ENGINE: A Scalable Equivariant Graph Network Framework for Precise Protein Function Prediction

ENGINE: A Scalable Equivariant Graph Network Framework for Precise Protein Function Prediction | 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 ENGINE: A Scalable Equivariant Graph Network Framework for Precise Protein Function Prediction Zixu Ran, Xudong Guo, Tong Pan, Yue Bi, Yi Hao, Heyun Sun, Jiangning Song, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6961427/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 Nov, 2025 Read the published version in Genome Biology → Version 1 posted 10 You are reading this latest preprint version Abstract Protein function research helps in understanding the complex biological processes that occur within cells. However, the intricate nature of protein structures and functions, along with the rapid growth of protein sequence data, presents a pressing challenge to develop efficient computational methods for accurate protein annotation. In this study, we propose ENGINE, a multi-channel deep learning framework designed for robust protein function prediction. ENGINE integrates an equivariant graph convolutional network model to capture geometric features from protein 3D structures, leverages the large language model ESM-C to encode evolutionary and sequence-derived information, and combines an innovative 3D sequence representation that unifies spatial and sequential signals. We demonstrate that ENGINE consistently surpasses current state-of-the-art methods across diverse protein function prediction benchmarks, demonstrating robust generalisation and high predictive accuracy. Beyond performance, ENGINE provides interpretable insights into key sequence features and structural motifs, enabling the identification of functionally critical residues and substructures within proteins. This facilitates a deeper mechanistic understanding of protein function annotation outcomes and supports hypothesis generation for downstream biological studies. By offering reliable predictions with biological interpretability, ENGINE contributes to advancing research into cellular processes and disease mechanisms. The model is freely available for academic use at https://github.com/ABILiLab/ENGINE , serving as a valuable tool for the broader scientific community. deep learning protein 3D structure GO terms protein function prediction Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryResults.docx Cite Share Download PDF Status: Published Journal Publication published 29 Nov, 2025 Read the published version in Genome Biology → Version 1 posted Editorial decision: Revision requested 24 Sep, 2025 Reviews received at journal 25 Jul, 2025 Reviewers agreed at journal 19 Jul, 2025 Reviews received at journal 16 Jul, 2025 Reviewers agreed at journal 14 Jul, 2025 Reviewers agreed at journal 14 Jul, 2025 Reviewers invited by journal 14 Jul, 2025 Editor assigned by journal 27 Jun, 2025 Submission checks completed at journal 24 Jun, 2025 First submitted to journal 24 Jun, 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-6961427","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":485703508,"identity":"555b42e5-fca0-4a34-aae2-d55a8fccbfeb","order_by":0,"name":"Zixu Ran","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Zixu","middleName":"","lastName":"Ran","suffix":""},{"id":485703509,"identity":"aa1b1258-fbd1-405a-9b90-1a269b9ef6e5","order_by":1,"name":"Xudong Guo","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Xudong","middleName":"","lastName":"Guo","suffix":""},{"id":485703510,"identity":"2c417160-1d59-4ba4-9b97-0b559c82b7bd","order_by":2,"name":"Tong Pan","email":"","orcid":"","institution":"Monash University","correspondingAuthor":false,"prefix":"","firstName":"Tong","middleName":"","lastName":"Pan","suffix":""},{"id":485703511,"identity":"05b25760-0f6a-42d7-9866-1110c000c90e","order_by":3,"name":"Yue Bi","email":"","orcid":"","institution":"Monash University","correspondingAuthor":false,"prefix":"","firstName":"Yue","middleName":"","lastName":"Bi","suffix":""},{"id":485703512,"identity":"501286c7-7aa9-4a42-aa07-7e091d6a497b","order_by":4,"name":"Yi Hao","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Hao","suffix":""},{"id":485703513,"identity":"66201acf-c4f8-42a9-bca2-affd9f987dc3","order_by":5,"name":"Heyun Sun","email":"","orcid":"","institution":"The University of Adelaide","correspondingAuthor":false,"prefix":"","firstName":"Heyun","middleName":"","lastName":"Sun","suffix":""},{"id":485703514,"identity":"621fefa4-cd0d-41ed-9ef6-a1dec8396302","order_by":6,"name":"Jiangning Song","email":"","orcid":"","institution":"Monash University","correspondingAuthor":false,"prefix":"","firstName":"Jiangning","middleName":"","lastName":"Song","suffix":""},{"id":485703515,"identity":"d96737a0-3090-4428-b9d0-d289a5f6ee9e","order_by":7,"name":"Fuyi Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYBAC9gYGhgMMBRJyIM4HIGZsIKSF5wBIi4GEMUj1DKK1MDAYMCQ2EK9FIscQaItF+naJ5IfNPAw2shsOMD97QECLAchhuTtnpBkCtaQZbzjAZm6AT4s9TMuG2wnmj3kYDiduOMDDJkGMLekGt9M/Am35T7yWBIPbOSCHHSBCC8+zggMJBhKGG+6/KWycY5BsPPMwmxl+LezJmz98qKiTNzhzfGPDmwo72b7jzc/wamFg4DBgSIBzQEHFjF89ELA/IKhkFIyCUTAKRjgAANqjR2gVSEukAAAAAElFTkSuQmCC","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":true,"prefix":"","firstName":"Fuyi","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-06-24 04:38:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6961427/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6961427/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13059-025-03886-y","type":"published","date":"2025-11-29T15:58:45+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97178659,"identity":"b0f9a872-ed52-4909-b0d5-f348d9d74b91","added_by":"auto","created_at":"2025-12-01 16:12:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1669894,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptENGINE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6961427/v1_covered_f4f6eb8a-d22f-47cb-8531-a9b66dda167e.pdf"},{"id":86833127,"identity":"a9663f85-935f-49b2-8168-ce6ea38a0d5c","added_by":"auto","created_at":"2025-07-16 06:35:13","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":495509,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryResults.docx","url":"https://assets-eu.researchsquare.com/files/rs-6961427/v1/9a58769049ee90960b55edc7.