Automated Classification of Mass Spectra
Build a sample-by-m/z intensity matrix from a list of peaks (fast, C++...
Build design matrix X and response Y from peak intensities
Function calculating the distance between two vectors.
Function joining two tables based not on exact matches
Internal: choose a safe number of workers
Fast cross-validated permutation variable importance (ranger-based)
Function finding k Nearest Neighbors for each row of a matrix
Function generating synthetic examples using SMOTE
Fast MDA-style variable selection using ranger permutation importance
Fast random-forest classifier with stratified CV and in-fold sampling ...
Fast supervised classifier with m/z subsetting and optional sampling
Internal C++ helpers (not user-facing)
Internal helpers and C++ exports
Automated classification of mass spectra
Detection of peaks in MassSpectrum objects
Plot spectral data with optional peak markers
Fast class prediction from peak lists using linear regressions
Prediction of the category to which a mass spectrum belongs
Variable selection using methods based on random forests and others.
Fast feature (m/z) selection using multiple hypothesis testing (LIMMA/...
Signal processing for MALDI-TOF spectra (wrapper to SignalProcessingUl...
Optimized signal processing for MALDI-TOF spectra (parallel + optional...
SMOTE for classification datasets
Functions to classify mass spectra in known categories and to determine discriminant mass-to-charge values (m/z). Includes easy-to-use preprocessing pipelines for Matrix Assisted Laser Desorption Ionisation - Time Of Flight Mass Spectrometry (MALDI-TOF) mass spectra, methods to select discriminant m/z from labelled libraries, and tools to predict categories (species, phenotypes, etc.) from selected features. Also provides utilities to build design matrices from peak intensities and labels. While this package was developed with the aim of identifying very similar species or phenotypes of bacteria from MALDI-TOF MS, the functions of this package can also be used to classify other categories associated to mass spectra; or from mass spectra obtained with other mass spectrometry techniques. Parallelized processing and optional C++-accelerated functions are available (notably to deal with large datasets) from version 0.5.0. If you use this package in your research, please cite the associated publication (<doi:10.1016/j.eswa.2025.128796>). For a comprehensive guide, additional applications, and detailed examples, see <https://github.com/agodmer/MSclassifR_examples>.
Useful links