Saved in:
Bibliographic Details
Main Authors: Xu, Dong, Yang, Zhangfan, Wong, Ka-chun, Zhu, Zexuan, Li, Jiangqiang, Ji, Junkai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14488
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916796904243200
author Xu, Dong
Yang, Zhangfan
Wong, Ka-chun
Zhu, Zexuan
Li, Jiangqiang
Ji, Junkai
author_facet Xu, Dong
Yang, Zhangfan
Wong, Ka-chun
Zhu, Zexuan
Li, Jiangqiang
Ji, Junkai
contents Breakthroughs in high-accuracy protein structure prediction, such as AlphaFold, have established receptor-based molecule design as a critical driver for rapid early-phase drug discovery. However, most approaches still struggle to balance pocket-specific geometric fit with strict valence and synthetic constraints. To resolve this trade-off, a Retrieval-Enhanced Aligned Diffusion termed READ is introduced, which is the first to merge molecular Retrieval-Augmented Generation with an SE(3)-equivariant diffusion model. Specifically, a contrastively pre-trained encoder aligns atom-level representations during training, then retrieves graph embeddings of pocket-matched scaffolds to guide each reverse-diffusion step at inference. This single mechanism can inject real-world chemical priors exactly where needed, producing valid, diverse, and shape-complementary ligands. Experimental results demonstrate that READ can achieve very competitive performance in CBGBench, surpassing state-of-the-art generative models and even native ligands. That suggests retrieval and diffusion can be co-optimized for faster, more reliable structure-based drug design.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14488
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reimagining Target-Aware Molecular Generation through Retrieval-Enhanced Aligned Diffusion
Xu, Dong
Yang, Zhangfan
Wong, Ka-chun
Zhu, Zexuan
Li, Jiangqiang
Ji, Junkai
Biomolecules
Machine Learning
Breakthroughs in high-accuracy protein structure prediction, such as AlphaFold, have established receptor-based molecule design as a critical driver for rapid early-phase drug discovery. However, most approaches still struggle to balance pocket-specific geometric fit with strict valence and synthetic constraints. To resolve this trade-off, a Retrieval-Enhanced Aligned Diffusion termed READ is introduced, which is the first to merge molecular Retrieval-Augmented Generation with an SE(3)-equivariant diffusion model. Specifically, a contrastively pre-trained encoder aligns atom-level representations during training, then retrieves graph embeddings of pocket-matched scaffolds to guide each reverse-diffusion step at inference. This single mechanism can inject real-world chemical priors exactly where needed, producing valid, diverse, and shape-complementary ligands. Experimental results demonstrate that READ can achieve very competitive performance in CBGBench, surpassing state-of-the-art generative models and even native ligands. That suggests retrieval and diffusion can be co-optimized for faster, more reliable structure-based drug design.
title Reimagining Target-Aware Molecular Generation through Retrieval-Enhanced Aligned Diffusion
topic Biomolecules
Machine Learning
url https://arxiv.org/abs/2506.14488