BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning

TL;DR

BindGPT is a scalable, language model-based framework for 3D molecular design that generates molecules within protein binding sites, combining pretraining and reinforcement learning to outperform specialized models efficiently.

Contribution

The paper introduces BindGPT, a unified generative model that creates 3D molecules conditioned on protein pockets without equivariance assumptions, leveraging large-scale pretraining and reinforcement learning.

Findings

Performs on par or better than diffusion and graph models

Samples molecules two orders of magnitude faster

Eliminates the need for graph reconstruction step

Abstract

Generating novel active molecules for a given protein is an extremely challenging task for generative models that requires an understanding of the complex physical interactions between the molecule and its environment. In this paper, we present a novel generative model, BindGPT which uses a conceptually simple but powerful approach to create 3D molecules within the protein's binding site. Our model produces molecular graphs and conformations jointly, eliminating the need for an extra graph reconstruction step. We pretrain BindGPT on a large-scale dataset and fine-tune it with reinforcement learning using scores from external simulation software. We demonstrate how a single pretrained language model can serve at the same time as a 3D molecular generative model, conformer generator conditioned on the molecular graph, and a pocket-conditioned 3D molecule generator. Notably, the model does not make any representational equivariance assumptions about the domain of generation. We show how such simple conceptual approach combined with pretraining and scaling can perform on par or better than the current best specialized diffusion models, language models, and graph neural networks while being two orders of magnitude cheaper to sample.