数字农科院2.0

ICVAE: Interpretable Conditional Variational Autoencoder for De Novo Molecular Design

文献类型： 外文期刊

作者： Xiaqiong Fan;Senlin Fang;Zhengyan Li;Hongchao Ji;Minghan Yue;Jiamin Li;Xiaozhen Ren

作者机构：

关键词： drug discovery;molecular generation;variational autoencoder

期刊名称： International Journal of Molecular Sciences

ISSN： 1661-6596

年卷期： 2025 年 26 卷 9 期

页码：

收录情况： SCIE（2025版）

摘要： Recent studies have demonstrated that machine learning-based generative models can create novel molecules with desirable properties. Among them, Conditional Variational Autoencoder (CVAE) is a powerful approach to generate molecules with desired physiochemical and pharmacological properties. However, the CVAE’s latent space is still a black-box, making it difficult to understand the relationship between the latent space and molecular properties. To address this issue, we propose the Interpretable Conditional Variational Autoencoder (ICVAE), which introduces a modified loss function that correlates the latent value with molecular properties. ICVAE established a linear mapping between latent variables and molecular properties. This linearity is not only crucial for improving interpretability, by assigning clear semantic meaning to latent dimensions, but also provides a practical advantage. It enables direct manipulation of molecular attributes through simple coordinate shifts in latent space, rather than relying on opaque, black-box optimization algorithms. Our experimental results show that the ICVAE can linearly relate one or multiple molecular properties with the latent value and generate molecules with precise properties by controlling the latent values. The ICVAE’s interpretability allows us to gain insight into the molecular generation process, making it a promising approach in drug discovery and material design.

分类号：

  • 相关文献

[1]TransVAE-DTA: Transformer and variational autoencoder network for drug-target binding affinity prediction. Zhou C.,Li Z.,Song J.,Xiang W.. 2024

[2]Searching for protein variants with desired properties using deep generative models. Yan Li,Yinying Yao,Yu Xia,Mingjing Tang. 2023

[3]Epigenetics in Schistosomes: What We know and What We Need know. Liu, Weiwei. 2016

[4]Target deconvolution with matrix-augmented pooling strategy reveals cell-specific drug-protein interactions. Hongchao Ji,Xue Lu,Shiji Zhao,Qiqi Wang,Bin Liao,Ludwig G. Bauer,Kilian V.M. Huber,Ray Luo,Ruijun Tian,Chris Soon Heng Tan. 2023

[5]Advances in the Development of Ferroptosis-Inducing Agents for Cancer Treatment. Li Zhang,Yulong Li,Yufeng Qian,Ruliang Xie,Wei Peng,Wen Zhou. 2025

作者其他论文 更多>>