Unified all-atom molecule generation with neural fields

TL;DR

FuncBind is a unified neural field-based generative framework capable of creating diverse, target-conditioned all-atom molecules, including small molecules, peptides, and antibodies, across various atomic systems with competitive performance.

Contribution

The paper introduces FuncBind, a modality-agnostic, neural field-based generative model for structure-conditioned molecule design across diverse atomic systems.

Findings

Achieves competitive in silico performance on multiple molecule types.

Successfully generated novel antibody binders in vitro.

Introduces a new dataset and benchmark for macrocyclic peptide generation.

Abstract

Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBind, a framework based on computer vision to generate target-conditioned, all-atom molecules across atomic systems. FuncBind uses neural fields to represent molecules as continuous atomic densities and employs score-based generative models with modern architectures adapted from the computer vision literature. This modality-agnostic representation allows a single unified model to be trained on diverse atomic systems, from small to large molecules, and handle variable atom/residue counts, including non-canonical amino acids. FuncBind achieves competitive in silico performance in generating small molecules, macrocyclic peptides, and antibody complementarity-determining region loops, conditioned on target structures. FuncBind also generated in vitro novel antibody binders via de novo redesign of the complementarity-determining region H3 loop of two chosen co-crystal structures. As a final contribution, we introduce a new dataset and benchmark for structure-conditioned macrocyclic peptide generation. The code is available at https://github.com/prescient-design/funcbind.