论文标题
生成分子设计模型的多目标潜在空间优化
Multi-Objective Latent Space Optimization of Generative Molecular Design Models
论文作者
论文摘要
基于生成模型的分子设计，例如变异自动编码器（VAE），由于其在探索具有所需特性的高维分子空间的效率上，近年来变得越来越流行。虽然初始模型的功效在很大程度上取决于训练数据，但该模型的采样效率可以通过潜在空间优化进一步增强具有增强性能的新分子。在本文中，我们提出了一种多目标潜在空间优化（LSO）方法，可以显着提高生成分子设计（GMD）的性能。所提出的方法采用了一种迭代的加权再培训方法，其中训练数据中各个分子的权重取决于它们的帕累托效率。我们证明，我们的多目标GMD LSO方法可以显着提高GMD的性能，以共同优化多个分子特性。
Molecular design based on generative models, such as variational autoencoders (VAEs), has become increasingly popular in recent years due to its efficiency for exploring high-dimensional molecular space to identify molecules with desired properties. While the efficacy of the initial model strongly depends on the training data, the sampling efficiency of the model for suggesting novel molecules with enhanced properties can be further enhanced via latent space optimization. In this paper, we propose a multi-objective latent space optimization (LSO) method that can significantly enhance the performance of generative molecular design (GMD). The proposed method adopts an iterative weighted retraining approach, where the respective weights of the molecules in the training data are determined by their Pareto efficiency. We demonstrate that our multi-objective GMD LSO method can significantly improve the performance of GMD for jointly optimizing multiple molecular properties.
