Supervised multiple kernel learning approaches for multi-omics data integration
Multiple kernel learning offers a natural framework for predictive models in multi-omics data. It proved to provide a fast and reliable solution that can compete with and outperform more complex architectures. Our results offer a direction for bio-data mining research, biomarker discovery and further development of methods for heterogeneous data integration.
Authors
- Mitja Briscik
- Sébastien Dejean (ORCID: https://orcid.org/0000-0001-9610-5306)
- Marie‐Agnès Dillies
- László Vidács (ORCID: https://orcid.org/0000-0002-5422-7812)
- Gabriele Tazza (ORCID: https://orcid.org/0000-0001-5263-2278)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Université Toulouse III - Paul Sabatier (FR)
- Institut Pasteur (FR)
- Université Fédérale de Toulouse Midi-Pyrénées (FR)
- Institut National des Sciences Appliquées de Toulouse (FR)
- Université Paris Cité (FR)
- University of Szeged (HU)
- Toulouse Mathematics Institute (FR)
- Génomique Bioinformatique et Applications (FR)
- MTA-SZTE Research Group on Artificial Intelligence (HU)
- Institut de Mathématiques de Toulouse (FR)
Publication Details
- Journal
- BioData Mining
- Published
- 2024-11-23
- DOI
- https://doi.org/10.1186/s13040-024-00406-9
- Citations
- 23
- Primary Topic
- Bioinformatics and Genomic Networks
- Type
- article
- Field-Weighted Citation Impact
- 5.38