Human genetic evidence is associated with drug approval across therapeutic areas: an observational analysis of 26,278 target-disease pairs with temporal validation and feature ablation
A new observational analysis of 26,278 target-disease pairs has found that drug targets with genetic associations show a significantly higher approval rate compared to those without. The study, which utilized data from Open Targets and ChEMBL, indicated a 3.25-fold higher approval rate for genetically associated targets. While literature mining accounted for most of the classifier's performance, suggesting potential temporal leakage from post-approval publications, other evidence types still retained a baseline signal. The research also identified 1,433 genetically supported Phase 1/2 pairs as a resource for hypothesis generation, though the classifier's practical predictive value was noted as limited. AI