InstGAN: Instant Actor-Critic-Driven GAN for De Novo Molecule Generation and Property Optimization

Tang, Huidong; Li, Chen; Kamei, Sayaka; Yamanishi, Yoshihiro; Morimoto, Yasuhiko

doi:10.24963/ijcai.2025/694

InstGAN: Instant Actor-Critic-Driven GAN for De Novo Molecule Generation and Property Optimization

Huidong Tang, Chen Li, Sayaka Kamei, Yoshihiro Yamanishi, Yasuhiko Morimoto

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 6236-6244.

https://doi.org/10.24963/ijcai.2025/694

Keywords

Machine Learning: ML: Applications
Multidisciplinary Topics and Applications: MTA: Bioinformatics

Abstract

Deep generative models, such as generative adversarial networks (GANs), have been employed for de~novo molecular generation in drug discovery. Most prior studies have utilized reinforcement learning (RL) algorithms, particularly Monte Carlo tree search (MCTS), to handle the discrete nature of molecular representations in GANs. However, due to the inherent instability in training GANs and RL models, along with the high computational cost associated with MCTS sampling, MCTS RL-based GANs struggle to scale to large chemical databases. To tackle these challenges, this study introduces a novel GAN based on actor-critic RL with instant and global rewards, called InstGAN, to generate molecules at the token-level with multi-property optimization. Furthermore, maximized information entropy is leveraged to alleviate the mode collapse. The experimental results demonstrate that InstGAN outperforms other baselines, achieves comparable performance to state-of-the-art models, and efficiently generates molecules with multi-property optimization. The code is available at: https://github.com/tang777777/InstGAN.

Huidong Tang, Chen Li, Sayaka Kamei, Yoshihiro Yamanishi, and Yasuhiko Morimoto. 2025. InstGAN: Instant Actor-Critic-Driven GAN for De Novo Molecule Generation and Property Optimization. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 6236–6244. https://doi.org/10.24963/ijcai.2025/694

@inproceedings{ijcai2025p694,
  title     = {InstGAN: Instant Actor-Critic-Driven GAN for De Novo Molecule Generation and Property Optimization},
  author    = {Tang, Huidong and Li, Chen and Kamei, Sayaka and Yamanishi, Yoshihiro and Morimoto, Yasuhiko},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {6236--6244},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/694},
  url       = {https://doi.org/10.24963/ijcai.2025/694},
}

TY  - CPAPER
TI  - InstGAN: Instant Actor-Critic-Driven GAN for De Novo Molecule Generation and Property Optimization
AU  - Tang, Huidong
AU  - Li, Chen
AU  - Kamei, Sayaka
AU  - Yamanishi, Yoshihiro
AU  - Morimoto, Yasuhiko
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 6236
EP  - 6244
DO  - 10.24963/ijcai.2025/694
UR  - https://doi.org/10.24963/ijcai.2025/694
ER  -