Merge branch 'v4.0.0' of https://github.com/compomics/ms2pip_c into s…

…pectrum-output

.github/workflows/build_and_publish.yml

@@ -12,19 +12,21 @@ jobs:
       - uses: actions/checkout@v4
         with:
           lfs: "true"
+
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: "3.11"
+
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade build flake8
-      - name: Check for syntax errors
-        run: |
-          flake8 ./ms2pip --count --select=E9,F63,F7,F82 --show-source --statistics
+          python -m pip install --upgrade pip
+          pip install build
+
       - name: Build sdist
         run: python -m build --sdist --outdir dist
-      - uses: actions/upload-artifact@v3
+
+      - uses: actions/upload-artifact@v4
         with:
           name: dist
           path: dist/*.tar.gz
@@ -34,33 +36,41 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, windows-latest, macos-latest]
+        os: [ubuntu-latest, windows-latest, macos-13, macos-14]  # macos-13 for intel, macos-14 for apple silicon
     steps:
       - uses: actions/checkout@v4
         with:
           lfs: "true"
-      - uses: actions/setup-python@v4
+
+      - uses: actions/setup-python@v5
         name: Set up Python
         with:
           python-version: "3.11"
+
       - name: Install cibuildwheel
         run: python -m pip install cibuildwheel>=2
+
       - name: Build wheels
         run: python -m cibuildwheel --output-dir dist
-      - uses: actions/upload-artifact@v3
+
+      - uses: actions/upload-artifact@v4
         with:
           name: dist
           path: dist/ms2pip-*.whl
 
   publish-to-pypi:
     needs: [build-sdist, build-wheels]
     runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/ms2pip
+    permissions:
+      id-token: write
     steps:
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v4
         with:
           name: dist
           path: dist
-      - uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          user: ${{ secrets.PYPI_USERNAME }}
-          password: ${{ secrets.PYPI_PASSWORD }}
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/test.yml

@@ -5,39 +5,42 @@ on:
     branches:
       - releases
   pull_request:
+  workflow_dispatch:
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
       max-parallel: 4
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - uses: actions/checkout@v4
         with:
           lfs: "true"
+
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install flake8
-      - name: Lint with flake8
-        run: |
-          # stop the build if there are Python syntax errors or undefined names
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+          pip install ruff
+
+      - name: Check with Ruff
+        run: ruff check --output-format=github ./ms2pip
+
       - name: Build and install ms2pip
         run: |
           pip install .[test]
+
       # - name: Test with pytest
       #   run: |
       #     pytest
+
       - name: Test installation
         run: |
           ms2pip --help

docs/source/installation.rst

@@ -53,3 +53,11 @@ Clone this repository and use pip to install an editable version:
 .. code-block:: bash
 
    pip install --editable .
+
+
+Optionally, add the ``[dev,docs]`` extras to install the development and
+documentation dependencies:
+
+.. code-block:: bash
+
+   pip install --editable .[dev,docs]

docs/source/usage.rst

@@ -55,6 +55,11 @@ This mode was first developed in collaboration with the ProGenTomics group for t
 
 To train a new prediction model, see :ref:`Training new MS²PIP models`.
 
+``annotate-spectra``
+---------------------
+
+[todo]
+
 
 Input
 =====

fasta2speclib/fasta2speclib.py

@@ -23,6 +23,7 @@
 - Terminal modifications can have site specificity (e.g. N-term K or N-term P).
 
 """
+
 from __future__ import annotations
 
 __author__ = "Ralf Gabriels"
@@ -40,10 +41,10 @@
 from functools import cmp_to_key, partial
 from itertools import chain, product
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Union
+from typing import Dict, List, Optional, Union
 
 import pandas as pd
-from pydantic import BaseModel, validator
+from pydantic import BaseModel, field_validator, model_validator
 from pyteomics.fasta import FASTA, Protein, decoy_db
 from pyteomics.parser import icleave
 from rich.logging import RichHandler
@@ -56,6 +57,8 @@
 
 logger = logging.getLogger(__name__)
 
+raise NotImplementedError("This module is not yet implemented for MS²PIP v4.")
+
 
 class Peptide(BaseModel):
     """Peptide representation within the fasta2speclib search space."""
@@ -81,20 +84,18 @@ class ModificationConfig(BaseModel):
     protein_c_term: Optional[bool] = False
     fixed: Optional[bool] = False
 
