Medicine and Health

Phenotype prediction using biologically interpretable neural networks on multi-cohort multi-omics data

A. V. Hilten, J. V. Rooij, et al.

This groundbreaking research by Arno van Hilten, Jeroen van Rooij, M. Arfan Ikram, Wiro J. Niessen, Joyce B. J. van Meurs, and Gennady V. Roshchupkin introduces interpretable predictive models for multi-omics data using biologically informed neural networks. The study showcases high performance in predicting smoking status, with significant insights into genes involved. Discover how multi-omics approaches can surpass single-omics models in stability and generalizability!