AF2BIND: lightweight and fast prediction of ligand-binding sites

Github | Poster

The accurate prediction of ligand-binding sites in proteins remains an outstanding challenge, despite its potential to accelerate drug discovery and inform on natural protein function. Here, we train a neural network, AF2BIND, using embedding features from a protein structure prediction model, AlphaFold2, to accurately predict the binding sites of proteins.

Contributors: Artem Gazizov, Sergey Ovchinnikov, Nicholas Polizzi