Explainable prediction of catalysing enzymes from reactions using multilayer perceptrons

Explainable prediction of catalysing enzymes from reactions using multilayer perceptrons | 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 Explainable prediction of catalysing enzymes from reactions using multilayer perceptrons Daniel Probst This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2552276/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 Assigning or proposing a catalysing enzyme given a chemical or biochemical reaction is of great interest to life sciences and chemistry alike. The exploration and design of metabolic pathways or the challenge of finding more sustainable enzyme-catalysed alternatives to traditional organic reactions are just two examples of tasks that require an association between reaction and enzyme. However, given the lack of large and balanced annotated data sets of enzyme-catalysed reactions, assigning an enzyme to a reaction still relies on expert-curated rules and databases. Here, we present a data-driven explainable human-in-the-loop machine learning approach to support and ultimately automate the association of a catalysing enzyme with a given biochemical reaction. In addition, the proposed method is capable of predicting enzymes as candidate catalysts for arbitrary organic reactions. Finally, the introduced explainability and visualisation methods can easily be generalised to support other machine-learning approaches involving chemical and biochemical reactions. Physical sciences/Chemistry/Cheminformatics Physical sciences/Chemistry/Chemical synthesis Biological sciences/Computational biology and bioinformatics/Biochemical reaction networks Biological sciences/Biochemistry/Biocatalysis Biological sciences/Drug discovery/Medicinal chemistry/Cheminformatics achine learning enzymatic reactions explainable machine learning cheminformatics Full Text Additional Declarations There is NO Competing Interest. 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-2552276","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":178806391,"identity":"1e6a3b75-8fcc-4dcd-bf14-bdfab2379770","order_by":0,"name":"Daniel Probst","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIie3PsQrCMBCA4SsBuwTniD7EgaCL+CwWwUmC0KWDgyDoUvcO4mO4miOgS9XVh3CodHEQNFJ1cEgdHfLT0hv6kRyAy/WPqeczek7cvBGAPwdg5QRfRKXmo38g8CE0+4FUd3tSGYJszxc6v6w6kjPw8pGF1FLZowQhbKSHgaD1IDSE1RMLQTVEzRGCRAxbQGsdbBhUGLeR4xn1rSDNjJb3IC4lJ3MKFAQFTVQ5qZ3OSDGKUHCzS7rtm128ad1Gqkdzn2vUkcJf6CwadyX3p5TbyCvRe09m8CbloPjza3C5XC7Xuwdn301DyMxdwgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-1737-4407","institution":"EPFL","correspondingAuthor":true,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Probst","suffix":""}],"badges":[],"createdAt":"2023-02-05 10:00:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2552276/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2552276/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":33535783,"identity":"9f926696-a272-45bd-9b2c-c81d913f5fa5","added_by":"auto","created_at":"2023-02-28 05:30:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1978601,"visible":true,"origin":"","legend":"Article File","description":"","filename":"ExplainableECpredictionv1.0.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2552276/v1/ab1513337fc9a17f7198fdf5.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Explainable prediction of catalysing enzymes from reactions using multilayer perceptrons","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":"achine learning, enzymatic reactions, explainable machine learning, cheminformatics","lastPublishedDoi":"10.21203/rs.3.rs-2552276/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2552276/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Assigning or proposing a catalysing enzyme given a chemical or biochemical reaction is of great interest to life sciences and chemistry alike. The exploration and design of metabolic pathways or the challenge of finding more sustainable enzyme-catalysed alternatives to traditional organic reactions are just two examples of tasks that require an association between reaction and enzyme. However, given the lack of large and balanced annotated data sets of enzyme-catalysed reactions, assigning an enzyme to a reaction still relies on expert-curated rules and databases. Here, we present a data-driven explainable human-in-the-loop machine learning approach to support and ultimately automate the association of a catalysing enzyme with a given biochemical reaction. In addition, the proposed method is capable of predicting enzymes as candidate catalysts for arbitrary organic reactions. Finally, the introduced explainability and visualisation methods can easily be generalised to support other machine-learning approaches involving chemical and biochemical reactions.","manuscriptTitle":"Explainable prediction of catalysing enzymes from reactions using multilayer perceptrons","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-02-28 05:30:15","doi":"10.21203/rs.3.rs-2552276/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":"cfc4fd6f-14a1-4456-be4a-e51ab926b803","owner":[],"postedDate":"February 28th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":19477128,"name":"Physical sciences/Chemistry/Cheminformatics"},{"id":19477129,"name":"Physical sciences/Chemistry/Chemical synthesis"},{"id":19477130,"name":"Biological sciences/Computational biology and bioinformatics/Biochemical reaction networks"},{"id":19477131,"name":"Biological sciences/Biochemistry/Biocatalysis"},{"id":19477132,"name":"Biological sciences/Drug discovery/Medicinal chemistry/Cheminformatics"}],"tags":[],"updatedAt":"2023-02-28T05:30:15+00:00","versionOfRecord":[],"versionCreatedAt":"2023-02-28 05:30:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-2552276","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2552276","identity":"rs-2552276","version":["v1"]},"buildId":"J0_U0BvcaRcwD8yVFaRlm","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}