Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design

TL;DR

This paper introduces a novel diffusion model approach for dual-target drug design, leveraging pretraining on single-target data to generate potential dual-target therapeutics with improved efficiency.

Contribution

It presents a new method that reprograms pretrained single-target diffusion models for dual-target drug design, enabling zero-shot transfer and effective generation of dual-target compounds.

Findings

Outperforms baseline methods in dual-target drug generation

Successfully transfers knowledge from single-target pretraining

Demonstrates effectiveness through extensive experiments

Abstract

Dual-target therapeutic strategies have become a compelling approach and attracted significant attention due to various benefits, such as their potential in overcoming drug resistance in cancer therapy. Considering the tremendous success that deep generative models have achieved in structure-based drug design in recent years, we formulate dual-target drug design as a generative task and curate a novel dataset of potential target pairs based on synergistic drug combinations. We propose to design dual-target drugs with diffusion models that are trained on single-target protein-ligand complex pairs. Specifically, we align two pockets in 3D space with protein-ligand binding priors and build two complex graphs with shared ligand nodes for SE(3)-equivariant composed message passing, based on which we derive a composed drift in both 3D and categorical probability space in the generative process. Our algorithm can well transfer the knowledge gained in single-target pretraining to dual-target scenarios in a zero-shot manner. We also repurpose linker design methods as strong baselines for this task. Extensive experiments demonstrate the effectiveness of our method compared with various baselines.