This study introduces ML-GPS, a machine learning-assisted genetic priority score, to enhance drug target discovery for 112 chronic diseases. ML-GPS integrates genetic associations with predicted disease phenotypes, improving upon the original GPS framework. Using gradient boosting models and continuous feature encoding, ML-GPS significantly improves prediction accuracy and expands drug target coverage, identifying thousands of previously unsupported gene-phenotype pairs and promising targets for drugs in clinical trials.
Publisher
Nature Communications
Published On
Oct 15, 2024
Authors
Robert Chen, Aine Duffy, Ben O. Petrizzini, Ha My Vy, David Stein, Matthew Mort, Joshua K. Park, Avner Schlessinger, Yuval Itan, David N. Cooper, Daniel M. Jordan, Ghislain Rocheleau, Ron Do
Tags
machine learning
genetic associations
drug target discovery
chronic diseases
gradient boosting models
prediction accuracy
gene-phenotype pairs
Related Publications
Explore these studies to deepen your understanding of the subject.
