ICVAE: Interpretable Conditional Variational Autoencoder for De Novo Molecular Design

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...

Full description

Saved in:
Bibliographic Details
Published in:International journal of molecular sciences Vol. 26; no. 9; p. 3980
Main Authors: Fan, Xiaqiong, Fang, Senlin, Li, Zhengyan, Ji, Hongchao, Yue, Minghan, Li, Jiamin, Ren, Xiaozhen
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 23.04.2025
MDPI
Subjects:
Algorithms
Autoencoder
Drug Design
Drug development
Drug Discovery - methods
Kinases
Machine Learning
Neural networks
Normal distribution
Optimization
drug discovery
variational autoencoder
molecular generation
ISSN:1422-0067, 1661-6596, 1422-0067
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1422-0067
1661-6596
1422-0067
DOI:10.3390/ijms26093980