Molecular Generative Adversarial Network with Multi-Property Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Huidong, Li, Chen, Kamei, Sayaka, Yamanishi, Yoshihiro, Morimoto, Yasuhiko
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912574972362752
author Tang, Huidong
Li, Chen
Kamei, Sayaka
Yamanishi, Yoshihiro
Morimoto, Yasuhiko
author_facet Tang, Huidong
Li, Chen
Kamei, Sayaka
Yamanishi, Yoshihiro
Morimoto, Yasuhiko
contents 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 source code will be released upon acceptance of the paper.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00081
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Molecular Generative Adversarial Network with Multi-Property Optimization
Tang, Huidong
Li, Chen
Kamei, Sayaka
Yamanishi, Yoshihiro
Morimoto, Yasuhiko
Biomolecules
Artificial Intelligence
Machine Learning
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 source code will be released upon acceptance of the paper.
title Molecular Generative Adversarial Network with Multi-Property Optimization
topic Biomolecules
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2404.00081