2. Academic Validation
  3. Deep learning enables discovery of highly potent anti-osteoporosis natural products

Deep learning enables discovery of highly potent anti-osteoporosis natural products

  • Eur J Med Chem. 2021 Jan 15:210:112982. doi: 10.1016/j.ejmech.2020.112982.
Zhihong Liu 1,  Dane Huang 2,  Shuangjia Zheng 3,  Ying Song 4,  Bingdong Liu 1,  Jingyuan Sun 5,  Zhangming Niu 6,  Qiong Gu 7,  Jun Xu 8,  Liwei Xie 9
Affiliations

Affiliations

  • 1 State Key Laboratory of Applied Microbiology Southern China, Guangdong Provincial Key Laboratory of Microbial Culture Collection and Application, Guangdong Open Laboratory of Applied Microbiology, Guangdong Institute of Microbiology, Guangdong Academy of Sciences, Guangzhou, 510070, China.
  • 2 Research Center for Drug Discovery, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, 510006, China; Guangdong Province Engineering Technology Research Institute of T.C.M., Guangdong Provincial Key Laboratory of Research and Development in Traditional Chinese Medicine, Guangzhou, 510095, China.
  • 3 Research Center for Drug Discovery, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, 510006, China; School of Data and Computer Science, Sun Yat-sen University, Guangzhou, 510006, China.
  • 4 School of Data and Computer Science, Sun Yat-sen University, Guangzhou, 510006, China.
  • 5 Research Center for Drug Discovery, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, 510006, China.
  • 6 Aladdin Healthcare Technologies Ltd., 24-26, Baltic Street West, London EC1Y OUR, UK.
  • 7 Research Center for Drug Discovery, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, 510006, China. Electronic address: guqiong@mail.sysu.edu.cn.
  • 8 Research Center for Drug Discovery, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, 510006, China; School of Biotechnology and Health Sciences, Wuyi University, 99 Yingbin Road, Jiangmen, 529020, China. Electronic address: junxu@biochemomes.com.
  • 9 State Key Laboratory of Applied Microbiology Southern China, Guangdong Provincial Key Laboratory of Microbial Culture Collection and Application, Guangdong Open Laboratory of Applied Microbiology, Guangdong Institute of Microbiology, Guangdong Academy of Sciences, Guangzhou, 510070, China. Electronic address: xielw@gdim.cn.
PMID: 33158578 DOI: 10.1016/j.ejmech.2020.112982
Abstract

A pre-trained self-attentive message passing neural network (P-SAMPNN) model was developed based on our anti-osteoclastogenesis dataset for virtual screening purpose. Validation processes proved that P-SAMPNN model was significantly superior to the Other base line models. A commercially available natural product library was virtually screened by the P-SAMPNN model and resulted in confirmed 5 hits from 10 selected virtual hits. Among the confirmed hits, compounds AP-123/40765213 and AE-562/43462182 are the nanomolar inhibitors against osteoclastogenesis with a new scaffold. Further studies indicate that AP-123/40765213 and AE-562/43462182 significantly suppress the mRNA expression of RANK and downregulate the expressions of osteoclasts-related genes Ctsk, Nfatc1, and Tracp. Our work demonstrated that P-SAMPNN method can guide phenotype-based drug discovery.

Figures