Zoom ID: 989 8993 4794
Passcode: 628565
- Join Via Zoom -
Abstract
Frequent hitters (FH) are the key factors that lead to high false positives in high-throughput screening (HTS). In 2017, an article titled "The Ecstasy and Agony of Assay Interference Compounds", co-authored by nine journal editors of the American Chemical Society, emphasized the dangers of false positive compounds caused by assay interference, and warned researchers that the authenticity of screened positive results needed to be repeatedly confirmed and that potential false positive results needed to be vigilant. However, the existing FH screening methods do not have enough understanding of the mechanism of FH generation, and cannot clearly analyze specific types of FH, which leads to some problems such as low accuracy of FH prediction, underutilization of FH data and narrow application domain. Based on the preliminary work, this project aims to develop high-precision FH prediction models, efficient FH expectation score function, and high-resolution molecular fragment rules toward the key question of " How to effectively reduce the influence of FH on HTS results " based on big data and new artificial intelligence technologies. Then, this project tries to develop an integrated high-precision online FH structural analysis and identification platform based on artificial intelligence technology. The project is of great significance for breaking through the key technical bottlenecks of high-throughput screening and achieving efficient drug development.
Biography
Dr. Dongsheng Cao is a Professor at Xiangya School of Pharmaceutical Sciences of Central South University, Visiting Professor at Xiangya Hospital, Visiting Professor at Hong Kong Baptist University, and a doctoral advisor. He has received multiple honors and awards, including Leading Talent in Science and Technology Innovation of Hunan Province, Distinguished Young Scholar of Hunan Province, Young Talent of Hunan Province, Xiangjiang Scholar, and winner of the excellent doctoral dissertation in Hunan Province. Dr. Cao’s research directions are chemoinformatics, computer-aided drug design and systems biology. He is mainly engaged in high-efficiency chemoinformatics and computer-aided drug molecular design methods and application research based on artificial intelligence technology. He has published over 170 papers in the SCI journals with total citations more than 5700 and H-index is 38. He also developed 35 sets of software platforms, obtained 20 software copyrights, and has accumulated more than 1.7 million visits. Professionally, he currently serves as the Vice Chairman of the Hunan Biomedical Information Committee and a member of the Committee of Computational Toxicology, CST. He was also invited to be the associate editor of the SCI journal CMES-Comp. Model. Eng. and an editorial advisory board member of Chemometric. Intell. Lab. Syst.
Seminar Series by the NYU-ECNU Center for Computational Chemistry at NYU Shanghai