Predicting Enzyme-Compound Interactions for Enzyme-Catalysed Reactions

Predicting Enzyme-Compound Interactions for Enzyme-Catalysed Reactions | 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 Research Article Predicting Enzyme-Compound Interactions for Enzyme-Catalysed Reactions Liam Brydon-Brown, Gillian Dobbie, Jörg Simon Wicker, Katerina Taškova This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8129973/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Apr, 2026 Read the published version in Journal of Cheminformatics → Version 1 posted 9 You are reading this latest preprint version Abstract Enzyme-catalysed reactions are common in many areas, including pharmaceutical metabolism and agricultural chemical biodegradation. Analysing and predicting how these reactions occur is increasingly important for identifying toxic by-products and achieving regulatory approval. Incorporating enzyme information into these predictions has been shown to improve prediction capabilities. However, existing methods require knowledge of the enzyme to perform prediction, and in many situations, especially biodegradation, the complexities of the reaction environment mean the exact enzymes are not known. In this paper, we alleviate this issue by proposing a framework to train and evaluate a hierarchical multi-label classifier to predict the enzyme commission numbers a chemical compound will react with. Our method achieves a hierarchical F1-score of up to 93.2%, outperforming existing methodologies. Additionally, we examine how including true and predicted enzyme information impacts product prediction performance compared to not using enzyme information. In our case study utilising biodegradation reaction data, we find that including enzyme commission numbers improve product prediction performance by approximately two percentage points. Scientific Contribution We contribute a novel method for predicting enzyme-compound interactions using a hierarchical multi-label classifier framework. Our method is self tuning to find the best hyperparameters for a given dataset and achieves higher F1 scores than existing methods. We also contribute an investigation into including enzyme information into product prediction algorithms, showing that including this information can improve product prediction performance. cheminformatics biodegradation hierarchical learning enzyme prediction product prediction Full Text Additional Declarations No competing interests reported. Supplementary Files chemeclipsesupp.pdf Cite Share Download PDF Status: Published Journal Publication published 22 Apr, 2026 Read the published version in Journal of Cheminformatics → Version 1 posted Editorial decision: Revision requested 15 Jan, 2026 Reviews received at journal 15 Jan, 2026 Reviewers agreed at journal 20 Dec, 2025 Reviews received at journal 14 Dec, 2025 Reviewers agreed at journal 01 Dec, 2025 Reviewers invited by journal 01 Dec, 2025 Editor assigned by journal 17 Nov, 2025 Submission checks completed at journal 17 Nov, 2025 First submitted to journal 16 Nov, 2025 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-8129973","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":546639711,"identity":"ddba17d5-6a2b-4872-b3c5-3517547791c8","order_by":0,"name":"Liam Brydon-Brown","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABD0lEQVRIiWNgGAWjYBACPgkgkVAhIQekmBkeMDAwNoAQPsAG0vLgjIUxWEsCsVoYH7ZVJDYgtBAAbNK9zyQS2CTS+2ckPzZIqLkju+F2cwPDjxqGPHkcmtlkjptJJPBI5M64kWackHDsmfGGOwcbGHuOMRTjso9NIo1NIkFCIrfhRg7zgQS2w4kbbgAdydvAkNiM0y8gLQYS6fJgLf8gWhj/ArW04dWSANQF1JKQ2AbRwgyypQeXFpljzBYJByQMN555ZmyQ2HfYeCZQy2GZYxKJM3Bo4ZduY7z581+dvNzx5McSH74dlu27kf7w4Zsam8T5OLwPBCwSGEIHGBgwBZEA8wd8sqNgFIyCUTAKGABdeF7A6rLIaAAAAABJRU5ErkJggg==","orcid":"","institution":"University of Auckland","correspondingAuthor":true,"prefix":"","firstName":"Liam","middleName":"","lastName":"Brydon-Brown","suffix":""},{"id":546639712,"identity":"70f0000d-8b3d-43cd-8e5d-4e1ac538b10a","order_by":1,"name":"Gillian Dobbie","email":"","orcid":"","institution":"University of Auckland","correspondingAuthor":false,"prefix":"","firstName":"Gillian","middleName":"","lastName":"Dobbie","suffix":""},{"id":546639713,"identity":"b76d5103-92ae-47c0-9dfb-937de982f98f","order_by":2,"name":"Jörg Simon Wicker","email":"","orcid":"","institution":"University of Auckland","correspondingAuthor":false,"prefix":"","firstName":"Jörg","middleName":"Simon","lastName":"Wicker","suffix":""},{"id":546639715,"identity":"5eace0b1-cb49-4ab1-8508-c6d6d381879e","order_by":3,"name":"Katerina Taškova","email":"","orcid":"","institution":"University of Auckland","correspondingAuthor":false,"prefix":"","firstName":"Katerina","middleName":"","lastName":"Taškova","suffix":""}],"badges":[],"createdAt":"2025-11-17 