Supervised multiple kernel learning approaches for multi-omics data integration

Mitja Briscik, Gabriele Tazza, László Vidács, Marie-Agnès Dillies, Sébastien Déjean · 2024

Read Supervised multiple kernel learning approaches for multi-omics data integration by Mitja Briscik, Gabriele Tazza, László Vidács, Marie-Agnès Dillies, Sébastien Déjean (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11585117.txt.

Description

Mitja Briscik and co-authors present new ways in a 2024 paper to fuse many kinds of gene-scale data into one forecast. Labs can now read genes, proteins, and more from the same sample, but joining such mixed sets is hard. One fusion method has shown promise yet sees little use in the field.

The team adapts fusion tricks first built for unguided tasks to guided ones with a known end label. They also test deep learning fusions. Their models sort samples well across test sets. Such joins can sharpen disease calls that no single data kind can make alone. The paper gives gene data teams a wider set of fusion tools.

Catalog record

CREATORMitja Briscik, Gabriele Tazza, László Vidács, Marie-Agnès Dillies, Sébastien Déjean
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE60 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11585117

Browse the full library · About the Tower of Babel