Deep learning-driven scaffold hopping in the discovery of Akt kinase inhibitors.

Journal: Chemical communications (Cambridge, England)
PMID: 34560776

Abstract

Scaffold hopping has been widely used in drug discovery and is a topic of high interest. Here a deep conditional transformer neural network, SyntaLinker, was applied for the scaffold hopping of a phase III clinical Akt inhibitor, AZD5363. A number of novel scaffolds were generated and compound 1a as a proof-of-concept was synthesized and validated by biochemical assay. Further structure-based optimization of 1a led to a novel Akt inhibitor with high potency (Akt1 IC = 88 nM) and antitumor activities.

Authors

  • Zuqin Wang
    College of Pharmacy, Jinan University, 601 Huangpu Avenue West, Guangzhou 510632, China. zhouyang@jnu.edu.cn.
  • Ting Ran
    Fujian Provincial Key Laboratory of Innovative Drug Target Research, School of Pharmaceutical Sciences, Xiamen University, Xiamen, China.
  • Fang Xu
    CAS Key Laboratory of Urban Pollutant Conversion, Department of Chemistry, University of Science & Technology of China, Hefei 230026, China; School of Medical Engineering, Hefei University of Technology, Hefei 230009, China.
  • Chang Wen
    School of Computer Science, Yangtze University, Jingzhou 434023, China. 400100@yangtzeu.edu.cn.
  • Shukai Song
    College of Pharmacy, Jinan University, 601 Huangpu Avenue West, Guangzhou 510632, China. zhouyang@jnu.edu.cn.
  • Yang Zhou
    State Environmental Protection Key Laboratory of Environmental Pollution Health Risk Assessment, South China Institute of Environmental Sciences, Ministry of Environmental Protection, Guangzhou, China.
  • Hongming Chen
    Hit Discovery, Discovery Sciences, Innovative Medicines and Early Development Biotech Unit, AstraZeneca R&D Gothenburg, 431 83, Mölndal, Sweden.
  • Xiaoyun Lu
    College of Pharmacy, Jinan University, 601 Huangpu Avenue West, Guangzhou 510632, China. zhouyang@jnu.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals