Every Compound a Candidate: experience-led risk-taking approaches to accelerate small-molecule drug discovery

Abstract

Despite progress, small-molecule drug discovery remains slow and costly. A paradigm shift is underway by leveraging artificial intelligence (AI) and machine learning (ML); however, these technological advances are necessary but not sufficient. Performance indicators from our partnered portfolio include timelines for data turnaround (5-day) and candidate delivery (2.9 versus 4.0 years for industry). Together with optimised processes and effective decision-making, improved translational predictivity is required. Progressing more compounds through downstream in vitro and in vivo models will rapidly reveal translational thresholds or crucial blockers for compound progression, with humans and machines actively learning from such data. We advocate for more experience-led risk-taking and a mindset shift toward an Every Compound a Candidate strategy, which aims to deliver drug candidates in <2 years.