Background: Understanding the relationship between the Omics and the phenotype is a central problem in precision medicine. The high dimensionality of metabolomics data challenges learning algorithms in terms of scalability and generalization. Most learning algorithms do not produce interpretable models -- Method: We propose an ensemble learning algorithm based on conjunctions or disjunctions of decision rules. -- Results : Applications on metabolomics data shows that it produces models that achieves high predictive performances. The interpretability of the models makes them useful for biomarker discovery and patterns discovery in high dimensional data.
@article{arxiv.2208.06436,
title = {RandomSCM: interpretable ensembles of sparse classifiers tailored for omics data},
author = {Thibaud Godon and Pier-Luc Plante and Baptiste Bauvin and Elina Francovic-Fontaine and Alexandre Drouin and Jacques Corbeil},
journal= {arXiv preprint arXiv:2208.06436},
year = {2022}
}