01:08:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8129973/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8129973/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13321-026-01190-w","type":"published","date":"2026-04-22T15:58:49+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96367604,"identity":"c0aeba7e-d846-434a-be85-be4211455ffa","added_by":"auto","created_at":"2025-11-20 10:13:33","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6430,"visible":true,"origin":"","legend":"","description":"","filename":"445fb01ab09f4630857120ff662bcb4c.json","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/07bba9a79fca5092f4dffb61.json"},{"id":96366972,"identity":"3413b695-2242-44d6-aa70-56ef73538b58","added_by":"auto","created_at":"2025-11-20 10:12:04","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":496020,"visible":true,"origin":"","legend":"","description":"","filename":"445fb01ab09f4630857120ff662bcb4c1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/e8c2c4dd7a6e9ea8a82b053a.xml"},{"id":96342712,"identity":"1ced99d9-d1c9-4c81-897f-cad02c6e561b","added_by":"auto","created_at":"2025-11-20 05:05:22","extension":"eps","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3580,"visible":true,"origin":"","legend":"","description":"","filename":"Orcidlogo.eps","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/fcd42303bb8422b5bebd96c1.eps"},{"id":96367266,"identity":"a742ef16-dba8-48a7-996e-ec54081c1906","added_by":"auto","created_at":"2025-11-20 10:12:28","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95987,"visible":true,"origin":"","legend":"","description":"","filename":"bbd1product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/33703c85cacd8f3976019adf.pdf"},{"id":96342717,"identity":"dd58dd6f-d4e4-457a-a431-5a9ab16aec61","added_by":"auto","created_at":"2025-11-20 05:05:22","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91809,"visible":true,"origin":"","legend":"","description":"","filename":"bbd2product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/205b4c90bab68df69bbbc3a8.pdf"},{"id":96367097,"identity":"df0335b5-a9cf-42f1-9ba2-218795ea8415","added_by":"auto","created_at":"2025-11-20 10:12:10","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95224,"visible":true,"origin":"","legend":"","description":"","filename":"bbd3product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/1bdd7501a5dd8bc3d995db51.pdf"},{"id":96366502,"identity":"7b75c64f-6fc0-415b-acd7-748f8eac0dfe","added_by":"auto","created_at":"2025-11-20 10:11:31","extension":"pdf","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93566,"visible":true,"origin":"","legend":"","description":"","filename":"bbd4product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/e0272fcf4b8dab7152a078b5.pdf"},{"id":96366570,"identity":"04aeea37-ffea-4b63-980a-764fb6d8110b","added_by":"auto","created_at":"2025-11-20 10:11:35","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91637,"visible":true,"origin":"","legend":"","description":"","filename":"bbd5product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/969ba222bc479c0b2cabdda1.pdf"},{"id":96367042,"identity":"004a23aa-1d97-431a-a4bf-56ef85c3f083","added_by":"auto","created_at":"2025-11-20 10:12:07","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38821,"visible":true,"origin":"","legend":"","description":"","filename":"chemeclipsecl.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/9749b8795b9c13516efd4d15.pdf"},{"id":96342721,"identity":"b40801b5-b0bd-4db1-94cc-413640c5510c","added_by":"auto","created_at":"2025-11-20 05:05:22","extension":"svg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105390,"visible":true,"origin":"","legend":"","description":"","filename":"chemeclipsegraphicalabstract.svg","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/c444353fa72cf89795e2a4a9.svg"},{"id":96342729,"identity":"1207d4fc-3e78-40f1-b9f0-7328645317f2","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":332697,"visible":true,"origin":"","legend":"","description":"","filename":"chemeclipsesupp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/c7b1b009d921c4cf8e69656a.pdf"},{"id":96342728,"identity":"7140f141-3d24-44a1-9f4c-3f43b8e46016","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":945097,"visible":true,"origin":"","legend":"","description":"","filename":"chemeclipse.