IECata: Interpretable bilinear attention network and evidential deep learning improve the catalytic efficiency prediction of enzymes

IECata: Interpretable bilinear attention network and evidential deep learning improve the catalytic efficiency prediction of enzymes | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article IECata: Interpretable bilinear attention network and evidential deep learning improve the catalytic efficiency prediction of enzymes Jingjing Wang, Yanpeng Zhao, Zhijiang Yang, Ge Yao, Penggang Han, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5583389/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Enzyme catalytic efficiency ( k cat / K m ) is a key parameter for identifying high-activity enzymes. Recently deep learning techniques have demonstrated the potential for fast and accurate k cat / K m prediction. However, three challenges remain: (i) the limited size of the available k cat / K m dataset hinders the development of deep learning models; (ii) the model predictions lacked reliable confidence estimates; and (iii) models lacked interpretable insights into enzyme-catalyzed reactions. To address these challenges, we proposed IECata, a k cat / K m prediction model that provides uncertainty estimation and interpretability. IECata collected two k cat / K m datasets from databases and literatures. By introducing evidential deep learning, IECata provides an uncertainty estimation for k cat / K m predictions. Moreover, it uses bilinear attention mechanism to focused on learning crucial local interactions to interpret the key residues and substrate atoms in enzyme-catalyzed reactions. Testing results indicate that the prediction performance of IECata exceeds that of state-of-the-art benchmark models. Case studies further highlight that the incorporation of uncertainty in screening for highly active enzymes can effectively reduce false positives, thereby improving the efficiency of experimental validation and accelerating directed enzyme evolution. To public usage of IECata, we have developed an online prediction platform: http://mathtc.nscc-tj.cn/cataai/ . Biological sciences/Biochemistry/Biocatalysis Biological sciences/Biochemistry/Enzymes Biological sciences/Chemical biology/Biosynthesis Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Supplementary.docx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5583389","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":402091891,"identity":"b444100a-1443-4b3f-8729-c7c678955781","order_by":0,"name":"Jingjing Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIie3RPQrCMBTA8ZZCpydZG+ohAoWqUOxVKoqTg5N0kkChkweoF+n8SkQd/DiAi+IF4tbRVt3UBjeH/KcM+ZG8xDB0uj+MieKMMnbAJgmKsgyAEK4giIMi23XbxFkPruZi3KYZKslQtNI4oHzieYYtAsYjJYmqUxxguPPdKRyBGWjK2+Q78SvymIWJdOZm3RN0LG7RZd5MXqeI3AE4QY+jbbUUpJqlJpFfvduhXjSTcLt6EspHngc2qklvn+LjYvUjX5aLIdCsSBpnYRsrkTKeh/VXoiz7ISFJIW8N5FMm/22/TqfT6d66AxSbY4e2L40eAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0008-2115-5454","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":true,"prefix":"","firstName":"Jingjing","middleName":"","lastName":"Wang","suffix":""},{"id":402091892,"identity":"cfac283f-1729-4c75-932d-fb488c67dbbc","order_by":1,"name":"Yanpeng Zhao","email":"","orcid":"https://orcid.org/0000-0002-2117-630X","institution":"Academy of Military Medical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Yanpeng","middleName":"","lastName":"Zhao","suffix":""},{"id":402091893,"identity":"09972e30-a34d-470f-b112-a12b2bba019b","order_by":2,"name":"Zhijiang Yang","email":"","orcid":"","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":false,"prefix":"","firstName":"Zhijiang","middleName":"","lastName":"Yang","suffix":""},{"id":402091894,"identity":"14a2bc66-5528-4be8-8345-e7df25581325","order_by":3,"name":"Ge Yao","email":"","orcid":"","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":false,"prefix":"","firstName":"Ge","middleName":"","lastName":"Yao","suffix":""},{"id":402091895,"identity":"5b0ee98e-ba59-4a01-a7c3-ba539339b2ec","order_by":4,"name":"Penggang Han","email":"","orcid":"","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":false,"prefix":"","firstName":"Penggang","middleName":"","lastName":"Han","suffix":""},{"id":402091896,"identity":"0021d68b-3b22-498d-b6ec-2fd2b9d95862","order_by":5,"name":"Jiajia Liu","email":"","orcid":"","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":false,"prefix":"","firstName":"Jiajia","middleName":"","lastName":"Liu","suffix":""},{"id":402091897,"identity":"3234ee05-b09a-4147-bd63-7c091cbc66d3","order_by":6,"name":"Chang Chen","email":"","orcid":"","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":false,"prefix":"","firstName":"Chang","middleName":"","lastName":"Chen","suffix":""},{"id":402091898,"identity":"7c76945d-d108-4560-9bff-32a8b37811cd","order_by":7,"name":"Peng Zan","email":"","orcid":"https://orcid.org/0000-0003-2588-2188","institution":"Shanghai University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Zan","suffix":""},{"id":402091899,"identity":"cd21d607-25dc-4930-b08f-ab3d690b9a25","order_by":8,"name":"Xiukun