MaldiAMRKit 0.16.0__tar.gz → 0.18.0__tar.gz

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0/MaldiAMRKit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MaldiAMRKit
-Version: 0.16.0
+Version: 0.18.0
 Summary: A comprehensive toolkit for MALDI-TOF mass spectrometry data preprocessing for antimicrobial resistance (AMR) prediction purposes
 Author-email: Ettore Rocchi <ettore.rocchi3@unibo.it>
 License-Expression: MIT
@@ -41,14 +41,14 @@ Requires-Dist: sphinx>=7.0.0; extra == "docs"
 Requires-Dist: pydata-sphinx-theme>=0.15.0; extra == "docs"
 Requires-Dist: sphinx-autodoc-typehints>=2.0.0; extra == "docs"
 Requires-Dist: sphinx-design>=0.6.0; extra == "docs"
-Requires-Dist: sphinx-click>=5.0.0; extra == "docs"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "docs"
 Requires-Dist: nbsphinx>=0.9.0; extra == "docs"
 Requires-Dist: ipykernel>=6.0.0; extra == "docs"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
-Requires-Dist: sphinx-click>=5.0.0; extra == "dev"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "dev"
 Requires-Dist: hypothesis>=6.0.0; extra == "dev"
 Provides-Extra: batch
 Requires-Dist: umap-learn>=0.5; extra == "batch"

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/MaldiAMRKit.egg-info/SOURCES.txt

@@ -19,6 +19,7 @@ maldiamrkit/filters.py
 maldiamrkit/py.typed
 maldiamrkit/spectrum.py
 maldiamrkit/alignment/__init__.py
+maldiamrkit/alignment/peak_align.py
 maldiamrkit/alignment/raw_warping.py
 maldiamrkit/alignment/strategies.py
 maldiamrkit/alignment/warping.py
@@ -52,6 +53,7 @@ maldiamrkit/data/breakpoints/eucast/eucast_v8.1.yaml
 maldiamrkit/data/breakpoints/eucast/eucast_v9.0.yaml
 maldiamrkit/detection/__init__.py
 maldiamrkit/detection/peak_detector.py
+maldiamrkit/detection/peaklist.py
 maldiamrkit/differential/__init__.py
 maldiamrkit/differential/analysis.py
 maldiamrkit/differential/plots.py
@@ -63,7 +65,6 @@ maldiamrkit/drift/peak_drift.py
 maldiamrkit/drift/plots.py
 maldiamrkit/drift/reference.py
 maldiamrkit/evaluation/__init__.py
-maldiamrkit/evaluation/label_encoder.py
 maldiamrkit/evaluation/metrics.py
 maldiamrkit/evaluation/mic_regression.py
 maldiamrkit/evaluation/splitting.py
@@ -94,4 +95,5 @@ maldiamrkit/visualization/peak_plots.py
 maldiamrkit/visualization/spectrum_plots.py
 tests/test_compat.py
 tests/test_numerical_edge_cases.py
-tests/test_peak_detector.py
+tests/test_peak_detector.py
+tests/test_peaklist.py

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/MaldiAMRKit.egg-info/requires.txt

@@ -21,7 +21,7 @@ combatlearn>=1.3
 pytest>=7.0.0
 pytest-cov>=4.0.0
 ruff>=0.1.0
-sphinx-click>=5.0.0
+sphinxcontrib-typer>=0.5.0
 hypothesis>=6.0.0
 
 [docs]
@@ -29,6 +29,6 @@ sphinx>=7.0.0
 pydata-sphinx-theme>=0.15.0
 sphinx-autodoc-typehints>=2.0.0
 sphinx-design>=0.6.0
-sphinx-click>=5.0.0
+sphinxcontrib-typer>=0.5.0
 nbsphinx>=0.9.0
 ipykernel>=6.0.0