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/64eaf3324c283eb2c7824503.pdf"},{"id":96342722,"identity":"86f56351-ecd4-45b5-aa51-37a7085f6726","added_by":"auto","created_at":"2025-11-20 05:05:22","extension":"pdf","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96502,"visible":true,"origin":"","legend":"","description":"","filename":"ecmap1product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/ea2f588c81e669b84558d5d2.pdf"},{"id":96366547,"identity":"66a0b5ca-3f8b-4caf-8b99-664639467fb0","added_by":"auto","created_at":"2025-11-20 10:11:33","extension":"pdf","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96727,"visible":true,"origin":"","legend":"","description":"","filename":"ecmap2product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/baef8d974a31bb0952aca062.pdf"},{"id":96367312,"identity":"c248d752-1061-4e9d-9ab5-2ca76ee908d9","added_by":"auto","created_at":"2025-11-20 10:12:31","extension":"pdf","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96675,"visible":true,"origin":"","legend":"","description":"","filename":"ecmap3product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/e86303b3274a684cf352d94b.pdf"},{"id":96342724,"identity":"a9de6977-01fa-4857-b8e1-3c5a8ed455c9","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96269,"visible":true,"origin":"","legend":"","description":"","filename":"ecmap4product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/7011c21a1134bdcc4593d566.pdf"},{"id":96342734,"identity":"5bfc1907-b54a-429e-8f2b-b80fdaa7e493","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96045,"visible":true,"origin":"","legend":"","description":"","filename":"ecmap5product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/4dc3d10e1757682010a87371.pdf"},{"id":96342739,"identity":"1ae12025-b277-46e0-bf94-fe78cff10909","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96205,"visible":true,"origin":"","legend":"","description":"","filename":"ecmap6product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/5518a3f21261a8bd6e7fa23a.pdf"},{"id":96366246,"identity":"dcfc7a0c-210d-4e4a-b228-33f7e8468438","added_by":"auto","created_at":"2025-11-20 10:11:18","extension":"pdf","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94673,"visible":true,"origin":"","legend":"","description":"","filename":"ecmap7product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/a448960642ee5d736cc8c0a9.pdf"},{"id":96366930,"identity":"9a7f16df-e565-4a40-817d-f73206d12cc2","added_by":"auto","created_at":"2025-11-20 10:12:02","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159990,"visible":true,"origin":"","legend":"","description":"","filename":"ecnpnotransfer.png","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/b4a21148aa274706e208e38e.png"},{"id":96367193,"identity":"38fc801b-d394-494e-86a6-c63e59f10ca2","added_by":"auto","created_at":"2025-11-20 10:12:16","extension":"pdf","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":60534,"visible":true,"origin":"","legend":"","description":"","filename":"envipathec.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/0aa0629d86120a9411952226.pdf"},{"id":96367129,"identity":"ab7df4eb-5d31-4cf8-bc50-8a0cb4c9237a","added_by":"auto","created_at":"2025-11-20 10:12:12","extension":"pdf","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100668,"visible":true,"origin":"","legend":"","description":"","filename":"exampleecsludge.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/68aacb3f23d3dbf6258ae017.pdf"},{"id":96367318,"identity":"4640e992-3cdf-4076-ba3f-43a8755a3ba0","added_by":"auto","created_at":"2025-11-20 10:12:32","extension":"pdf","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120023,"visible":true,"origin":"","legend":"","description":"","filename":"moebbd.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/0f8bedaadf7b30578bbc4a40.pdf"},{"id":96366189,"identity":"2f98a407-c27b-436d-b59a-115b3df9363f","added_by":"auto","created_at":"2025-11-20 10:11:16","extension":"pdf","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99228,"visible":true,"origin":"","legend":"","description":"","filename":"moeecnpeval.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/481832294cf96c1775a5f5e5.pdf"},{"id":96342740,"identity":"7e15cccb-92d7-41d4-b56d-98a96c6f4e4e","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99259,"visible":true,"origin":"","legend":"","description":"","filename":"moeeval.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/df0d14b73e3c0750e858a593.pdf"},{"id":96342736,"identity":"c174269e-21ec-4e87-8608-d120781387d0","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120105,"visible":true,"origin":"","legend":"","description":"","filename":"moenoebbd.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/32929f74f6fe442cfe57fcb2.pdf"},{"id":96366573,"identity":"b58bfad1-0a68-44ee-b67e-d7f79b8f5db5","added_by":"auto","created_at":"2025-11-20 10:11:35","extension":"pdf","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120434,"visible":true,"origin":"","legend":"","description":"","filename":"moenoesludge.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/5b5f8c2b86c705d63d6746e1.pdf"},{"id":96342748,"identity":"94517ece-3823-484f-b9ce-835018084384","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":121002,"visible":true,"origin":"","legend":"","description":"","filename":"moenoesoil.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/ba601e7e0d87878432a3028f.pdf"},{"id":96367392,"identity":"080254e2-e6e6-4bce-8ee7-c17cf39ec486","added_by":"auto","created_at":"2025-11-20 10:12:43","extension":"pdf","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28998,"visible":true,"origin":"","legend":"","description":"","filename":"sludgepredfrombbd.