Wan","email":"","orcid":"","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":false,"prefix":"","firstName":"Xiukun","middleName":"","lastName":"Wan","suffix":""},{"id":402091900,"identity":"0048da92-597c-4c5b-ac42-8906e4d7df04","order_by":9,"name":"Xiaochen Bo","email":"","orcid":"https://orcid.org/0000-0003-1911-7922","institution":"Institute of Health Service and Transfusion Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaochen","middleName":"","lastName":"Bo","suffix":""},{"id":402091901,"identity":"a9cf93ba-5347-466a-98a8-eb4e3dbee783","order_by":10,"name":"Hui Jiang","email":"","orcid":"","institution":"State Key Laboratory of NBC Protection for Civilian","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Jiang","suffix":""}],"badges":[],"createdAt":"2024-12-05 03:30:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5583389/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5583389/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78799620,"identity":"7ac88d2e-8fa0-45a3-bb9d-e4e71e2cb7b2","added_by":"auto","created_at":"2025-03-19 06:18:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1246956,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5583389/v1_covered_d4f75cc5-b331-49eb-ba64-211034a33f73.pdf"},{"id":78798528,"identity":"67318c82-13ec-4659-816f-94152508d71a","added_by":"auto","created_at":"2025-03-19 06:02:16","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":300544,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"Supplementary.docx","url":"https://assets-eu.researchsquare.com/files/rs-5583389/v1/d1d9f8a6478409e98a1a46ab.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"IECata: Interpretable bilinear attention network and evidential deep learning improve the catalytic efficiency prediction of enzymes","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5583389/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5583389/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEnzyme catalytic efficiency (\u003cem\u003ek\u003c/em\u003e\u003csub\u003ecat\u003c/sub\u003e / \u003cem\u003eK\u003c/em\u003e\u003csub\u003em\u003c/sub\u003e) is a key parameter for identifying high-activity enzymes. Recently deep learning techniques have demonstrated the potential for fast and accurate \u003cem\u003ek\u003c/em\u003e\u003csub\u003ecat\u003c/sub\u003e / \u003cem\u003eK\u003c/em\u003e\u003csub\u003em\u003c/sub\u003e prediction. However, three challenges remain: (i) the limited size of the available \u003cem\u003ek\u003c/em\u003e\u003csub\u003ecat\u003c/sub\u003e / \u003cem\u003eK\u003c/em\u003e\u003csub\u003em\u003c/sub\u003e dataset hinders the development of deep learning models; (ii) the model predictions lacked reliable confidence estimates; and (iii) models lacked interpretable insights into enzyme-catalyzed reactions. To address these challenges, we proposed IECata, a \u003cem\u003ek\u003c/em\u003e\u003csub\u003ecat\u003c/sub\u003e / \u003cem\u003eK\u003c/em\u003e\u003csub\u003em\u003c/sub\u003e prediction model that provides uncertainty estimation and interpretability. IECata collected two \u003cem\u003ek\u003c/em\u003e\u003csub\u003ecat\u003c/sub\u003e / \u003cem\u003eK\u003c/em\u003e\u003csub\u003em\u003c/sub\u003e datasets from databases and literatures. By introducing evidential deep learning, IECata provides an uncertainty estimation for \u003cem\u003ek\u003c/em\u003e\u003csub\u003ecat\u003c/sub\u003e / \u003cem\u003eK\u003c/em\u003e\u003csub\u003em\u003c/sub\u003e predictions. Moreover, it uses bilinear attention mechanism to focused on learning crucial local interactions to interpret the key residues and substrate atoms in enzyme-catalyzed reactions. Testing results indicate that the prediction performance of IECata exceeds that of state-of-the-art benchmark models. Case studies further highlight that the incorporation of uncertainty in screening for highly active enzymes can effectively reduce false positives, thereby improving the efficiency of experimental validation and accelerating directed enzyme evolution. To public usage of IECata, we have developed an online prediction platform: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://mathtc.nscc-tj.cn/cataai/\u003c/span\u003e\u003cspan address=\"http://mathtc.nscc-tj.cn/cataai/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"IECata: Interpretable bilinear attention network and evidential deep learning improve the catalytic efficiency prediction of enzymes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-19 05:46:12","doi":"10.21203/rs.3.rs-5583389/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6f71f036-5c44-4cd3-a179-2be0009a3df9","owner":[],"postedDate":"March 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":42856673,"name":"Biological sciences/Biochemistry/Biocatalysis"},{"id":42856674,"name":"Biological sciences/Biochemistry/Enzymes"},{"id":42856675,"name":"Biological sciences/Chemical biology/Biosynthesis"}],"tags":[],"updatedAt":"2025-03-19T05:46:14+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-19 05:46:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5583389","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5583389","identity":"rs-5583389","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}