dasmixer-core 0.6.0a2__tar.gz

dasmixer_core-0.6.0a2/PKG-INFO

@@ -0,0 +1,83 @@
+Metadata-Version: 2.4
+Name: dasmixer-core
+Version: 0.6.0a2
+Summary: DASMixer core library — project API, calculations, and data import
+Author: gluck
+Author-email: glucksistemi@gmail.com
+Requires-Python: <4.0, >=3.11
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Provides-Extra: all
+Provides-Extra: plotly
+Provides-Extra: proteins
+Requires-Dist: aiocsv (>=1.4.0,<2.0.0)
+Requires-Dist: aiofiles (>=25.1.0,<26.0.0)
+Requires-Dist: aiosqlite (>=0.22.1,<0.23.0)
+Requires-Dist: dasmixer-core[plotly,proteins] ; extra == "all"
+Requires-Dist: docxtpl (>=0.20.2,<0.21.0)
+Requires-Dist: html-for-docx (>=1.1.3,<2.0.0)
+Requires-Dist: jinja2 (>=3.1.6,<4.0.0)
+Requires-Dist: kaleido (>=1.2.0,<2.0.0) ; extra == "plotly"
+Requires-Dist: mztabwriter[pandas] (>=0.1.0,<0.2.0)
+Requires-Dist: npysearch (>=1.3.1,<2.0.0) ; (sys_platform != "win32") and (extra == "proteins")
+Requires-Dist: npysearch-win (>=1.3.1,<2.0.0) ; (sys_platform == "win32") and (extra == "proteins")
+Requires-Dist: numpy (>=2.4.1,<3.0.0)
+Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
+Requires-Dist: pandas (>=2.3.3,<3.0.0)
+Requires-Dist: parse (>=1.20.2,<2.0.0)
+Requires-Dist: peptacular (>=2.5.1,<3.0.0)
+Requires-Dist: plotly (>=6.5.2,<7.0.0) ; extra == "plotly"
+Requires-Dist: pydantic (>=2.12.5,<3.0.0)
+Requires-Dist: pydantic-settings (>=2.12.0,<3.0.0)
+Requires-Dist: pyteomics (>=4.7.5,<5.0.0)
+Requires-Dist: scikit-learn (>=1.8.0,<2.0.0)
+Requires-Dist: smart-round (>=1.0.1,<2.0.0)
+Requires-Dist: tabulate (>=0.9.0,<0.10.0)
+Requires-Dist: typer (>=0.21.1,<0.22.0)
+Requires-Dist: uniprot-meta-tool (>=0.2.1,<0.3.0)
+Requires-Dist: xlrd (>=2.0.2,<3.0.0)
+Project-URL: Homepage, https://github.com/protdb/dasmixer
+Description-Content-Type: text/markdown
+
+# DASMixer Core
+
+Core library for proteomics data project management, calculations, and data import.
+
+## Features
+
+- **Project management** — create, open, save `.dasmix` files (SQLite)
+- **Data import** — MGF (spectra), PowerNovo2 / MaxQuant / PLGS (identifications), FASTA (proteins)
+- **Calculations** — ion matching (b/y/a/c/x/z), de novo PPM correction (SeqFixer), coverage calculation
+- **Peptide-to-protein mapping** (npysearch BLAST)
+- **LFQ quantification** — emPAI, iBAQ, NSAF, Top3 (via semPAI)
+- **Reports** — PCA, Volcano, UpSet, Coverage, Sample Summary (Plotly-based)
+- **Export** — HTML, DOCX, XLSX, mzTab
+
+## Installation
+
+```bash
+pip install dasmixer-core
+```
+
+With optional extras:
+
+```bash
+pip install "dasmixer-core[plotly]"     # Plotly + Kaleido for charts and export
+pip install "dasmixer-core[proteins]"   # npysearch for BLAST-like search
+pip install "dasmixer-core[all]"        # Full installation
+```
+
+## Usage
+
+```python
+from dasmixer.api.project.project import Project
+
+async with Project(path="study.dasmix", create_if_not_exists=True) as project:
+    samples = await project.get_samples()
+    ...
+```
+
+Documentation: https://github.com/protdb/dasmixer