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/d791f1f057f97e045d6fc0c0.pdf"},{"id":96366594,"identity":"bdc0e435-372b-4b43-87af-e639ad689229","added_by":"auto","created_at":"2025-11-20 10:11:36","extension":"pdf","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41281,"visible":true,"origin":"","legend":"","description":"","filename":"sludgepredfromecmap.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/37b5ff6a390d3b895d285ddb.pdf"},{"id":96342737,"identity":"f794b45c-85ce-44d9-8c61-af43f8babe49","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115991,"visible":true,"origin":"","legend":"","description":"","filename":"sludgeproduct.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/33f0fe57e72b75f78a9ac5af.pdf"},{"id":96366968,"identity":"0223caeb-0bfe-42f5-ab02-1fdd75dfa7d8","added_by":"auto","created_at":"2025-11-20 10:12:04","extension":"bst","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35733,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/acf4ab4a7734eded1adf96a5.bst"},{"id":96342752,"identity":"9d66a7a5-cdf8-4a1d-a7e6-cf4be43444ba","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"cls","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55342,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/32d83a306b5aa3412661fbd3.cls"},{"id":96342754,"identity":"c9f25202-9a84-4c45-ae74-c6a76a9fe07d","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"bst","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64141,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/aabe980f419826c814aedbcf.bst"},{"id":96366869,"identity":"fb09f0d7-e6ea-421f-b6d8-45a446135538","added_by":"auto","created_at":"2025-11-20 10:11:59","extension":"pdf","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94092,"visible":true,"origin":"","legend":"","description":"","filename":"soil1product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/9f643cd2c49f9ad2c8a5eb0c.pdf"},{"id":96342756,"identity":"7d370650-e07a-4dd3-a4aa-e7d23717f2d4","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93513,"visible":true,"origin":"","legend":"","description":"","filename":"soil2product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/9a28358aa8b93c9faf284c2e.pdf"},{"id":96342744,"identity":"112cefd6-4cfa-47fd-bf34-6412a032015c","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93745,"visible":true,"origin":"","legend":"","description":"","filename":"soil3product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/cbf1110ec7d006b91012d1a6.pdf"},{"id":96366998,"identity":"cfcda070-6616-486d-b090-b95a96388430","added_by":"auto","created_at":"2025-11-20 10:12:05","extension":"pdf","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94160,"visible":true,"origin":"","legend":"","description":"","filename":"soil4product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/3fc8ae87e5ed181377789845.pdf"},{"id":96342745,"identity":"89842335-2e7d-4699-aafd-34194a355ca4","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93489,"visible":true,"origin":"","legend":"","description":"","filename":"soil5product.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/e071c2c0dcb7c9e60d5e52be.pdf"},{"id":96342746,"identity":"bc805077-a3e4-4bea-a208-7cf1cd58f3bc","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"pdf","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32005,"visible":true,"origin":"","legend":"","description":"","filename":"soilpredfrombbd.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/28c4069ef0093658f22497bf.pdf"},{"id":96366609,"identity":"a6c52ea8-3bdb-42fa-a4ab-2a62cf3cf3cc","added_by":"auto","created_at":"2025-11-20 10:11:37","extension":"pdf","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":116245,"visible":true,"origin":"","legend":"","description":"","filename":"topkec.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/a77a97ead254364bc4b5238e.pdf"},{"id":96366747,"identity":"0d1bc833-9250-4968-9171-dd621dff04d9","added_by":"auto","created_at":"2025-11-20 10:11:52","extension":"png","order_by":49,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":140401,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineecnpnotransfer.png","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/75b21c7662838cd977349879.png"},{"id":96342747,"identity":"93ec11b9-d77a-4a21-9fca-0892c47f5e9a","added_by":"auto","created_at":"2025-11-20 05:05:23","extension":"xml","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":518613,"visible":true,"origin":"","legend":"","description":"","filename":"445fb01ab09f4630857120ff662bcb4c1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/f15902714fee0d00bd4c76d3.xml"},{"id":96366911,"identity":"1d7a5e1b-836d-408f-9401-4484b4fdc1a7","added_by":"auto","created_at":"2025-11-20 10:12:02","extension":"html","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":517022,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/dbf37fd77a6626b6186a82dc.html"},{"id":107927781,"identity":"a0b1db11-e4ea-4a36-88b3-1cee71d252de","added_by":"auto","created_at":"2026-04-27 16:04:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":710631,"visible":true,"origin":"","legend":"","description":"","filename":"chemeclipse.