Saved in:
Bibliographic Details
Main Authors: Zhou, Renyi, Zhu, Huimin, Tang, Jing, Li, Min
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.06364
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915434859593728
author Zhou, Renyi
Zhu, Huimin
Tang, Jing
Li, Min
author_facet Zhou, Renyi
Zhu, Huimin
Tang, Jing
Li, Min
contents Achieving precise control over a molecule's biological activity-encompassing targeted activation/inhibition, cooperative multi-target modulation, and off-target toxicity mitigation-remains a critical challenge in de novo drug design. However, existing generative methods primarily focus on producing molecules with a single desired activity, lacking integrated mechanisms for the simultaneous management of multiple intended and unintended molecular interactions. Here, we propose ActivityDiff, a generative approach based on the classifier-guidance technique of diffusion models. It leverages separately trained drug-target classifiers for both positive and negative guidance, enabling the model to enhance desired activities while minimizing harmful off-target effects. Experimental results show that ActivityDiff effectively handles essential drug design tasks, including single-/dual-target generation, fragment-constrained dual-target design, selective generation to enhance target specificity, and reduction of off-target effects. These results demonstrate the effectiveness of classifier-guided diffusion in balancing efficacy and safety in molecular design. Overall, our work introduces a novel paradigm for achieving integrated control over molecular activity, and provides ActivityDiff as a versatile and extensible framework.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06364
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ActivityDiff: A diffusion model with Positive and Negative Activity Guidance for De Novo Drug Design
Zhou, Renyi
Zhu, Huimin
Tang, Jing
Li, Min
Machine Learning
Artificial Intelligence
Biomolecules
Achieving precise control over a molecule's biological activity-encompassing targeted activation/inhibition, cooperative multi-target modulation, and off-target toxicity mitigation-remains a critical challenge in de novo drug design. However, existing generative methods primarily focus on producing molecules with a single desired activity, lacking integrated mechanisms for the simultaneous management of multiple intended and unintended molecular interactions. Here, we propose ActivityDiff, a generative approach based on the classifier-guidance technique of diffusion models. It leverages separately trained drug-target classifiers for both positive and negative guidance, enabling the model to enhance desired activities while minimizing harmful off-target effects. Experimental results show that ActivityDiff effectively handles essential drug design tasks, including single-/dual-target generation, fragment-constrained dual-target design, selective generation to enhance target specificity, and reduction of off-target effects. These results demonstrate the effectiveness of classifier-guided diffusion in balancing efficacy and safety in molecular design. Overall, our work introduces a novel paradigm for achieving integrated control over molecular activity, and provides ActivityDiff as a versatile and extensible framework.
title ActivityDiff: A diffusion model with Positive and Negative Activity Guidance for De Novo Drug Design
topic Machine Learning
Artificial Intelligence
Biomolecules
url https://arxiv.org/abs/2508.06364