Artificial Intelligence to explore vast chemical spaces for drug leads
Pedro Ballester
Imperial College London
Academic research excels at discovering promising therapeutic targets. However, discovering drug leads and optimising their potency for a target is an expensive, time-consuming and particularly challenging process, which has traditionally been carried out by pharmaceutical companies with vast resources. This constitutes a barrier to translating innovative biomedical research from academia into new drug candidates, as an optimised lead is required to attract funding for further preclinical and clinical studies via out-licensing or industry partnerships.
Tools are therefore needed to help academics to bridge this translation gap by reducing the experimental efforts required, or even making it possible, to achieve optimised drug leads for a given target.
In this talk, I will start by describing the context and challenges in developing these computational models. I will then explain how current opportunities such as artificial intelligence (AI) and synthesis-on-demand gigascale compound libraries are transforming this research area. Next I will introduce AI models for structure-based virtual screening, where enormous progress has been achieved when a 3D structure of the target and a biochemical assay to validate predicted target activity are available. I will also talk about complementary AI models for phenotypic virtual screening, supplemented by target prediction tools enabling target-agnostic projects.