相似性(几何)
计算机科学
Web服务器
化学
万维网
互联网
人工智能
图像(数学)
作者
Caiqin Yan,Zhihong Liu,Yiming Bai,Zhe Wang,Jiansong Fang,Ailin Liu
标识
DOI:10.1021/acs.jcim.4c01445
摘要
Target identification plays a critical role in preclinical drug development. The in silico approach has been developed and widely applied to assist medicinal chemists and pharmacologists in drug target identification. There are many target prediction web servers available today that have revealed both advantages and shortcomings in practical applications. Here, we present 3DSTarPred, a web server for three-dimensional (3D) shape similarity-based target prediction of small molecules. A benchmark study showed that 3DSTarPred achieved a target prediction success rate of 76.27%, which was higher than that of existing target prediction web servers. In addition, the performance of 3DSTarPred in the target prediction of diverse substructures/superstructures was also better than that of the existing target prediction web servers. In case studies, 3DSTarPred was used to identify the potential targets of two small molecules, one being kaempferol, a natural lead compound for the treatment of Alzheimer's disease (AD), and the other being sildenafil, a candidate for drug repurposing in AD. The case studies further demonstrated the reliability and success of 3DSTarPred in practice. The 3DSTarPred server is freely available at http://3dstarpred.pumc.wecomput.com.
科研通智能强力驱动
Strongly Powered by AbleSci AI