Overview

Absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties play a crucial role in drug development and chemical risk assessment. The ADMET Structure-Activity Relationship server, entitled admetSAR, was initially launched in 2012 and updated in 2019 as admetSAR2.0. The latest version, admetSAR3.0, is a significantly enhanced version of the widely used comprehensive ADMET assessment tool, admetSAR2.0, supporting search, prediction, and optimization functionalities. Our web server hosts over 370,000 manually curated ADMET annotation data points for 100,000+ unique compounds, sourced from extensive literature and databases. admetSAR3.0 provides a user-friendly search interface, with similarity search aiding in read-across. The advanced multitask graph neural network framework (CLMGraph) supports property prediction. Users can rapidly obtain chemical property profiles for 119 ADMET endpoints. Additionally, a module named ADMETopt has been developed to automatically optimize the ADMET properties of query molecules through transformation rules and scaffold hopping. Here, ADMETopt2 is launched for the first time. With improvements based on functional modules, endpoint data, prediction models, and a user-friendly web interface, admetSAR3.0 aims to become a more useful and powerful tool for drug development and chemical risk assessment.

1. Hongbin Yang, Chaofeng Lou, Lixia Sun, Jie Li, Yinchun Cai, Zhuang Wang, Weihua Li, Guixia Liu, Yun Tang*, admetSAR 2.0: web-service for prediction and optimization of chemical ADMET properties. Bioinformatics 2019, 35, 1067-1069.
2. Feixiong Cheng, Weihua Li, Yadi Zhou, Jie Shen, Zengrui Wu, Guixia Liu, Philip W. Lee, Yun Tang*, admetSAR: a comprehensive source and free tool for assessment of chemical ADMET properties. J. Chem Inf. Model. 2012, 52, 3099-3105.

admetSAR3.0 is free access for every user. For any questions, please contact us at ytang234@ecust.edu.cn.

admetSAR3.0 was mainly developed by Yaxin Gu, Zhuohang Yu and Yimeng Wang. Yaxin Gu collected and processed data for 119 ADMET endpoints, prepared relevant images and textual materials for the website pages, and finalized the article manuscript. Zhuohang Yu completed the construction of the website and implemented the relevant functions of the service, Yimeng Wang established the Contrastive Learning based Multi-Task Graph Neural Network framework (CLMGraph) for 108 ADMET endpoint prediction. Furthermore, there are still many contributions from many people including Zengrui Wu, Long Chen, Chaofeng Lou, Hongbin Yang, Feixiong Cheng, Yadi Zhou, Jie Li, Chen Zhang, Defang Fan, Fuxing Li, Lixia Sun, Qianqian Cao, Zhuang Wang, Jianhui Chen, Mengting Huang, Zhiyuan Wang, Xuan Xu, Yuning Gong, Longqiang Li, Keyun Zhu, Zejun Huang, Yuanting Chen, Changda Gong, Jieyu Zhu, Yanjun Feng, Fei Pan, and Jiaojiao Fang. admetSAR was originally created by Feixiong Cheng and Yadi Zhou. admetSAR2.0 was updated by Hongbin Yang. The project is proposed and supervised by Prof. Yun Tang.