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"ENGINE: A Scalable Equivariant Graph Network Framework for Precise Protein Function Prediction","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":"genome-biology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gbio","sideBox":"Learn more about [Genome Biology](https://genomebiology.biomedcentral.com/)","snPcode":"13059","submissionUrl":"https://submission.springernature.com/new-submission/13059/3","title":"Genome Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"deep learning, protein 3D structure, GO terms, protein function prediction","lastPublishedDoi":"10.21203/rs.3.rs-6961427/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6961427/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eProtein function research helps in understanding the complex biological processes that occur within cells. However, the intricate nature of protein structures and functions, along with the rapid growth of protein sequence data, presents a pressing challenge to develop efficient computational methods for accurate protein annotation. In this study, we propose ENGINE, a multi-channel deep learning framework designed for robust protein function prediction. ENGINE integrates an equivariant graph convolutional network model to capture geometric features from protein 3D structures, leverages the large language model ESM-C to encode evolutionary and sequence-derived information, and combines an innovative 3D sequence representation that unifies spatial and sequential signals. We demonstrate that ENGINE consistently surpasses current state-of-the-art methods across diverse protein function prediction benchmarks, demonstrating robust generalisation and high predictive accuracy. Beyond performance, ENGINE provides interpretable insights into key sequence features and structural motifs, enabling the identification of functionally critical residues and substructures within proteins. This facilitates a deeper mechanistic understanding of protein function annotation outcomes and supports hypothesis generation for downstream biological studies. By offering reliable predictions with biological interpretability, ENGINE contributes to advancing research into cellular processes and disease mechanisms. The model is freely available for academic use at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/ABILiLab/ENGINE\u003c/span\u003e\u003cspan address=\"https://github.com/ABILiLab/ENGINE\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e, serving as a valuable tool for the broader scientific community.\u003c/p\u003e","manuscriptTitle":"ENGINE: A Scalable Equivariant Graph Network Framework for Precise Protein Function Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-16 06:35:08","doi":"10.21203/rs.3.rs-6961427/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-24T13:13:56+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-26T00:02:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"252661288629777241979218485116909695851","date":"2025-07-19T15:02:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-16T06:40:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"232017473348215423869700465148467161797","date":"2025-07-14T14:01:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"139046626180475274303038607573639321093","date":"2025-07-14T13:56:40+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-14T13:41:26+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-27T15:07:55+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-24T05:47:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Genome Biology","date":"2025-06-24T04:31:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"genome-biology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gbio","sideBox":"Learn more about [Genome Biology](https://genomebiology.biomedcentral.com/)","snPcode":"13059","submissionUrl":"https://submission.springernature.com/new-submission/13059/3","title":"Genome Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b677e5d7-db07-4f0c-b7aa-1e93c5dc92bb","owner":[],"postedDate":"July 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-01T16:05:41+00:00","versionOfRecord":{"articleIdentity":"rs-6961427","link":"https://doi.org/10.1186/s13059-025-03886-y","journal":{"identity":"genome-biology","isVorOnly":false,"title":"Genome Biology"},"publishedOn":"2025-11-29 15:58:45","publishedOnDateReadable":"November 29th, 2025"},"versionCreatedAt":"2025-07-16 06:35:08","video":"","vorDoi":"10.1186/s13059-025-03886-y","vorDoiUrl":"https://doi.org/10.1186/s13059-025-03886-y","workflowStages":[]},"version":"v1","identity":"rs-6961427","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6961427","identity":"rs-6961427","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}