re.IGNORECASE):
                 resolved_path = filename
                 break
         else:
             raise MS2RescoreConfigurationError(
-                "Resolved spectrum filename does not contain a supported file "
-                "extension (mzML, MGF, or .d) and could not find any matching existing "
+                f"Resolved spectrum filename ('{resolved_path}') does not contain a supported "
+                "file extension (mzML, MGF, or .d) and could not find any matching existing "
                 "files."
             )
 
     return Path(resolved_path)
+
+
+def _is_minitdf(spectrum_file: str) -> bool:
+    """
+    Check if the spectrum file is a Bruker miniTDF folder.
+
+    A Bruker miniTDF folder has no fixed name, but contains files matching the patterns
+    ``*ms2spectrum.bin`` and ``*ms2spectrum.parquet``.
+    """
+    files = set(Path(spectrum_file).glob("*ms2spectrum.bin"))
+    files.update(Path(spectrum_file).glob("*ms2spectrum.parquet"))
+    return len(files) >= 2

pyproject.toml

@@ -32,26 +32,26 @@ classifiers = [
 dynamic = ["version"]
 requires-python = ">=3.8"
 dependencies = [
-    "ms2rescore_rs",
-    "numpy>=1.16.0; python_version != '3.11'",
-    "numpy==1.24.3; python_version == '3.11'", # Incompatibility with sklearn, pygam, and TF...
-    "pandas>=1.0",
-    "rich>=12",
-    "pyteomics>=4.1.0, <4.7",
-    "lxml>=4.5",
-    "ms2pip>=4.0.0-dev5",
-    "click>=7",
     "cascade-config>=0.4.0",
+    "click>=7",
+    "customtkinter>=5,<6",
     "deeplc>=2.2",
     "deeplcretrainer>=0.2",
-    "tomli>=2; python_version < '3.11'",
-    "psm_utils>=0.4",
-    "customtkinter>=5,<6",
-    "mokapot>=0.9",
-    "pydantic>=1.8.2,<2",                      # Fix compatibility with v2 in psm_utils
+    "im2deep>=0.1.3",
     "jinja2>=3",
+    "lxml>=4.5",
+    "mokapot>=0.9",
+    "ms2pip>=4.0.0-dev10",
+    "ms2rescore_rs",
+    "numpy==1.24.3; python_version == '3.11'", # Incompatibility with sklearn, pygam, and TF...
+    "numpy>=1.16.0; python_version != '3.11'",
+    "pandas>=1.0",
     "plotly>=5",
-    "im2deep>=0.1.3",
+    "psm_utils>=0.8",
+    "pydantic>=1.8.2,<2",                      # Fix compatibility with v2 in psm_utils
+    "pyteomics>=4.1.0, <4.7",
+    "rich>=12",
+    "tomli>=2; python_version < '3.11'",
 ]
 
 [project.optional-dependencies]
@@ -80,6 +80,7 @@ CompOmics = "https://www.compomics.com"
 ms2rescore = "ms2rescore.__main__:main"
 ms2rescore-gui = "ms2rescore.gui.__main__:main"
 ms2rescore-report = "ms2rescore.report.__main__:main"
+tims2rescore = "ms2rescore.__main__:main_tims"
 
 [build-system]
 requires = ["flit_core >=3.2,<4"]