{maldiamrkit-0.16.0/MaldiAMRKit.egg-info → maldiamrkit-0.18.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MaldiAMRKit
-Version: 0.16.0
+Version: 0.18.0
 Summary: A comprehensive toolkit for MALDI-TOF mass spectrometry data preprocessing for antimicrobial resistance (AMR) prediction purposes
 Author-email: Ettore Rocchi <ettore.rocchi3@unibo.it>
 License-Expression: MIT
@@ -41,14 +41,14 @@ Requires-Dist: sphinx>=7.0.0; extra == "docs"
 Requires-Dist: pydata-sphinx-theme>=0.15.0; extra == "docs"
 Requires-Dist: sphinx-autodoc-typehints>=2.0.0; extra == "docs"
 Requires-Dist: sphinx-design>=0.6.0; extra == "docs"
-Requires-Dist: sphinx-click>=5.0.0; extra == "docs"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "docs"
 Requires-Dist: nbsphinx>=0.9.0; extra == "docs"
 Requires-Dist: ipykernel>=6.0.0; extra == "docs"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
-Requires-Dist: sphinx-click>=5.0.0; extra == "dev"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "dev"
 Requires-Dist: hypothesis>=6.0.0; extra == "dev"
 Provides-Extra: batch
 Requires-Dist: umap-learn>=0.5; extra == "batch"

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/__init__.py

@@ -5,8 +5,8 @@ Subpackage guide
 - ``maldiamrkit.data``           -- DatasetBuilder, DatasetLoader, InputLayout, DatasetLayout
 - ``maldiamrkit.filters``        -- SpeciesFilter, DrugFilter, QualityFilter, MetadataFilter
 - ``maldiamrkit.preprocessing``  -- PreprocessingPipeline, transformers, binning, quality, merging
-- ``maldiamrkit.alignment``      -- Warping, RawWarping, create_raw_input, AlignmentStrategy, AlignmentMethod
-- ``maldiamrkit.detection``      -- MaldiPeakDetector
+- ``maldiamrkit.alignment``      -- Warping, RawWarping, create_raw_input, align_peaks, AlignmentStrategy, AlignmentMethod
+- ``maldiamrkit.detection``      -- MaldiPeakDetector, PeakSet, PeakList, create_peakset_input
 - ``maldiamrkit.evaluation``     -- AMR metrics (binary + mic_regression_report), splitting (LabelEncoder moved to susceptibility)
 - ``maldiamrkit.susceptibility`` -- MICEncoder, BreakpointTable, BreakpointResult, LabelEncoder
 - ``maldiamrkit.similarity``     -- spectral_distance, pairwise_distances, clustering, plots
@@ -27,7 +27,7 @@ Examples
 from .dataset import MaldiSet
 from .spectrum import MaldiSpectrum
 
-__version__ = "0.16.0"
+__version__ = "0.18.0"
 __author__ = "Ettore Rocchi"
 
 __all__ = [

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/__init__.py

@@ -1,5 +1,6 @@
 """Spectral alignment and warping transformers."""
 
+from .peak_align import align_peaks
 from .raw_warping import RawWarping, create_raw_input
 from .strategies import AlignmentMethod, AlignmentStrategy
 from .warping import Warping
@@ -9,5 +10,6 @@ __all__ = [
     "AlignmentStrategy",
     "RawWarping",
     "Warping",
+    "align_peaks",
     "create_raw_input",
 ]

