mlsanityData to 14 Oct 2026

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

arXiv 2508.06364 ↗First posted 8 Aug 2025cs.LG cs.AI q-bio.BMcited by 1

On the map: Diffusion models → Flow matching, time series and science

Abstract (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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 17 of its 56 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

17 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design11 Oct
  2. 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep

Other references · 15

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  4. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  5. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  6. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 297
  7. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 264
  8. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 243
  9. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  10. 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 117
  11. 2021DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Sciencecited by 38
  12. 2021Learning to design drug-like molecules in three-dimensional space using deep generative modelscited by 37
3 more
  1. 2022Exploiting Pretrained Biochemical Language Models for Targeted Drug Designcited by 10
  2. 2023DTIAM: A unified framework for predicting drug-target interactions, binding affinities and activation/inhibition mechanismscited by 2
  3. 2024MolMetaLM: a Physicochemical Knowledge-Guided Molecular Meta Language Modelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SurfSpec: Enhancing Off-Target-Agnostic Specificity by Bounding Pocket-Ligand Geometric Mismatchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Structure-based Drug Design with Equivariant Diffusion Models
  2. 2025ReACT-Drug: Reaction-Template Guided Reinforcement Learning for de novo Drug Design
  3. 2025Pharmacophore-Conditioned Diffusion Model for Ligand-Based De Novo Drug Design
  4. 2026Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling
  5. 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
  6. 2026Generating Developable 3D Molecules via Pocket-Conditioned Diffusion and Property-Aware Optimization
  7. 2024Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
  8. 2025Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design