-    @validator("protein_c_term", always=True)  # Validate on last target in model
-    def modification_must_have_target(cls, v, values):
+    @model_validator(mode="after")
+    def modification_must_have_target(self):
         target_fields = [
             "amino_acid",
             "peptide_n_term",
             "protein_n_term",
             "peptide_c_term",
             "protein_c_term",
         ]
-        if not any(t in values and values[t] for t in target_fields):
-            raise ValueError(
-                "Modifications must have at least one target (amino acid or N/C-term)."
-            )
-        return v
+        if not any(getattr(self, t) for t in target_fields):
+            raise ValueError("Modifications must have a target (amino acid or N/C-term).")
+        return self
 
 
 DEFAULT_MODIFICATIONS = [
@@ -137,9 +138,10 @@ class Configuration(BaseModel):
     batch_size: int = 10000
     num_cpu: Optional[int] = None
 
-    @validator("output_filetype")
+    @field_validator("output_filetype")
+    @classmethod
     def _validate_output_filetypes(cls, v):
-        allowed_types = ["msp", "mgf", "bibliospec", "spectronaut", "dlib"]# , "hdf"]
+        allowed_types = ["msp", "mgf", "bibliospec", "spectronaut", "dlib"]  # , "hdf"]
         v = [filetype.lower() for filetype in v]
         for filetype in v:
             if filetype not in allowed_types:
@@ -149,7 +151,8 @@ def _validate_output_filetypes(cls, v):
                 )
         return v
 
-    @validator("modifications")
+    @field_validator("modifications")
+    @classmethod
     def _validate_modifications(cls, v):
         if all(isinstance(m, ModificationConfig) for m in v):
             return v
@@ -160,15 +163,17 @@ def _validate_modifications(cls, v):
                 "Modifications should be a list of dicts or ModificationConfig objects."
             )
 
-    @validator("ms2pip_model")
+    @field_validator("ms2pip_model")
+    @classmethod
     def _validate_ms2pip_model(cls, v):
         if v not in MODELS.keys():
             raise ValueError(
                 f"MS²PIP model `{v}` not recognized. Should be one of " f"`{MODELS.keys()}`."
             )
         return v
 
-    @validator("num_cpu")
+    @field_validator("num_cpu")
+    @classmethod
     def _validate_num_cpu(cls, v):
         available_cpus = multiprocessing.cpu_count()
         if not v or not 0 < v < available_cpus:
@@ -210,7 +215,7 @@ def __init__(
             if isinstance(config, dict):
                 config["fasta_filename"] = fasta_filename
                 config["output_filename"] = output_filename
-                config = Configuration.parse_obj(config)
+                config = Configuration.model_validate(config)
             elif isinstance(config, Configuration):
                 config.fasta_filename = fasta_filename
                 config.output_filename = output_filename
@@ -321,7 +326,7 @@ def peptides_to_batches(peptides: List[Peptide], batch_size: int) -> List[List[P
         """Divide peptides into batches for batch-based processing."""
         return [peptides[i : i + batch_size] for i in range(0, len(peptides), batch_size)]
 
-    def process_batch(self, batch_id, batch_peptides):
+    def process_batch(self, batch_id: int, batch_peptides: List[Peptide]):
         """Predict and write library for a batch of peptides."""
         # Generate MS²PIP input
         logger.info("Generating MS²PIP input...")
@@ -382,7 +387,7 @@ def _get_rt_predictor(config: Configuration) -> RetentionTime:
             logger.debug("Initializing DeepLC predictor")
             if not config.deeplc:
                 config.deeplc = {"calibration_file": None}
-            if not "n_jobs" in config.deeplc:
+            if "n_jobs" not in config.deeplc:
                 config.deeplc["n_jobs"] = config.num_cpu
             rt_predictor = RetentionTime(config=config.dict())
         else:
@@ -397,11 +402,15 @@ def _prepare_ms2pip_params(config: Configuration) -> dict:
                 "model": config.ms2pip_model,
                 "frag_error": 0.02,
                 "ptm": [
-                    "{},{},opt,N-term".format(mod.name, mod.mass_shift)
-                    if mod.peptide_n_term or mod.protein_n_term
-                    else "{},{},opt,C-term".format(mod.name, mod.mass_shift)
-                    if mod.peptide_c_term or mod.protein_c_term
-                    else "{},{},opt,{}".format(mod.name, mod.mass_shift, mod.amino_acid)
+                    (
+                        "{},{},opt,N-term".format(mod.name, mod.mass_shift)
+                        if mod.peptide_n_term or mod.protein_n_term
+                        else (
+                            "{},{},opt,C-term".format(mod.name, mod.mass_shift)
+                            if mod.peptide_c_term or mod.protein_c_term
+                            else "{},{},opt,{}".format(mod.name, mod.mass_shift, mod.amino_acid)
+                        )
+                    )
                     for mod in config.modifications
                 ],
                 "sptm": [],