maldiamrkit-0.18.0/maldiamrkit/alignment/peak_align.py

@@ -0,0 +1,123 @@
+"""Fit-free peak-m/z alignment for peak sets.
+
+:func:`align_peaks` warps the m/z positions of a :class:`~maldiamrkit.detection.PeakSet`
+onto a reference peak list using the shared alignment strategies. It is
+**fit-free**: the reference peaks are supplied by the caller, which is expected
+to estimate them on the training split only (in the consumer's fold). The
+intensities are carried through unchanged.
+"""
+
+from __future__ import annotations
+
+import numpy as np
+
+from ..detection.peaklist import PeakSet
+from .strategies import _ALIGNMENT_REGISTRY, AlignmentMethod, AlignmentStrategy
+
+
+def _build_strategy(
+    method: AlignmentMethod,
+    max_shift_da: float,
+    n_segments: int,
+    smooth_sigma: float,
+    lowess_frac: float,
+    lowess_it: int,
+) -> AlignmentStrategy:
+    """Instantiate the requested alignment strategy with its parameters."""
+    cls = _ALIGNMENT_REGISTRY[method]
+    if method in (AlignmentMethod.shift, AlignmentMethod.linear):
+        return cls(max_shift=max_shift_da)
+    if method == AlignmentMethod.piecewise:
+        return cls(
+            n_segments=n_segments, smooth_sigma=smooth_sigma, max_shift=max_shift_da
+        )
+    if method == AlignmentMethod.quadratic:
+        return cls(max_shift=max_shift_da, degree=2)
+    if method == AlignmentMethod.cubic:
+        return cls(max_shift=max_shift_da, degree=3)
+    if method == AlignmentMethod.lowess:
+        return cls(max_shift=max_shift_da, frac=lowess_frac, it=lowess_it)
+    return cls()
+
+
+def align_peaks(
+    peaks: PeakSet,
+    ref_peaks_mz: np.ndarray,
+    *,
+    method: str | AlignmentMethod = "shift",
+    max_shift_da: float = 50.0,
+    n_segments: int = 5,
+    smooth_sigma: float = 2.0,
+    lowess_frac: float = 0.3,
+    lowess_it: int = 3,
+) -> PeakSet:
+    """Align a peak set's m/z positions to a reference peak list.
+
+    Fit-free: ``ref_peaks_mz`` is supplied by the caller. Builds the requested
+    warping transform from the matched (sample, reference) peak pairs and applies
+    it to the peak m/z; intensities are unchanged.
+
+    Parameters
+    ----------
+    peaks : PeakSet
+        Peak set to align.
+    ref_peaks_mz : array-like
+        Reference peak m/z positions to align to.
+    method : {"shift", "linear", "piecewise", "quadratic", "cubic", "lowess"}, default="shift"
+        Warping strategy. ``"dtw"`` is unsupported for peak sets because it
+        resamples onto a dense grid and would destroy the set structure.
+    max_shift_da : float, default=50.0
+        Maximum allowed shift in Daltons (used by the shift fallback and the
+        rigid/linear strategies).
+    n_segments : int, default=5
+        Number of segments for ``method="piecewise"``.
+    smooth_sigma : float, default=2.0
+        Gaussian smoothing (Da) for piecewise transitions.
+    lowess_frac : float, default=0.3
+        LOWESS bandwidth for ``method="lowess"``.
+    lowess_it : int, default=3
+        LOWESS robustness iterations for ``method="lowess"``.
+
+    Returns
+    -------
+    PeakSet
+        A new peak set with warped m/z and unchanged intensities.
+
+    Raises
+    ------
+    ValueError
+        If ``method="dtw"``.
+
+    Notes
+    -----
+    ``"shift"``, ``"linear"``, ``"quadratic"``, ``"cubic"`` and ``"lowess"``
+    operate directly on the matched peak m/z and are the well-behaved choices
+    for sparse peak sets. ``"piecewise"`` derives its Gaussian smoothing width
+    from the median spacing of the input points; on a sparse peak set that
+    spacing is large, so the smoothing is effectively inactive and the warp
+    reduces to an unsmoothed piecewise-linear transform.
+    """
+    method = AlignmentMethod(method)
+    if method == AlignmentMethod.dtw:
+        raise ValueError(
+            "method='dtw' is not supported for peak sets (it resamples onto a "
+            "dense grid). Use 'shift', 'linear', 'piecewise', 'quadratic', "
+            "'cubic', or 'lowess'."
+        )
+
+    ref_peaks_mz = np.asarray(ref_peaks_mz, dtype=float).ravel()
+    if peaks.n_peaks == 0 or ref_peaks_mz.size == 0:
+        return PeakSet(peaks.mz.copy(), peaks.intensity.copy())
+
+    strategy = _build_strategy(
+        method, max_shift_da, n_segments, smooth_sigma, lowess_frac, lowess_it
+    )
+    new_mz, _ = strategy.align_raw(
+        peaks.mz,
+        peaks.intensity,
+        peaks.mz,
+        ref_peaks_mz,
+        ref_peaks_mz,
+        np.ones_like(ref_peaks_mz),
+    )
+    return PeakSet(np.asarray(new_mz, dtype=float), peaks.intensity.copy())

