MSGID: 1:317/3 6274a4af   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Using AI to analyze large amounts of biological data    
      
     Date:   
         May 5, 2022   
     Source:   
         University of Missouri-Columbia   
     Summary:   
         Researchers are applying a form of artificial intelligence (AI) -   
         - previously used to analyze how National Basketball Association   
         (NBA) players move their bodies -- to now help scientists develop   
         new drug therapies for medical treatments targeting cancers and   
         other diseases.   
      
      
      
   FULL STORY   
   ==========================================================================   
   Researchers at the University of Missouri are applying a form of   
   artificial intelligence (AI) -- previously used to analyze how National   
   Basketball Association (NBA) players move their bodies -- to now help   
   scientists develop new drug therapies for medical treatments targeting   
   cancers and other diseases.   
      
      
   ==========================================================================   
   The type of AI, called a graph neural network, can help scientists with   
   speeding up the time it takes to sift through large amounts of data   
   generated by studying protein dynamics. This approach can provide new   
   ways to identify target sites on proteins for drugs to work effectively,   
   said Dong Xu, a Curators' Distinguished Professor in the Department   
   of Electrical Engineering and Computer Science at the MU College of   
   Engineering and one of the study's authors.   
      
   "Previously, drug designers may have known about a couple places on a   
   protein's structure to target with their therapies," said Xu, who is   
   also the Paul K. and Dianne Shumaker Professor in bioinformatics. "A   
   novel outcome of this method is that we identified a pathway between   
   different areas of the protein structure, which could potentially allow   
   scientists who are designing drugs to see additional possible target   
   sites for delivering their targeted therapies. This can increase the   
   chances that the therapy may be successful."  Xu said they can also   
   simulate how proteins can change in relation to different conditions,   
   such as the development of cancer, and then use that information to   
   infer their relationships with other bodily functions.   
      
   "With machine learning we can really study what are the important   
   interactions within different areas of the protein structure," Xu   
   said. "Our method provides a systematic review of the data involved   
   when studying proteins, as well as a protein's energy state, which could   
   help when identifying any possible mutation's effect. This is important   
   because protein mutations can enhance the possibility of cancers and   
   other diseases developing in the body."  "Neural relational inference   
   to learn long-range allosteric interactions in proteins from molecular   
   dynamics simulations" was published in Nature Communications. Juexin Wang   
   at MU; and Jingxuan Zhu and Weiwei Han at Jilin University in China, also   
   contributed to this study. Funding was provided by the China Scholarship   
   Council and the Overseas Cooperation Project of Jilin Province, which   
   were used to support Jingxuan Zhu to conduct this research at MU, as well   
   as the National Institute of General Medical Sciences of the National   
   Institutes of Health. The content is solely the responsibility of the   
   authors and does not necessarily represent the official views of the   
   funding agencies.   
      
      
   ==========================================================================   
   Story Source: Materials provided by University_of_Missouri-Columbia. Note:   
   Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Jingxuan Zhu, Juexin Wang, Weiwei Han, Dong Xu. Neural relational   
         inference to learn long-range allosteric interactions in proteins   
         from molecular dynamics simulations. Nature Communications, 2022;   
         13 (1) DOI: 10.1038/s41467-022-29331-3   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2022/05/220505143820.htm   
      
   --- up 9 weeks, 3 days, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 129/330 331 153/7715 218/700   
   SEEN-BY: 229/110 111 317 400 426 428 470 664 700 292/854 298/25 305/3   
   SEEN-BY: 317/3 320/219 396/45   
   PATH: 317/3 229/426