Expanding drug targets for 112 chronic diseases using a machine learning-assisted genetic priority score

Identifying genetic drivers of chronic diseases is necessary for drug discovery. Here, we develop a machine learning-assisted genetic priority score, ML-GPS, that incorporates genetic associations with predicted disease phenotypes to enhance target discovery. We construct gradient boosting models to predict 112 chronic disease phenocodes in the UK Biobank and analyze associations of predicted and observed phenotypes with common, rare, and ultra-rare variants. We integrate these associations with existing evidence using gradient boosting with continuous feature encoding to construct ML-GPS, training it to predict drug indications on Open Targets and externally testing it in SIDER. ML-GPS generates predictions for 2,362,636 gene–phenocode pairs. Using predicted phenotypes, which identify substantially more genetic associations than observed phenotypes across the allele-frequency spectrum, significantly improves ML-GPS performance. ML-GPS increases coverage of drug targets, with the top 1% of scores supporting 15,077 gene–phenocode pairs that previously had no support. ML-GPS identifies known target–disease relationships, promising targets without indicated drugs, and targets for drugs in clinical trials, including LRRK2 inhibitors for Parkinson’s disease and olaparib for cardiovascular disease.