Macon: Enhance Protein Mutation Representation using Contrastive Learning with Effect Prediction on Protein–protein Interactions

Macon: Enhance Protein Mutation Representation using Contrastive Learning with Effect Prediction on Protein–protein Interactions | 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 Macon: Enhance Protein Mutation Representation using Contrastive Learning with Effect Prediction on Protein–protein Interactions Weihao Li, Zhe Liu, Guan Ning Lin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7469880/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Mutations in protein sequences can significantly alter protein-protein interactions (PPIs), leading to diverse functional outcomes relevant to disease mechanisms and therapeutic targeting. While existing computational approaches predominantly estimate changes in binding free energy in PPIs, they often failed to capture categorical effects such as complete disruption of interaction or gain of interaction. Categorical models like MIPPI addresses this by predicting mutation effects into functional classes, yet their reliance on one-hot encoding limits the ability to capture detailed sequence information. Here, we propose Macon, a two-stage deep-learning framework that integrates contrastive pretraining and protein language model (pLM) embeddings to enhance mutation-sensitive sequence representation. In the first stage, Macon leverages contrastive learning to distinguish wild-type and mutant sequences in a context-independent manner; in the second, it integrates both contrastive embeddings and pLM-derived features to perform multi-class classification of PPI mutation effects. Evaluated on a curated IMEx dataset with 10,119 annotated single-point mutations, Macon achieves state-of-the-art performance with an overall accuracy of 0.73, outperforming baseline methods including MIPPI and embedding-only classifiers. Our results highlight the benefit of contrastive representation learning in capturing subtle mutational impacts and demonstrate Macon’s utility as a robust and generalizable tool for functional variant interpretation in protein interaction networks. Mutation effect prediction contrastive learning protein language model deep learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 23 Oct, 2025 Reviews received at journal 21 Oct, 2025 Reviews received at journal 13 Oct, 2025 Reviewers agreed at journal 26 Sep, 2025 Reviewers agreed at journal 26 Sep, 2025 Reviewers invited by journal 26 Sep, 2025 Editor assigned by journal 26 Sep, 2025 Editor invited by journal 24 Sep, 2025 Submission checks completed at journal 24 Sep, 2025 First submitted to journal 24 Sep, 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-7469880","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":526591309,"identity":"e4df49a8-c14f-410c-9baa-1f07fd6a30b0","order_by":0,"name":"Weihao Li","email":"","orcid":"","institution":"Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Weihao","middleName":"","lastName":"Li","suffix":""},{"id":526591310,"identity":"27e61ae5-0aa6-4e81-9916-caba6797546a","order_by":1,"name":"Zhe Liu","email":"","orcid":"","institution":"Department of Computer Science and Engineering, East China University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhe","middleName":"","lastName":"Liu","suffix":""},{"id":526591311,"identity":"214bdf64-7ce6-4edb-905e-0e9030ecb1d2","order_by":2,"name":"Guan Ning Lin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYDACZiBkYLDgYWBvYDAAixwgTosEDwPPAQaDA0RpYYBoAaIEqGpCWszZmR8bft0hIWMu+fxB8cc2Bjm+GwmMnwvwaLFsZjNOlj0jwWM5O8fA4GAbg7HkjQRm6Rl4tBgc5mE+LNkmwWNwO4cBpCVxw40ENmYeorTcPP4ApKWeKC2JH0FabjCAHZZgQFgLm7ExI0jLGaBfzpyTMJx55mGzNF4t5w8/lvzZZmNvcPz4M4OKMht5vuPJBz/j0wICMGewGYAjiIGxgYAGoJIfUK0PCCodBaNgFIyCEQkAd8NHtTYq+nwAAAAASUVORK5CYII=","orcid":"","institution":"Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong University","correspondingAuthor":true,"prefix":"","firstName":"Guan","middleName":"Ning","lastName":"Lin","suffix":""}],"badges":[],"createdAt":"2025-08-27 09:08:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7469880/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7469880/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93173140,"identity":"ce8df7e8-d467-42de-b02b-6501f02ecbee","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5413,"visible":true,"origin":"","legend":"","description":"","filename":"eef9a12a44b6492d92c845be80c33fd6.json","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/434294cccf2cf2010900cb39.json"},{"id":93173144,"identity":"83bc15e0-b6da-4231-9baf-bdd3c4aef3ed","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86352,"visible":true,"origin":"","legend":"","description":"","filename":"eef9a12a44b6492d92c845be80c33fd61enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/0cc3ea83ab6c9ba9f754c2f5.xml"},{"id":93173119,"identity":"c797a3c8-dfab-4411-8d47-db31de0342ee","added_by":"auto","created_at":"2025-10-09 20:08:14","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1943289,"visible":true,"origin":"","legend":"","description":"","filename":"MaconEnhanceProteinMutationRepresentationusingContrastiveLearningwithEffectPredictiononProteinproteinInteractions.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/dedc2f350096401a50ab2b43.pdf"},{"id":93173138,"identity":"fa45bcd5-2e93-4252-95fb-90ed6c60ca6f","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"eps","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/6495d33976d671df35b256ae.eps"},{"id":93173922,"identity":"4a69d084-00e1-4eae-bf13-2567d54c2a86","added_by":"auto","created_at":"2025-10-09 20:16:16","extension":"eps","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/b55065eb1143100d5aceafb5.eps"},{"id":93173134,"identity":"f9b1979b-c568-4ba2-b8b5-400a51522b88","added_by":"auto","created_at":"2025-10-09 20:08:15","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":488430,"visible":true,"origin":"","legend":"","description":"","filename":"maconfigure.png","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/cf1e66b34b0867bc4d6b8b48.png"},{"id":93173124,"identity":"3d7f1c82-4859-4a9f-bc60-2e5042f70aeb","added_by":"auto","created_at":"2025-10-09 20:08:14","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1460248,"visible":true,"origin":"","legend":"","description":"","filename":"maconfigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/59c8b53bf19f0a11a99df6aa.png"},{"id":93173145,"identity":"006881c8-62d8-4ce2-8230-21b9a2e6ac40","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":210429,"visible":true,"origin":"","legend":"","description":"","filename":"reviewersresponse.