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/raw_warping.py

@@ -16,7 +16,7 @@ from ..io.readers import read_spectrum
 from ..preprocessing.binning import BinningMethod, bin_spectrum
 from ..preprocessing.pipeline import preprocess
 from ..preprocessing.preprocessing_pipeline import PreprocessingPipeline
-from .strategies import ALIGNMENT_REGISTRY, AlignmentMethod
+from .strategies import _ALIGNMENT_REGISTRY, AlignmentMethod
 
 
 def create_raw_input(
@@ -393,7 +393,7 @@ class RawWarping(BaseEstimator, TransformerMixin):
 
     def _get_strategy(self):
         """Build strategy instance from current parameters."""
-        cls = ALIGNMENT_REGISTRY[self.method]
+        cls = _ALIGNMENT_REGISTRY[self.method]
         if self.method == "shift":
             return cls(max_shift=self.max_shift_da)
         elif self.method == "linear":

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/strategies.py

@@ -689,7 +689,7 @@ class LOWESSStrategy(AlignmentStrategy):
         return new_mz, intensity
 
 
-ALIGNMENT_REGISTRY: dict[str, type[AlignmentStrategy]] = {
+_ALIGNMENT_REGISTRY: dict[str, type[AlignmentStrategy]] = {
     "shift": ShiftStrategy,
     "linear": LinearStrategy,
     "piecewise": PiecewiseStrategy,

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/warping.py

@@ -10,7 +10,7 @@ from joblib import Parallel, delayed
 from sklearn.base import BaseEstimator, TransformerMixin
 
 from ..detection.peak_detector import MaldiPeakDetector
-from .strategies import ALIGNMENT_REGISTRY, AlignmentMethod, DTWStrategy
+from .strategies import _ALIGNMENT_REGISTRY, AlignmentMethod, DTWStrategy
 
 
 class Warping(BaseEstimator, TransformerMixin):
@@ -177,7 +177,7 @@ class Warping(BaseEstimator, TransformerMixin):
 
     def _get_strategy(self):
         """Build strategy instance from current parameters."""
-        cls = ALIGNMENT_REGISTRY[self.method]
+        cls = _ALIGNMENT_REGISTRY[self.method]
         if self.method == "shift":
             return cls(max_shift=self.max_shift)
         elif self.method == "linear":

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/cli.py

@@ -420,7 +420,5 @@ def build(
         )
 
 
-typer_click_object = typer.main.get_command(app)
-
 if __name__ == "__main__":
     app()

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/data/__init__.py

@@ -22,8 +22,6 @@ from .duplicates import DuplicateStrategy
 from .input_layouts import BrukerTreeLayout, FlatLayout, InputLayout
 from .loader import DatasetLoader
 from .site_info import (
-    CURRENT_FORMAT_VERSION,
-    MANIFEST_FILENAME,
     BuildInfo,
     SiteInfo,
     read_site_info,
@@ -53,6 +51,4 @@ __all__ = [
     "BuildInfo",
     "read_site_info",
     "write_site_info",
-    "MANIFEST_FILENAME",
-    "CURRENT_FORMAT_VERSION",
 ]

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/data/dataset_layouts.py

@@ -30,7 +30,7 @@ logger = logging.getLogger(__name__)
 class _Sentinel:
     """Sentinel for ``DRIAMSLayout`` kwargs.
 
-    A kwarg defaulted to :data:`_AUTO` means: "fill from ``site_info.json``
+    A kwarg defaulted to ``_AUTO`` means: "fill from ``site_info.json``
     if present, otherwise use the library default".  Explicit kwargs
     always win.
     """
@@ -255,7 +255,7 @@ class DRIAMSLayout(DatasetLayout):
     ) -> None:
         """Initialise the layout.
 
-        Several kwargs accept the sentinel :data:`_AUTO` as their default.
+        Several kwargs accept the sentinel ``_AUTO`` as their default.
         When ``_AUTO``, the value is filled from ``site_info.json`` at the
         dataset root (if present) and otherwise falls back to the
         library-level default.  Explicit kwargs always win.  Fields with

{maldiamrkit-0.16.0 → maldiamrkit-0.18.0}/maldiamrkit/data/site_info.py

@@ -45,10 +45,10 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any
 
-MANIFEST_FILENAME = "site_info.json"
+_MANIFEST_FILENAME = "site_info.json"
 """On-disk filename for the manifest, written at the dataset root."""
 
-CURRENT_FORMAT_VERSION = 1
+_CURRENT_FORMAT_VERSION = 1
 """Manifest schema version produced by *this* MaldiAMRKit release."""
 
