[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117781-en":3,"doc-seo-117781-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117781,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Improving Enzyme Fitness with Machine Learning - Review","Protein engineering applies machine learning to navigate the combinatorial complexity of protein sequence space. By learning how sequence encodes function, researchers can shortlist a smaller set of optimized variants for laboratory measurement, reducing cost and shortening enzyme-engineering campaign timelines. This review summarizes successful algorithm-aided examples, including work within NCCR Catalysis, and explains computational methods used to enhance enantioselectivity, regioselectivity, activity, and stability. With computational techniques rapidly maturing, continued integration is expected to enable more powerful biocatalysts for sustainable chemical synthesis.","doi:10 .2533/chimia.2023.116 Chimia 77 (2023) 116–121 © D. Patsch, R. Buller  \nImproving Enzyme Fitness with Machine Learning  \nDavid Patschaband Rebecca Bullera*  \nAbstract: The combinatorial composition of proteins has triggered the application of machine learning in enzyme engineering. By predicting how protein sequence encodes function, researchers aim to leverage machine learning models to select a reduced number of optimized sequences for laboratory measurement with the aim to lower costs and shorten timelines of enzyme engineering campaigns. In this review, we highlight successful algorithm-aided protein engineering examples, including work carried out within NCCR Catalysis. In this context, we will discuss the underlying computational methods developed to improve enzyme properties such as enantioselectivity, regioselectivity, activity, and stability. Considering the rapid maturing of computational techniques, we expect that their continued application in enzyme engineering campaigns will be key to deliver additional powerful biocatalysts for sustainable chemical synthesis.  \nKeywords: Bioinformatics · Enzyme engineering · Halogenase · Industrial biocatalysis · Machine learning  \nDavid Patsch studied biology and received his BSc from the University of Innsbruck. He obtained his MSc degree in biotechnology from the Management Center Innsbruck. Since 2019 he is pursuing his PhD in the group of Rebecca Buller at the ZHAW.  \nRebecca Buller is a biological chemist and Professor for Biotechnological Methods, Systems and Processes at the Zurich University of Applied Sciences. Rebecca Buller studied chemistry at the Westfälische – Wilhelms Universität Münster (D) and the University of California Santa Barbara (US) . After completing her PhD with a focus on enzyme engineering atETH Zurich (CH), Rebecca Buller accepted a position as laboratory head at the flavour and fragrance company Firmenich (CH) . In 2015, she relocated to the Zurich University of Applied Sciences where she founded the Competence Center for Biocatalysis (CCBIO) . Research in Rebecca Buller’s laboratory focusses on the expansion of the biocatalytic toolbox by sourcing and engineering enzymes for synthetic applications.  \n1. Introduction  \nIn optimal settings, enzymes can facilitate complex reactions with extraordinary specificity and selectivity.[1,2] However, practical reality usually differs from this ideal as wildtype enzymes are often just marginally stable in the selected reaction conditions[3] and perform at scales well below what is required to drive an industrial process. However, as enzymes are combinatorically composed from a limited set of simple building blocks, improved catalysts can be constructed in the laboratory by applying enzyme engineering strategies, among them the directed evolution of proteins. Consequently, engineered enzymes are harnessed in many industrial fields ranging from the fine chemical to the pharmaceutical sectors.[4–6]  \nOver the last decades, the technique of directed evolution has developed into a powerful tool (Nobel prize for chemistry 2018)[7] and today, it is routinely applied to tailor critical protein properties. [4,8] Directed evolution mimics nature’s selection process in the laboratory through iterative cycles of gene diversification and selection of the encoded protein variants generating enzyme lineages with new or improved functions.[9] However, unlike nature, which selects for survival or reproduction, directed evolution can be used to precisely tailor desired protein traits. [10] In this context, astounding improvements in target biological functions for several different enzyme families have been achieved, including activity,[11–13] stereoselectivity,[14,15] thermostability,[16] and solvent tolerance. [17] Strikingly, these studies screened only a relatively small fraction of the target protein’s underlying sequence space, raising the question of whether better sequence solutions would, in principle, exist ","cbCaigJks08YZtov","https://ap.wps.com/l/cbCaigJks08YZtov","pdf",540140,1,6,"English","en",105,"# Introduction\n## Directed evolution and its limitations\n## Computational approaches to address the search-space problem\n## Integration of machine learning into enzyme engineering","[{\"question\":\"How does machine learning help improve enzyme fitness in protein engineering?\",\"answer\":\"Machine learning models relate protein sequence to function, enabling the selection of a reduced number of promising sequences for experimental testing instead of screening extremely large libraries.\"},{\"question\":\"What limitations of directed evolution motivate computational techniques?\",\"answer\":\"Wildtype enzymes are often only marginally stable under process conditions, and directed evolution requires sampling large sequence spaces where many mutations are neutral or unfavorable, making exhaustive experimental screening inefficient.\"},{\"question\":\"Which enzyme properties does the review focus on improving?\",\"answer\":\"The review discusses computational methods aimed at improving enantioselectivity, regioselectivity, activity, and stability of enzymes.\"}]","Improving Enzyme Fitness with Machine Learning - Review | PDF",1785679512,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"improving-enzyme-fitness-with-machine-learning-review","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/improving-enzyme-fitness-with-machine-learning-review/117781/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does machine learning help improve enzyme fitness in protein engineering?","Question",{"text":75,"@type":76},"Machine learning models relate protein sequence to function, enabling the selection of a reduced number of promising sequences for experimental testing instead of screening extremely large libraries.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitations of directed evolution motivate computational techniques?",{"text":80,"@type":76},"Wildtype enzymes are often only marginally stable under process conditions, and directed evolution requires sampling large sequence spaces where many mutations are neutral or unfavorable, making exhaustive experimental screening inefficient.",{"name":82,"@type":73,"acceptedAnswer":83},"Which enzyme properties does the review focus on improving?",{"text":84,"@type":76},"The review discusses computational methods aimed at improving enantioselectivity, regioselectivity, activity, and stability of enzymes.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]