paper-with-me

홈 › Papers

ActivityDiff: A diffusion model with Positive and Negative Activity Guidance for De Novo Drug Design

2025-08-08 · Renyi Zhou, Huimin Zhu, Jing Tang, Min Li arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.06364

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts

2024-11-26 · Jinho Chang, Hyungjin Chung, Jong Chul Ye

As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applications use a negated CFG term to filter out unwanted features from samples. Howe…

Denoising

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

2026-07-27 · Bingnan Li, Haozhe Wang, Haozhong Xiong, Fangtai Wu 외 hf

On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern…

Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance

2026-02-21 · Zhou Jiang, Yandong Wen, Zhen Liu arxiv

Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-scale finetuning often shows a generalizat…

Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model

2025-03-28 · CVPR 2025 1 · Changchang Sun, Gaowen Liu, Charles Fleming, Yan Yan

Conditional diffusion models have gained increasing attention since their impressive results for cross-modal synthesis, where the strong alignment between conditioning input and generated output can be achieved by traini…

Music Generation

Diffusion Models with Adaptive Negative Sampling Without External Resources

2025-08-05 · Alakh Desai, Nuno Vasconcelos arxiv

Diffusion models (DMs) have demonstrated an unparalleled ability to create diverse and high-fidelity images from text prompts. However, they are also well-known to vary substantially regarding both prompt adherence and q…