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1_covered_350b0b7c-78fd-4f40-aed4-51a077282ee6.pdf"},{"id":96342714,"identity":"72f0eec2-c577-4cf4-9a85-c77dc28e1384","added_by":"auto","created_at":"2025-11-20 05:05:22","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":332697,"visible":true,"origin":"","legend":"","description":"","filename":"chemeclipsesupp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8129973/v1/d0534cf500db6546162813c2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predicting Enzyme-Compound Interactions for Enzyme-Catalysed Reactions","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"cheminformatics, biodegradation, hierarchical learning, enzyme prediction, product prediction","lastPublishedDoi":"10.21203/rs.3.rs-8129973/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8129973/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEnzyme-catalysed reactions are common in many areas, including pharmaceutical metabolism and agricultural chemical biodegradation. Analysing and predicting how these reactions occur is increasingly important for identifying toxic by-products and achieving regulatory approval. Incorporating enzyme information into these predictions has been shown to improve prediction capabilities. However, existing methods require knowledge of the enzyme to perform prediction, and in many situations, especially biodegradation, the complexities of the reaction environment mean the exact enzymes are not known. In this paper, we alleviate this issue by proposing a framework to train and evaluate a hierarchical multi-label classifier to predict the enzyme commission numbers a chemical compound will react with. Our method achieves a hierarchical F1-score of up to 93.2%, outperforming existing methodologies. Additionally, we examine how including true and predicted enzyme information impacts product prediction performance compared to not using enzyme information. In our case study utilising biodegradation reaction data, we find that including enzyme commission numbers improve product prediction performance by approximately two percentage points.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eScientific Contribution\u003c/strong\u003e We contribute a novel method for predicting enzyme-compound interactions using a hierarchical multi-label classifier framework. Our method is self tuning to find the best hyperparameters for a given dataset and achieves higher F1 scores than existing methods. We also contribute an investigation into including enzyme information into product prediction algorithms, showing that including this information can improve product prediction performance.\u003c/p\u003e","manuscriptTitle":"Predicting Enzyme-Compound Interactions for Enzyme-Catalysed Reactions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-20 05:05:17","doi":"10.21203/rs.3.rs-8129973/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-15T10:50:22+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-15T10:44:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180943771800102522435300789299045804511","date":"2025-12-20T10:26:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-14T23:58:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"49221874271511186083727283443990895554","date":"2025-12-01T10:54:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-01T08:02:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-18T03:18:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-18T03:17:55+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Cheminformatics","date":"2025-11-17T00:55:06+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5972e47e-c004-49f4-be81-4a6d4d1775af","owner":[],"postedDate":"November 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T16:02:13+00:00","versionOfRecord":{"articleIdentity":"rs-8129973","link":"https://doi.org/10.1186/s13321-026-01190-w","journal":{"identity":"journal-of-cheminformatics","isVorOnly":false,"title":"Journal of Cheminformatics"},"publishedOn":"2026-04-22 15:58:49","publishedOnDateReadable":"April 22nd, 2026"},"versionCreatedAt":"2025-11-20 05:05:17","video":"","vorDoi":"10.1186/s13321-026-01190-w","vorDoiUrl":"https://doi.org/10.1186/s13321-026-01190-w","workflowStages":[]},"version":"v1","identity":"rs-8129973","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8129973","identity":"rs-8129973","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}