In early drug discovery stages, high throughput virtual screening exercises are routinely done to identify an initial set of hit molecules from a large dataset. In such an experiment, each molecule from a large small-molecule drug library is evaluated in terms of physical properties such as the docking score against a target receptor. In real-life drug discovery experiments, drug libraries are extremely large but still there is only a minor representation of the essentially infinite chemical space, and evaluation of physical properties for each molecule in the library is not computationally feasible. We have developed a novel machine learning framework using Bayesian optimiation that allows us to efficiently sample the chemical space. We show that by sampling only about 5-6% of the molecules in a database, one can identify more than 95% of all the top hit molecules in the whole of the database. We also demonstrate that we could extend this method to multiple objectives (eg. docking score and QED value). We believe that such a framework would tremendously help in reducing the computational effort in not only drug-discovery projects but also areas that require such high-throughput experiments and computations.

Accelerating virtual screening using modern machine learning methods

Fall 2022 abstracts, posters, and presentations will launch in mid-September.

ACS Fall 2022

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.