 _REQUIRED_V1_KEYS: tuple[str, ...] = (
@@ -65,7 +65,7 @@ _REQUIRED_V1_KEYS: tuple[str, ...] = (
 
 @dataclass
 class BuildInfo:
-    """Optional provenance block nested under :attr:`SiteInfo.build_info`.
+    """Optional provenance block nested under :attr:`~maldiamrkit.data.SiteInfo.build_info`.
 
     Informational only; readers may inspect it but are not required to
     interpret any field.  All fields are optional.
@@ -102,8 +102,9 @@ class SiteInfo:
         Bin width in Daltons used at build time.
     build_info : BuildInfo, optional
         Optional provenance block.
-    format_version : int, default=:data:`CURRENT_FORMAT_VERSION`
-        Manifest schema version.
+    format_version : int, optional
+        Manifest schema version; defaults to the current release's schema
+        version.
     """
 
     id_column: str
@@ -114,7 +115,7 @@ class SiteInfo:
     mz_range: tuple[float, float]
     bin_width: float
     build_info: BuildInfo | None = None
-    format_version: int = CURRENT_FORMAT_VERSION
+    format_version: int = _CURRENT_FORMAT_VERSION
 
     def to_dict(self) -> dict[str, Any]:
         """Serialise as a plain dict, with ``format_version`` first."""
@@ -134,7 +135,7 @@ class SiteInfo:
 
 
 def write_site_info(dataset_dir: str | Path, site_info: SiteInfo) -> Path:
-    """Write a :class:`SiteInfo` to ``<dataset_dir>/site_info.json``.
+    """Write a :class:`~maldiamrkit.data.SiteInfo` to ``<dataset_dir>/site_info.json``.
 
     Parameters
     ----------
@@ -153,7 +154,7 @@ def write_site_info(dataset_dir: str | Path, site_info: SiteInfo) -> Path:
         raise FileNotFoundError(
             f"Cannot write manifest: dataset directory does not exist: {dataset_dir}"
         )
-    path = dataset_dir / MANIFEST_FILENAME
+    path = dataset_dir / _MANIFEST_FILENAME
     data = site_info.to_dict()
     path.write_text(json.dumps(data, indent=2, sort_keys=False) + "\n")
     return path
@@ -187,11 +188,11 @@ def read_site_info(
         If the manifest is malformed, missing a required field, or has
         a non-integer ``format_version``.
     """
-    path = Path(dataset_dir) / MANIFEST_FILENAME
+    path = Path(dataset_dir) / _MANIFEST_FILENAME
     if not path.exists():
         if missing_ok:
             return None
-        raise FileNotFoundError(f"{MANIFEST_FILENAME} not found in {dataset_dir}")
+        raise FileNotFoundError(f"{_MANIFEST_FILENAME} not found in {dataset_dir}")
 
     try:
         raw = json.loads(path.read_text())
@@ -218,10 +219,10 @@ def _site_info_from_dict(
     if not isinstance(fv, int):
         raise ValueError(f"site_info{where} has non-integer format_version={fv!r}.")
 
-    if fv > CURRENT_FORMAT_VERSION:
+    if fv > _CURRENT_FORMAT_VERSION:
         warnings.warn(
             f"site_info{where} was written by a newer MaldiAMRKit "
-            f"(format_version={fv}; this reader knows v{CURRENT_FORMAT_VERSION}). "
+            f"(format_version={fv}; this reader knows v{_CURRENT_FORMAT_VERSION}). "
             "Reading what I can; unknown fields will be ignored. "
             "Upgrade `maldiamrkit` if loading misbehaves.",
             UserWarning,
@@ -282,8 +283,6 @@ def _current_iso_utc() -> str:
 
 
 __all__ = [
-    "MANIFEST_FILENAME",
-    "CURRENT_FORMAT_VERSION",
     "SiteInfo",
     "BuildInfo",
     "read_site_info",

maldiamrkit-0.18.0/maldiamrkit/detection/__init__.py

@@ -0,0 +1,12 @@
+"""Peak detection algorithms and transformers."""
+
+from .peak_detector import MaldiPeakDetector, PeakMethod
+from .peaklist import PeakList, PeakSet, create_peakset_input
+
+__all__ = [
+    "MaldiPeakDetector",
+    "PeakMethod",
+    "PeakList",
+    "PeakSet",
+    "create_peakset_input",
+]