Molecular Generative Adversarial Network with Multi-Property Optimization

• URL: http://arxiv.org/abs/2404.00081v1
• Date: Fri, 29 Mar 2024 08:55:39 GMT
• Title: Molecular Generative Adversarial Network with Multi-Property Optimization
• Authors: Huidong Tang, Chen Li, Sayaka Kamei, Yoshihiro Yamanishi, Yasuhiko Morimoto,
• Abstract summary: Deep generative models, such as generative adversarial networks (GANs), have been employed for $denovo$ molecular generation in drug discovery. 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.
• Score: 3.0001188337985236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 source code will be released upon acceptance of the paper.

Related papers

• When Molecular GAN Meets Byte-Pair Encoding [2.5398391570038736]
  This study introduces a molecular GAN that integrates a byte level byte-pair encoding tokenizer and employs reinforcement learning to enhance de novo molecular generation. Specifically, the generator functions as an actor, producing SMILES strings, while the discriminator acts as a critic, evaluating their quality.
  arXiv  Detail & Related papers  (2024-09-29T15:39:26Z)
• Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review [63.31328039424469]
  This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. We explain the application of various RL algorithms, including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
  arXiv  Detail & Related papers  (2024-07-18T17:35:32Z)
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
  We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation. We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
  arXiv  Detail & Related papers  (2024-02-08T14:54:47Z)
• Distributed Reinforcement Learning for Molecular Design: Antioxidant case [0.20971479389679337]
  DA-MolDQN is a distributed reinforcement learning algorithm for antioxidants. It is 100x faster than previous algorithms and can discover new optimized molecules from proprietary and public antioxidants.
  arXiv  Detail & Related papers  (2023-12-03T03:23:13Z)
• Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting [53.44684898432997]
  Generation of molecules with desired chemical and biological properties is critical for drug discovery. We propose a probabilistic generative model to capture the joint distribution of molecules and their properties. Our method achieves very strong performances on various molecule design tasks.
  arXiv  Detail & Related papers  (2023-06-09T03:04:21Z)
• Retrieval-based Controllable Molecule Generation [63.44583084888342]
  We propose a new retrieval-based framework for controllable molecule generation. We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria. Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
  arXiv  Detail & Related papers  (2022-08-23T17:01:16Z)
• Exploring Chemical Space with Score-based Out-of-distribution Generation [57.15855198512551]
  We propose a score-based diffusion scheme that incorporates out-of-distribution control in the generative differential equation (SDE) Since some novel molecules may not meet the basic requirements of real-world drugs, MOOD performs conditional generation by utilizing the gradients from a property predictor. We experimentally validate that MOOD is able to explore the chemical space beyond the training distribution, generating molecules that outscore ones found with existing methods, and even the top 0.01% of the original training pool.
  arXiv  Detail & Related papers  (2022-06-06T06:17:11Z)
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data [125.7135706352493]
  Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator overfitting. This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator.
  arXiv  Detail & Related papers  (2021-11-12T18:13:45Z)
• Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation [34.26748101294543]
  We propose a novel framework that generates pharmacochemically acceptable molecules with large docking scores. Our method constrains the generated molecules to a realistic and qualified chemical space and effectively explores the space to find drugs. Our model produces molecules of higher quality compared to existing methods while achieving state-of-the-art performance on two of three targets.
  arXiv  Detail & Related papers  (2021-10-04T07:21:00Z)
• TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search [17.2131835813425]
  We present an efficient sequential conformer search technique based on reinforcement learning under the rigid rotor approximation. Our experimental results show that torsionNet outperforms the highest scoring chemoinformatics method by 4x on large alkanes, and by several orders of magnitude on the previously unexplored biopolymer lignin.
  arXiv  Detail & Related papers  (2020-06-12T11:03:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.