AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug Design

TL;DR

AUTODIFF is a diffusion-based autoregressive model for structure-based drug design that generates realistic, valid molecules with high binding affinity by preserving local conformations and modeling protein-ligand interactions.

Contribution

The paper introduces AUTODIFF, a novel molecule generation framework that improves local structure validity and interaction modeling in structure-based drug design.

Findings

Outperforms existing models in generating valid, realistic molecules.

Maintains high binding affinity in generated molecules.

Uses conformal motif strategy for local structure preservation.

Abstract

Structure-based drug design (SBDD), which aims to generate molecules that can bind tightly to the target protein, is an essential problem in drug discovery, and previous approaches have achieved initial success. However, most existing methods still suffer from invalid local structure or unrealistic conformation issues, which are mainly due to the poor leaning of bond angles or torsional angles. To alleviate these problems, we propose AUTODIFF, a diffusion-based fragment-wise autoregressive generation model. Specifically, we design a novel molecule assembly strategy named conformal motif that preserves the conformation of local structures of molecules first, then we encode the interaction of the protein-ligand complex with an SE(3)-equivariant convolutional network and generate molecules motif-by-motif with diffusion modeling. In addition, we also improve the evaluation framework of SBDD by constraining the molecular weights of the generated molecules in the same range, together with some new metrics, which make the evaluation more fair and practical. Extensive experiments on CrossDocked2020 demonstrate that our approach outperforms the existing models in generating realistic molecules with valid structures and conformations while maintaining high binding affinity.