Salvato in:
Dettagli Bibliografici
Autori principali: Zeng, Qingyuan, Cai, Pengxiang, Guan, Zixin, Chen, Ziyang, Liu, Anglin, Qin, Lang, Lai, Xinyao, Chen, Jintai
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.25681
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910254805024768
author Zeng, Qingyuan
Cai, Pengxiang
Guan, Zixin
Chen, Ziyang
Liu, Anglin
Qin, Lang
Lai, Xinyao
Chen, Jintai
author_facet Zeng, Qingyuan
Cai, Pengxiang
Guan, Zixin
Chen, Ziyang
Liu, Anglin
Qin, Lang
Lai, Xinyao
Chen, Jintai
contents Designing a single molecule that modulates two targets is a promising strategy for polypharmacology, but it remains substantially harder than standard single-target generation because one candidate must satisfy two binding requirements while preserving drug-likeness and synthesizability. Existing dual-target generative methods typically introduce dual-target capability by either retraining the generator or intervening in the diffusion process during sampling. The former can be costly and difficult to stabilize when dual-target supervision is sparse, while the latter may be sensitive to denoising-time target balancing and competing update directions. These limitations motivate a generator-preserving alternative that keeps the pretrained prior intact: can dual-target candidates instead be recovered from the input space of a frozen single-target diffusion model, without modifying its parameters or denoising dynamics? We formulate this task as a constrained multi-objective optimization problem and propose REUSE, a hierarchical evolutionary input-space search framework that combines pair-conditioned exploration with structured multi-stage selection to enforce dual-target affinity, chemical quality, and diversity. Experiments show that, compared with methods that modify the diffusion process, REUSE consistently improves dual-target affinity and balance, achieving a 20.9-percentage-point gain in Dual High Affinity over the strongest prior baseline while maintaining competitive molecular quality.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25681
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models
Zeng, Qingyuan
Cai, Pengxiang
Guan, Zixin
Chen, Ziyang
Liu, Anglin
Qin, Lang
Lai, Xinyao
Chen, Jintai
Machine Learning
Artificial Intelligence
Designing a single molecule that modulates two targets is a promising strategy for polypharmacology, but it remains substantially harder than standard single-target generation because one candidate must satisfy two binding requirements while preserving drug-likeness and synthesizability. Existing dual-target generative methods typically introduce dual-target capability by either retraining the generator or intervening in the diffusion process during sampling. The former can be costly and difficult to stabilize when dual-target supervision is sparse, while the latter may be sensitive to denoising-time target balancing and competing update directions. These limitations motivate a generator-preserving alternative that keeps the pretrained prior intact: can dual-target candidates instead be recovered from the input space of a frozen single-target diffusion model, without modifying its parameters or denoising dynamics? We formulate this task as a constrained multi-objective optimization problem and propose REUSE, a hierarchical evolutionary input-space search framework that combines pair-conditioned exploration with structured multi-stage selection to enforce dual-target affinity, chemical quality, and diversity. Experiments show that, compared with methods that modify the diffusion process, REUSE consistently improves dual-target affinity and balance, achieving a 20.9-percentage-point gain in Dual High Affinity over the strongest prior baseline while maintaining competitive molecular quality.
title Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.25681