Mapping the avoid-ome: a systematic open-science approach to predictive ADMET.

Fraser, James S; Edgar, Steven; Handly, L Naomi; Kosuri, Sriram; Chodera, John D; Murcko, Mark; Walters, W Patrick · Nat Commun · 2026

Where this comes from

Abstract

Drug discovery often fails due to unpredictable ADMET issues, which account for 30% of clinical setbacks. Conventional methods lack the atomistic detail needed to navigate the "Avoid-ome"-a finite set of proteins acting as "anti-targets". OpenADMET is an open-science initiative addressing this by creating pre-competitive, mechanistic datasets. Using high-throughput structural biology, active learning, and community challenges, it builds generalizable models grounded in structural "ground truth". By directly studying the Avoid-ome, OpenADMET facilitates an era of rational, multi-parameter drug design.

Medical subject headings