ms-toolkit-nrel 0.1.1

Tools for mass spectrometry data analysis

ms-toolkit

Tools for mass spectrometry (MS) library searching and model training.

This library provides a pipeline for vectorizing spectra, training Word2Vec models, preselecting candidates using clustering/GMM, and searching using weighted cosine or embedding similarity. Portions of the code are adapted from the Spec2Vec project.

Features

• Parse MS library text files with optional progress UI
• Create SpectrumDocument objects for Word2Vec training
• Train and load Word2Vec models (w2v.py)
• Vectorize spectra and perform similarity search (preprocessing.py, similarity.py)
• Preselect candidates using KMeans or Gaussian Mixture Models (preselector.py)
• High-level MSToolkit facade wrapping the workflow (api.py)

Installation

Install with pip using the included setup.py:

pip install .

Dependencies include numpy, joblib, gensim, and scikit-learn. Optional UI features require customtkinter or PySide6.

Usage Example

from ms_toolkit.api import MSToolkit

# Initialize toolkit
ms = MSToolkit(library_txt="NIST14.txt", cache_json="library.json")

# Load library (shows progress UI by default)
ms.load_library()

# Vectorize and train models
ms.vectorize_library()
ms.train_preselector()
ms.train_w2v()

# Search using a query spectrum
query = [(100, 0.5), (150, 1.0), (200, 0.8)]
results = ms.search_w2v(query)
for compound, score in results:
    print(compound, score)

License

This project is licensed under the Apache License 2.0. See LICENSE for details. The NOTICE file explains that some code derives from Spec2Vec, which is also Apache 2.0 licensed.