dasmixer_core-0.6.0a2/README.md

@@ -0,0 +1,39 @@
+# DASMixer Core
+
+Core library for proteomics data project management, calculations, and data import.
+
+## Features
+
+- **Project management** — create, open, save `.dasmix` files (SQLite)
+- **Data import** — MGF (spectra), PowerNovo2 / MaxQuant / PLGS (identifications), FASTA (proteins)
+- **Calculations** — ion matching (b/y/a/c/x/z), de novo PPM correction (SeqFixer), coverage calculation
+- **Peptide-to-protein mapping** (npysearch BLAST)
+- **LFQ quantification** — emPAI, iBAQ, NSAF, Top3 (via semPAI)
+- **Reports** — PCA, Volcano, UpSet, Coverage, Sample Summary (Plotly-based)
+- **Export** — HTML, DOCX, XLSX, mzTab
+
+## Installation
+
+```bash
+pip install dasmixer-core
+```
+
+With optional extras:
+
+```bash
+pip install "dasmixer-core[plotly]"     # Plotly + Kaleido for charts and export
+pip install "dasmixer-core[proteins]"   # npysearch for BLAST-like search
+pip install "dasmixer-core[all]"        # Full installation
+```
+
+## Usage
+
+```python
+from dasmixer.api.project.project import Project
+
+async with Project(path="study.dasmix", create_if_not_exists=True) as project:
+    samples = await project.get_samples()
+    ...
+```
+
+Documentation: https://github.com/protdb/dasmixer

dasmixer_core-0.6.0a2/pyproject.toml

@@ -0,0 +1,61 @@
+[project]
+name = "dasmixer-core"
+version = "0.6.0a2"
+description = "DASMixer core library — project API, calculations, and data import"
+authors = [
+    {name = "gluck", email = "glucksistemi@gmail.com"}
+]
+readme = "README.md"
+requires-python = "<4.0, >=3.11"
+urls = {Homepage = "https://github.com/protdb/dasmixer"}
+dependencies = [
+    "pandas >=2.3.3,<3.0.0",
+    "numpy >=2.4.1,<3.0.0",
+    "aiosqlite >=0.22.1,<0.23.0",
+    "pydantic >=2.12.5,<3.0.0",
+    "pydantic-settings >=2.12.0,<3.0.0",
+    "typer >=0.21.1,<0.22.0",
+    "pyteomics >=4.7.5,<5.0.0",
+    "peptacular >=2.5.1,<3.0.0",
+    "uniprot-meta-tool >=0.2.1,<0.3.0",
+    "aiofiles >=25.1.0,<26.0.0",
+    "aiocsv >=1.4.0,<2.0.0",
+    "parse >=1.20.2,<2.0.0",
+    "tabulate >=0.9.0,<0.10.0",
+    "scikit-learn >=1.8.0,<2.0.0",
+    "jinja2 >=3.1.6,<4.0.0",
+    "docxtpl >=0.20.2,<0.21.0",
+    "html-for-docx >=1.1.3,<2.0.0",
+    "openpyxl >=3.1.5,<4.0.0",
+    "xlrd >=2.0.2,<3.0.0",
+    "smart-round >=1.0.1,<2.0.0",
+    "mztabwriter[pandas] >=0.1.0,<0.2.0",
+]
+
+[project.optional-dependencies]
+plotly = [
+    "plotly >=6.5.2,<7.0.0",
+    "kaleido >=1.2.0,<2.0.0",
+]
+proteins = [
+    "npysearch >=1.3.1,<2.0.0 ; sys_platform != 'win32'",
+    "npysearch-win >=1.3.1,<2.0.0 ; sys_platform == 'win32'",
+]
+all = [
+    "dasmixer-core[plotly,proteins]",
+]
+
+[build-system]
+requires = ["poetry-core>=2.0.0,<3.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry]
+packages = [
+    {include = "dasmixer/api", from = "src"},
+    {include = "dasmixer/utils", from = "src"},
+    {include = "dasmixer/versions.py", from = "src"},
+]
+
+[tool.poetry.dependencies]
+npysearch = {version = ">=1.3.1,<2", optional = true, markers = "sys_platform != 'win32'"}
+npysearch-win = {version = ">=1.3.1,<2", optional = true, markers = "sys_platform == 'win32'"}

