MSGID: 1:317/3 63f6ebf1   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Artificial intelligence conjures proteins that speed up chemical   
   reactions    
    A team has devised machine-learning algorithms that created light-   
   emitting enzymes called luciferases    
      
     Date:   
         February 22, 2023   
     Source:   
         University of Washington School of Medicine/UW Medicine   
     Summary:   
         Scientists have used machine learning to create brand-new enzymes,   
         which are proteins that accelerate chemical reactions. This   
         is an important step in the field of protein design as new   
         enzymes could have many uses across medicine and industrial   
         manufacturing. The research team devised deep-learning, artificial   
         intelligence algorithms that created light- emitting enzymes called   
         luciferases. Laboratory testing confirmed that the new enzymes   
         can recognize specific chemicals and emit light very efficiently.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
   FULL STORY   
   ==========================================================================   
   For the first time, scientists have used machine learning to   
   create brand-new enzymes, which are proteins that accelerate chemical   
   reactions. This is an important step in the field of protein design as new   
   enzymes could have many uses across medicine and industrial manufacturing.   
      
      
   ==========================================================================   
   "Living organisms are remarkable chemists. Rather than relying on toxic   
   compounds or extreme heat, they use enzymes to break down or build   
   up whatever they need under gentle conditions. New enzymes could put   
   renewable chemicals and biofuels within reach," said senior author David   
   Baker, professor of biochemistry at the University of Washington School   
   of Medicine and recipient of the 2021 Breakthrough Prize in Life Sciences.   
      
   As reported Feb, 22 in the journal Nature, a team based at the Institute   
   for Protein Design at UW Medicine devised machine-learning algorithms   
   that can create light-emitting enzymes called luciferases. Laboratory   
   testing confirmed that the new enzymes can recognize specific chemicals   
   and emit light very efficiently. This project was led by two postdoctoral   
   scholars in the Baker Lab, Andy Hsien-Wei Yeh and Christoffer Norn.   
      
   The Naturepaper is titled De novo design of luciferases using deep   
   learning.   
      
   To create new luciferase enzymes, the team first selected chemicals   
   called luciferins that they wanted the proteins to act upon. They then   
   used software to generate thousands of possible protein structures that   
   might react with those chemicals.   
      
   During laboratory testing, the researchers identified an efficient   
   enzyme, dubbed LuxSit (Let there be light). The enzyme performed the   
   desired chemical reaction. Refinement of the enzyme led to dramatic   
   improvements in performance.   
      
   An optimized enzyme, dubbed LuxSit-i, generated enough light to be   
   visible to the naked eye. It was found to be brighter than the natural   
   luciferase enzyme found in the glowing sea pansy Renilla reniformis.   
      
   "We were able to design very efficient enzymes from scratch on the   
   computer, as opposed to relying on enzymes found in nature. This   
   breakthrough means that custom enzymes for almost any chemical reaction   
   could, in principle, be designed," said Yeh.   
      
   New enzymes could benefit biotechnology, medicine, environmental   
   remediation, and manufacturing. For example, in biotechnology, enzymes   
   can improve biofuel production, food processing, and pharmaceutical   
   manufacturing. In medicine, enzymes can serve as therapeutic and   
   diagnostic tools. Enzyme design can improve the environment by breaking   
   down pollutants or cleaning up contaminated sites. And enzymes may also   
   aid in the production of new materials such as biodegradable plastics   
   and adhesives.   
      
   This research was led by UW School of Medicine scientists and included   
   collaborators at the University of California, Los Angeles.   
      
   This work was supported by the Howard Hughes Medical Institute, National   
   Institutes of Health (K99EB031913), United World Antiviral Research   
   Network, National Institute of Allergy and Infectious Disease (1 U01   
   AI151698-01), Audacious Project at the Institute for Protein Design,   
   Open Philanthropy Project Improving Protein Design Fund, Novo Nordisk   
   Foundation (NNF18OC0030446), National Science Foundation (CHE-1764328,   
   OCI-1053575), and Eric and Wendy Schmidt by recommendation of the Schmidt   
   Futures program.   
      
   National Natural Science Foundation of China (22103060) provided partial   
   computational resources.   
      
       * RELATED_TOPICS   
             o Matter_&_Energy   
                   # Biochemistry # Organic_Chemistry # Optics # Chemistry   
             o Computers_&_Math   
                   # Software # Computer_Modeling # Artificial_Intelligence   
                   # Video_Games   
       * RELATED_TERMS   
             o Protein o Artificial_intelligence o Industrial_robot   
             o Denaturation_(biochemistry) o Bioinformatics o   
             Electromagnetic_spectrum o Computer_vision o Electroluminescence   
      
   ==========================================================================   
   Story Source: Materials provided by   
   University_of_Washington_School_of_Medicine/UW_Medicine.   
      
   Original written by Ian Haydon. Note: Content may be edited for style   
   and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Andy Hsien-Wei Yeh, Christoffer Norn, Yakov Kipnis, Doug Tischer,   
      Samuel   
         J. Pellock, Declan Evans, Pengchen Ma, Gyu Rie Lee, Jason Z. Zhang,   
         Ivan Anishchenko, Brian Coventry, Longxing Cao, Justas Dauparas,   
         Samer Halabiya, Michelle DeWitt, Lauren Carter, K. N. Houk, David   
         Baker. De novo design of luciferases using deep learning. Nature,   
         2023; 614 (7949): 774 DOI: 10.1038/s41586-023-05696-3   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/02/230222141133.htm   
      
   --- up 51 weeks, 2 days, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 226/30 227/114 229/111   
   SEEN-BY: 229/112 113 307 317 400 426 428 470 664 700 292/854 298/25   
   SEEN-BY: 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426