4.7 Article

Multi-Objective Drug Design Based on Graph-Fragment Molecular Representation and Deep Evolutionary Learning

期刊

FRONTIERS IN PHARMACOLOGY
卷 13, 期 -, 页码 -

出版社

FRONTIERS MEDIA SA
DOI: 10.3389/fphar.2022.920747

关键词

drug design; multi-objective optimization; deep evolutionary learning; graph fragmentation; variational autoencoder; protein-ligand binding affinity

资金

  1. Artificial Intelligence for Design Challenge Program at the National Research Council Canada
  2. Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant [RGPIN-2021-03879]
  3. Vector Institute for Artificial Intelligence

向作者/读者索取更多资源

Fragment-based drug design is an effective method to constrain the search space and better utilize biologically active compounds. This study integrates a graph fragmentation-based deep generative model with deep evolutionary learning for large-scale multi-objective molecular optimization, and applies protein-ligand binding affinity scores and other desired physicochemical properties as objectives. Experimental results show that the proposed method can generate novel molecules with improved property values and binding affinities.
Drug discovery is a challenging process with a huge molecular space to be explored and numerous pharmacological properties to be appropriately considered. Among various drug design protocols, fragment-based drug design is an effective way of constraining the search space and better utilizing biologically active compounds. Motivated by fragment-based drug search for a given protein target and the emergence of artificial intelligence (AI) approaches in this field, this work advances the field of in silico drug design by (1) integrating a graph fragmentation-based deep generative model with a deep evolutionary learning process for large-scale multi-objective molecular optimization, and (2) applying protein-ligand binding affinity scores together with other desired physicochemical properties as objectives. Our experiments show that the proposed method can generate novel molecules with improved property values and binding affinities.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据