Over the last few years many new machine-learning based scoring functions for predicting the binding of small molecules to proteins have been developed. The aim of these functions is to approximate the distribution which takes two molecules as input and outputs the energy of their interaction. This distribution is dependent on interactions between the atoms of the two molecules and the solvent, and only a scoring function that accounts for these interactions can accurately predict binding affinity on novel/unseen molecules.<br/>To attempt to create a method capable of learning these interactions we built PointVS, a machine learning scoring function, which achieves state-of-the-art performance even after performing rigorous filtering of the training set. PointVS is able to identify important interactions, and further, can be used to extract important binding pharmacophores from a given protein target when supplied with a number of bound structures. This information can be used to perform fragment elaboration, and improve docking scores compared to using structural information from a traditional data-based approach. This not only provides definitive proof that PointVS is learning to identify important binding interactions, but also constitutes the first deep learning-based method for extracting structural information from a target for molecule design.

Can machine learning understand the physics of binding?

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

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