Replace C/Cython with ms2rescore-rs

.github/workflows/build_and_publish.yml

@@ -5,49 +5,20 @@ on:
     types: [created]
 
 jobs:
-  build-sdist:
-    name: Build source distribution
+  build:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-        with:
-          lfs: "true"
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install build
-      - name: Build sdist
-        run: python -m build --sdist --outdir dist
-      - uses: actions/upload-artifact@v4
-        with:
-          name: dist-source
-          path: dist
-
-  build-wheels:
-    name: Build wheels on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, windows-latest, macos-15, macos-15-intel]
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          lfs: "true"
-      - name: Build wheels
-        uses: pypa/cibuildwheel@v3.4.0
-        with:
-          output-dir: dist
+      - uses: astral-sh/setup-uv@v6
+      - name: Build sdist and wheel
+        run: uv build --out-dir dist
       - uses: actions/upload-artifact@v4
         with:
-          name: dist-${{ matrix.os }}
+          name: dist
           path: dist
 
   publish-to-pypi:
-    needs: [build-sdist, build-wheels]
+    needs: [build]
     runs-on: ubuntu-latest
     environment:
       name: pypi
@@ -56,10 +27,8 @@ jobs:
       id-token: write
     steps:
       - uses: actions/download-artifact@v4
-      - name: Move wheels to dist
-        run: |
-          mkdir dist/
-          mv dist-*/*.whl dist/
-          mv dist-*/*.tar.gz dist/
+        with:
+          name: dist
+          path: dist
       - name: Publish to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/test.yml

@@ -8,40 +8,36 @@ on:
   workflow_dispatch:
 
 jobs:
-  build:
+  lint:
     runs-on: ubuntu-latest
-    strategy:
-      max-parallel: 4
-      fail-fast: false
-      matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
+      - run: uvx ruff check --output-format=github ./ms2pip
 
+  typecheck:
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
         with:
-          lfs: "true"
+          enable-cache: true
+      - run: uv run --all-extras --group dev --python 3.13 ty check ms2pip/
 
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
         with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Install dependencies
+          enable-cache: true
+      - name: Install and test
         run: |
-          python -m pip install --upgrade pip
-          pip install ruff
-
-      - name: Check with Ruff
-        run: ruff check --output-format=github ./ms2pip
-
-      - name: Build and install ms2pip
-        run: |
-          pip install .[dev]
-
-      - name: Test with pytest
-        run: |
-          pytest
-
-      - name: Test installation
+          uv run --python ${{ matrix.python-version }} pytest
+      - name: Test CLI
         run: |
-          ms2pip --help
+          uv run --python ${{ matrix.python-version }} ms2pip --help

.gitignore

@@ -1,10 +1,5 @@
-.pytest_cache/
-
-# Custom MS2PIP stuff
+# Custom
 data/
-*_pyx.c
-*_pyx_*.c
-ms2pip/models_xgboost/*.xgboost
 
 # Pytest
 .pytest_cache/
@@ -98,6 +93,7 @@ celerybeat-schedule
 .venv/
 venv/
 ENV/
+.venv-*/
 
 # Spyder project settings
 .spyderproject

README.rst

@@ -36,7 +36,8 @@ peptide fragmentation spectrum that accurately resembles its observed equivalent
 can be used to validate peptide identifications, generate proteome-wide spectral libraries, or to
 select discriminative transitions for targeted proteomics. MS²PIP employs the
 `XGBoost <https://xgboost.readthedocs.io/en/stable/>`_ machine learning algorithm and is written in
-Python and C.
+Python, with helper functions in Rust
+(`ms2rescore-rs <https://github.com/compomics/ms2rescore-rs>`_).
 
 .. figure:: https://raw.githubusercontent.com/compomics/ms2pip/v4.0.0/img/mirror-DVAQIFNNILR-2.png
 

docs/source/api/ms2pip.result.rst

@@ -3,3 +3,4 @@ ms2pip.result
 *************
 
 .. automodule:: ms2pip.result
+   :members:

docs/source/api/ms2pip.spectrum.rst

@@ -3,3 +3,4 @@ ms2pip.spectrum
 ***************
 
 .. automodule:: ms2pip.spectrum
+   :members:

docs/source/installation.rst

@@ -6,17 +6,12 @@ Pip package
 .. image:: https://flat.badgen.net/badge/install%20with/pip/green
    :target: https://pypi.org/project/ms2pip/
 
-With Python 3.9 or higher, run:
+With Python 3.11 or higher, run:
 
 .. code-block:: bash
 
    pip install ms2pip
 
-Compiled wheels are available for various Python versions on 64bit Linux,
-Windows, and macOS. This should install MS²PIP in a few seconds. For other
-platforms, MS²PIP can be built from source, although it can take a while
-to compile the large prediction models.
-
 We recommend using a `venv <https://docs.python.org/3/library/venv.html>`__ or
 `conda <https://docs.conda.io/en/latest/>`__ virtual environment.
 

ms2pip/__init__.py

@@ -1,13 +1,14 @@
 # isort: skip_file
 """MS2PIP: Accurate and versatile peptide fragmentation spectrum prediction."""
 