dasmixer_core-0.6.0a2/src/dasmixer/api/__init__.py

@@ -0,0 +1,5 @@
+"""DASMixer API package."""
+
+from .project.project import Project
+
+__all__ = ['Project']

dasmixer_core-0.6.0a2/src/dasmixer/api/calculations/peptides/__init__.py

@@ -0,0 +1 @@
+"""Peptide identification and matching."""

dasmixer_core-0.6.0a2/src/dasmixer/api/calculations/peptides/matching.py

@@ -0,0 +1,161 @@
+"""Peptide identification matching and selection."""
+from typing import Literal
+
+import pandas as pd
+
+from dasmixer.api.project.project import Project
+from dasmixer.utils.logger import logger
+
+
+async def select_preferred_identifications(
+    project: Project,
+    criterion: str,
+    tool_settings: dict[int, dict]
+) -> int:
+    """
+    Select preferred identifications for all spectra based on criterion.
+
+    Args:
+        project: Project instance
+        criterion: Selection criterion — "ppm" or "intensity"
+        tool_settings: Tool-specific settings, mapping tool_id to:
+            - max_ppm: Maximum allowed PPM error (float)
+            - min_score: Minimum identification score (float)
+            - min_ion_intensity_coverage: Minimum % intensity coverage (float)
+            - use_protein_from_file: Use protein IDs from file (bool)
+            - min_protein_identity: Minimum protein sequence identity (float)
+            - denovo_correction: Apply de novo correction (bool)
+            - min_peptide_length: Minimum peptide length (int, default 7)
+            - max_peptide_length: Maximum peptide length (int, default 30)
+
+    Returns:
+        Number of spectra processed
+    """
+    logger.info(f"Starting preferred identification selection (criterion: {criterion})")
+    logger.debug(f"Tool settings: {tool_settings}")
+    counter = 0
+
+    if criterion not in ("ppm", "intensity"):
+        raise ValueError(f"Invalid criterion: {criterion}. Must be 'ppm' or 'intensity'")
+
+    spectra_files = await project.get_spectra_files()
+    for _, spectra_file in spectra_files.iterrows():
+        idents_not_merged = []
+        for tool_id, tool_params in tool_settings.items():
+            idents = await project.get_identifications(spectra_file['id'], tool_id)
+            if tool_params.get("ignore_criteria", False):
+                idents_not_merged.append(idents.copy())
+                continue
+            max_ppm = tool_params.get("max_ppm", 50000)
+            min_score = tool_params.get("min_score", 0)
+            min_ion_intensity_coverage = tool_params["min_ion_intensity_coverage"]
+            min_len = tool_params.get("min_peptide_length", 7)
+            max_len = tool_params.get("max_peptide_length", 30)
+
+
+
+            idents['canonical_length'] = idents['canonical_sequence'].str.len()
+            idents['ppm'] = idents['ppm'].abs()
+            if not tool_params.get("denovo_correction", False):
+                query = (
+                    "ppm <= @max_ppm and "
+                    "score >= @min_score and "
+                    "intensity_coverage >= @min_ion_intensity_coverage and "
+                    "canonical_length >= @min_len and "
+                    "canonical_length <= @max_len"
+                )
+            else:
+                query = (
+                    "ppm <= 50000 and "
+                    "score >= @min_score and "
+                    "intensity_coverage >= @min_ion_intensity_coverage and "
+                    "canonical_length >= @min_len and "
+                    "canonical_length <= @max_len"
