{"id":26840,"date":"2025-07-02T16:57:36","date_gmt":"2025-07-02T11:12:36","guid":{"rendered":"https:\/\/www.revoscience.com\/en\/?p=26840"},"modified":"2025-07-02T16:58:07","modified_gmt":"2025-07-02T11:13:07","slug":"self-driving-lab-ai-and-automated-biology-combine-to-improve-enzymes","status":"publish","type":"post","link":"https:\/\/www.revoscience.com\/en\/self-driving-lab-ai-and-automated-biology-combine-to-improve-enzymes\/","title":{"rendered":"Self-driving lab: AI and automated biology combine to improve enzymes"},"content":{"rendered":"\n
\"\"
\u00a0Pictured, from left: Nilmani Singh, Jingxia Lu, Stephen Lane and Professor Huimin Zhao. \/\u00a0Craig Pessman<\/sup><\/em><\/figcaption><\/figure>\n\n\n\n

CHAMPAIGN, Ill.\u2014 By combining artificial intelligence with automated robotics and synthetic biology, researchers at the University of Illinois Urbana-Champaign have dramatically improved the performance of two important industrial enzymes\u2014and created a user-friendly, fast process to improve many more.<\/p>\n\n\n\n

Led by Huimin Zhao<\/a>, a professor of chemical and biomolecular engineering<\/a> at the U. of I., the team reported its findings<\/a> in the journal Nature Communications.<\/em><\/p>\n\n\n\n

\u00a0\u201cEnzymes have been increasingly used in energy production, in therapeutics, and even in consumer products like laundry detergent. But they are not as widely used as they could be because they still have limitations. Our technology can help address those limitations efficiently,\u201d said Zhao, who is also affiliated with the\u00a0Carl R. Woese Institute for Genomic Biology<\/a>\u00a0at the U. of I.<\/p>\n\n\n\n

Enzymes are proteins that carry out specific catalytic functions that drive many biological processes. Those seeking to harness enzymes to advance medicine, technology, energy, or sustainability often run into roadblocks involving an enzyme\u2019s efficiency or its ability to single out a desired target amidst a complex chemical environment, Zhao said.<\/p>\n\n\n\n

\u201cImproving protein function, particularly enzyme function, is challenging because we don\u2019t know exactly what kinds of mutations we should introduce\u2014and it\u2019s usually not just a single mutation; it\u2019s a lot of synergistic mutations,\u201d Zhao said. \u201cWith our model of integrating AI and automated synthetic biology, we offer an efficient way to solve that problem.\u201d<\/p>\n\n\n\n

Zhao\u2019s group\u00a0previously<\/a>\u00a0reported an AI model to predict an enzyme\u2019s function based on its sequence. In the new paper, the researchers take their AI a step further: predicting what changes to a known protein would improve its function.<\/p>\n\n\n\n

\u201cIn a typically sized enzyme, the possible number of variations is larger than the number of atoms in the universe,\u201d said Nilmani Singh, the co-first author of the paper. \u201cSo we use the AI method to help us create a relatively small library of potentially useful variant combinations instead of randomly searching the whole protein sequence.\u201d<\/p>\n\n\n\n

However, training and improving an AI model is more than just code; it requires a lot of input, data, and feedback. So the Illinois team coupled their AI models with the automated capabilities offered by the\u00a0iBioFoundry<\/a>, a center at the U. of I. dedicated to quick, user-friendly engineering and testing of biological systems ranging from enzymes to whole cells. Zhao directs the iBioFoundry, which is supported by the National Science Foundation. \u00a0<\/p>\n\n\n\n

In the new paper, the researchers lay out their process: First, they ask the AI tool how to improve a desired enzyme\u2019s performance. The AI tool searches datasets of known enzyme structures and suggests sequence changes. The automated protein-building machines at the iBioFoundry produce the suggested enzymes, which are then rapidly tested to characterize their functions. The data from those tests is fed into another AI model, which uses the information to improve the next round of suggested protein designs.<\/p>\n\n\n\n

\u201cIt\u2019s a step toward a self-driving lab: a lab that designs its own proteins, makes the proteins, tests them, and makes the next one,\u201d said Stephan Lane, the manager of the iBioFoundry and co-first author. \u201cThe designing and learning is done by an AI algorithm, and the building and testing is done by robotics.\u201d<\/p>\n\n\n\n

Using this method, the team produced variants of two key industrial enzymes with substantially improved performance. One enzyme, added to animal feed to improve its nutritional content, increased its activity by 26 times. The other, a catalyst used in industrial chemical synthesis, had 16 times greater activity and 90 times greater substrate preference, meaning it was far less likely to grab molecules that were not its target.<\/p>\n\n\n\n

\u201cWe described two enzymes in the paper, but it\u2019s truly a generalized approach. We only need a protein sequence and an assay,\u201d Zhao said. \u201cWe want to try to apply it to as many enzymes as possible.\u201d<\/p>\n\n\n\n

Next, the researchers plan to continue improving their AI models and upgrading equipment for even faster, higher-throughput synthesis and testing. They also have developed a user interface, enabling the system to run with a simple typed query. They aim to offer their method as a service for other researchers seeking to improve enzymes and speed drug development and innovations in energy and technology.<\/p>\n\n\n\n

\u201cFor the user interface, the motivation is to allow people with different backgrounds to use the tool,\u201d said graduate student Tianhao Yu, a coauthor of the paper. <\/p>\n\n\n\n

\u201cIf an experimental scientist doesn\u2019t know how to run Python programs, then they can use our interface to help them run the program. They just need to use English to describe their needs, and it will automatically run.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

By combining artificial intelligence with automated robotics and synthetic biology, researchers at the University of Illinois Urbana-Champaign have dramatically improved the performance of two important industrial enzymes\u2014and created a user-friendly, fast process to improve many more.<\/p>\n","protected":false},"author":2,"featured_media":26841,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16,163],"tags":[],"class_list":["post-26840","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-biology","category-ai"],"featured_image_urls":{"full":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme.webp",1260,700,false],"thumbnail":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-200x200.webp",200,200,true],"medium":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-675x375.webp",675,375,true],"medium_large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-768x427.webp",750,417,true],"large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-1100x611.webp",750,417,true],"1536x1536":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme.webp",1260,700,false],"2048x2048":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme.webp",1260,700,false],"ultp_layout_landscape_large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-1200x700.webp",1200,700,true],"ultp_layout_landscape":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-870x570.webp",870,570,true],"ultp_layout_portrait":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-600x700.webp",600,700,true],"ultp_layout_square":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-600x600.webp",600,600,true],"newspaper-x-single-post":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-760x490.webp",760,490,true],"newspaper-x-recent-post-big":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-550x360.webp",550,360,true],"newspaper-x-recent-post-list-image":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-95x65.webp",95,65,true],"web-stories-poster-portrait":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-640x700.webp",640,700,true],"web-stories-publisher-logo":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-96x96.webp",96,96,true],"web-stories-thumbnail":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2025\/07\/sd-enzyme-150x83.webp",150,83,true]},"author_info":{"info":["RevoScience"]},"category_info":"Biology<\/a> AI<\/a>","tag_info":"AI","comment_count":"0","_links":{"self":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/26840","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/comments?post=26840"}],"version-history":[{"count":1,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/26840\/revisions"}],"predecessor-version":[{"id":26842,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/26840\/revisions\/26842"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/media\/26841"}],"wp:attachment":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/media?parent=26840"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/categories?post=26840"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/tags?post=26840"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}