-__version__ = "4.2.0-alpha.2"
+__version__ = "4.2.0-alpha.3"
 __all__ = [
     "predict_single",
     "predict_batch",
     "predict_library",
     "correlate",
     "correlate_preloaded",
+    "correlate_single",
     "get_training_data",
     "annotate_spectra",
     "download_models",
@@ -26,6 +27,7 @@
     predict_library,
     correlate,
     correlate_preloaded,
+    correlate_single,
     get_training_data,
     annotate_spectra,
     download_models,

ms2pip/__main__.py

@@ -1,7 +1,6 @@
 import logging
 import sys
 from pathlib import Path
-from typing import Optional
 
 import click
 import rich
@@ -32,7 +31,7 @@
 
 def _infer_output_name(
     input_filename: str,
-    output_name: Optional[str] = None,
+    output_name: str | None = None,
 ) -> Path:
     """Infer output filename from input filename if output_filename was not defined."""
     if output_name:
@@ -50,9 +49,7 @@ def cli(*args, **kwargs):
         format="%(message)s",
         datefmt="%Y-%m-%d %H:%M:%S",
         level=LOGGING_LEVELS[kwargs["logging_level"]],
-        handlers=[
-            RichHandler(rich_tracebacks=True, show_level=True, show_path=False)
-        ],
+        handlers=[RichHandler(rich_tracebacks=True, show_level=True, show_path=False)],
     )
     rich.print(build_credits())
 
@@ -79,7 +76,7 @@ def predict_single(*args, **kwargs):
     # Write output
     rich.print(build_prediction_table(predicted_spectrum))
     write_spectra(output_name, [result], output_format)
-    if plot:
+    if plot and predicted_spectrum:
         spectrum_to_png(predicted_spectrum, output_name)
 
 
@@ -142,6 +139,9 @@ def predict_library(*args, **kwargs):
 @click.option("--model", type=click.Choice(MODELS), default="HCD")
 @click.option("--model-dir")
 @click.option("--ms2-tolerance", type=float, default=0.02)
+@click.option(
+    "--ms2-tolerance-mode", type=click.Choice(["Da", "ppm"], case_sensitive=False), default="Da"
+)
 @click.option("--processes", "-n", type=int)
 def correlate(*args, **kwargs):
     # Parse arguments
@@ -171,6 +171,9 @@ def correlate(*args, **kwargs):
 @click.option("--spectrum-id-pattern", "-p")
 @click.option("--model", type=click.Choice(MODELS), default="HCD")
 @click.option("--ms2-tolerance", type=float, default=0.02)
+@click.option(
+    "--ms2-tolerance-mode", type=click.Choice(["Da", "ppm"], case_sensitive=False), default="Da"
+)
 @click.option("--processes", "-n", type=int)
 def get_training_data(*args, **kwargs):
     # Parse arguments
@@ -193,6 +196,9 @@ def get_training_data(*args, **kwargs):
 @click.option("--spectrum-id-pattern", "-p")
 @click.option("--model", type=click.Choice(MODELS), default="HCD")
 @click.option("--ms2-tolerance", type=float, default=0.02)
+@click.option(
+    "--ms2-tolerance-mode", type=click.Choice(["Da", "ppm"], case_sensitive=False), default="Da"
+)
 @click.option("--processes", "-n", type=int)
 def annotate_spectra(*args, **kwargs):
     # Parse arguments
@@ -203,8 +209,8 @@ def annotate_spectra(*args, **kwargs):
     results = ms2pip.core.annotate_spectra(*args, **kwargs)
 
     # Write intensities
-    output_name_int = output_name.with_name(output_name.stem + "_observations").with_suffix()
-    logger.info(f"Writing intensities to {output_name_int.with_suffix('.tsv')}")
+    output_name = output_name.with_name(output_name.stem + "_observations")
+    logger.info(f"Writing intensities to {output_name.with_suffix('.tsv')}")
     write_spectra(output_name, results, "tsv")