+                )
+            idents_not_merged.append(idents.query(query).copy())
+
+        all_idents = pd.concat(idents_not_merged, ignore_index=True)
+        spectras = await project.get_spectra(spectra_file['id'])
+
+        for _, spectrum in spectras.iterrows():
+            spectra_id = spectrum['id']
+            spectra_idents = all_idents.query("spectre_id == @spectra_id")
+            if len(spectra_idents) == 0:
+                continue
+            if criterion == "ppm":
+                crit = 'ppm'
+                asc = True
+            else:
+                crit = 'intensity_coverage'
+                asc = False
+            best_id = spectra_idents.sort_values(crit, ascending=asc).iloc[0]['id']
+            await project.set_preferred_identification(spectra_id, best_id)
+            counter += 1
+
+    return counter
+
+
+async def calculate_preferred_identifications_for_file(
+    project: Project,
+    spectra_file_id: int,
+    criterion: Literal['ppm', 'intensity'],
+    tool_settings: dict[int, dict]
+) -> list[int]:
+    """
+    Calculate preferred identification IDs for a single spectra file.
+
+    Args:
+        project: Project instance
+        spectra_file_id: ID of spectra file to process
+        criterion: "ppm" or "intensity"
+        tool_settings: Tool-specific settings dict
+
+    Returns:
+        List of identification IDs that should be marked as preferred
+    """
+    if criterion not in ("ppm", "intensity"):
+        raise ValueError(f"Invalid criterion: {criterion}. Must be 'ppm' or 'intensity'")
+
+    idents_not_merged = []
+    for tool_id, tool_params in tool_settings.items():
+        max_ppm = tool_params.get("max_ppm", 50)
+        min_score = tool_params.get("min_score", 0)
+        min_ion_intensity_coverage = tool_params["min_ion_intensity_coverage"]
+        min_len = tool_params.get("min_peptide_length", 7)
+        max_len = tool_params.get("max_peptide_length", 30)
+        min_peaks = tool_params.get("min_spectre_peaks", 1)
+        top_peaks_count = tool_params.get("min_top_peaks", 1)
+        min_ions = tool_params.get("min_ions_covered", 1)
+        denovo_correction = tool_params.get("denovo_correction", False)
+        denovo_correction_ppm = tool_params.get("denovo_correction_ppm", 50000)
+
+        idents = await project.get_idents_for_preferred(
+            spectra_file_id=spectra_file_id,
+            tool_id=tool_id,
+            min_score=min_score,
+            max_abs_ppm=max_ppm if not denovo_correction else denovo_correction_ppm,
+            intensity_coverage=min_ion_intensity_coverage,
+            canonical_length=(min_len, max_len),
+            spectre_peaks_count=min_peaks,
+            ions_matched=min_ions,
+            top_peaks_covered=top_peaks_count,
+        )
+        logger.debug(idents)
+        logger.debug(f"{tool_id} {spectra_file_id}")
+        if denovo_correction:
+            idents['min_ppm'] = idents.apply(
+                lambda row: min(abs(row['ppm']), abs(row['matched_ppm'])), axis=1
+            )
+            idents = idents.query('min_ppm <= @max_ppm')
+        else:
+            try:
+                idents['min_ppm'] = idents['ppm'].abs()
+            except KeyError:
+                idents['min_ppm'] = None
+        idents_not_merged.append(idents.copy())
+
+    df = pd.concat(idents_not_merged, ignore_index=True)
+    if df.empty:
+        return []
+    idx = df.groupby('spectre_id')['min_ppm'].idxmin()
+    return [int(x) for x in df.loc[idx, 'id']]