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/98ff25bb6a42979a49113126.pdf"},{"id":93173128,"identity":"5c0e6cec-8b2d-494b-b974-f00f4448aa1d","added_by":"auto","created_at":"2025-10-09 20:08:15","extension":"bst","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/c46b7496b8e5891c3a086d3a.bst"},{"id":93173151,"identity":"979bbf66-8f56-4019-936c-d1e2045b3d1f","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"bst","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/a16c1fe10ec7bb3c8c201f66.bst"},{"id":93173126,"identity":"872e60ce-546f-44d3-8b94-f338fcb4621f","added_by":"auto","created_at":"2025-10-09 20:08:15","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/00ba8ab348e24836c790a57c.pdf"},{"id":93173161,"identity":"a2d4c3a2-0122-4bc3-8fa5-89dfde7e878f","added_by":"auto","created_at":"2025-10-09 20:08:17","extension":"bst","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/23a9ccd1bb40a4fbfdf5c11f.bst"},{"id":93173921,"identity":"a9b32427-d95f-4ba9-b92f-12f6d876e6da","added_by":"auto","created_at":"2025-10-09 20:16:15","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/32186be0466f7a0e9460165e.bst"},{"id":93173153,"identity":"dc0cbfad-3dec-47ac-a0f5-1cf66ce97c63","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"cls","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/17c21f9c2752263490c86096.cls"},{"id":93173924,"identity":"99c4d289-7eb3-469b-a0df-034e6b7edac4","added_by":"auto","created_at":"2025-10-09 20:16:17","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/c89fb3cf2c3c9892b4ba6c8f.bst"},{"id":93173131,"identity":"a202bb73-e77f-46a0-a90a-8dc8af8ae14d","added_by":"auto","created_at":"2025-10-09 20:08:15","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/2d08df690633fa3efc2e41cc.bst"},{"id":93173148,"identity":"2892e130-030d-4def-a960-95473478a001","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/682b21e1b2f78f46d8990c23.bst"},{"id":93173149,"identity":"1a799b64-7369-4b48-9358-ba7708d2bbf2","added_by":"auto","created_at":"2025-10-09 20:08:16","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/9b32f62ea713f19a8eec4acf.bst"},{"id":93173132,"identity":"130bd920-a0dc-484c-9580-e5d750350c26","added_by":"auto","created_at":"2025-10-09 20:08:15","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/db1c4317ef8378f88d9d83da.bst"},{"id":93173154,"identity":"77f0ddaf-a95f-4db0-912d-1632513ff934","added_by":"auto","created_at":"2025-10-09 20:08:17","extension":"pdf","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/4633d2ba914387c6734aa987.pdf"},{"id":93173162,"identity":"14683e7b-a806-4114-92a0-dec3804caaab","added_by":"auto","created_at":"2025-10-09 20:08:17","extension":"xml","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115664,"visible":true,"origin":"","legend":"","description":"","filename":"eef9a12a44b6492d92c845be80c33fd61structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/239fb518302a59089e3b52f4.xml"},{"id":93173133,"identity":"7a7f63d6-8f6b-4347-8a92-54dbf99bf4b1","added_by":"auto","created_at":"2025-10-09 20:08:15","extension":"html","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96225,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1/6fe72b66c99481757cfcb7d9.html"},{"id":93174277,"identity":"0a6b6042-7138-49aa-b5d1-d16c53573e4d","added_by":"auto","created_at":"2025-10-09 20:24:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1073812,"visible":true,"origin":"","legend":"","description":"","filename":"MaconEnhanceProteinMutationRepresentationusingContrastiveLearningwithEffectPredictiononProteinproteinInteractions.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7469880/v1_covered_bd9d7fbb-2093-4afe-9c34-534a4a624b8f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Macon: Enhance Protein Mutation Representation using Contrastive Learning with Effect Prediction on Protein–protein Interactions","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Mutation effect prediction, contrastive learning, protein language model, deep learning","lastPublishedDoi":"10.21203/rs.3.rs-7469880/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7469880/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMutations in protein sequences can significantly alter protein-protein interactions (PPIs), leading to diverse functional outcomes relevant to disease mechanisms and therapeutic targeting. While existing computational approaches predominantly estimate changes in binding free energy in PPIs, they often failed to capture categorical effects such as complete disruption of interaction or gain of interaction. Categorical models like MIPPI addresses this by predicting mutation effects into functional classes, yet their reliance on one-hot encoding limits the ability to capture detailed sequence information. Here, we propose Macon, a two-stage deep-learning framework that integrates contrastive pretraining and protein language model (pLM) embeddings to enhance mutation-sensitive sequence representation. In the first stage, Macon leverages contrastive learning to distinguish wild-type and mutant sequences in a context-independent manner; in the second, it integrates both contrastive embeddings and pLM-derived features to perform multi-class classification of PPI mutation effects. Evaluated on a curated IMEx dataset with 10,119 annotated single-point mutations, Macon achieves state-of-the-art performance with an overall accuracy of 0.73, outperforming baseline methods including MIPPI and embedding-only classifiers. Our results highlight the benefit of contrastive representation learning in capturing subtle mutational impacts and demonstrate Macon\u0026rsquo;s utility as a robust and generalizable tool for functional variant interpretation in protein interaction networks.\u003c/p\u003e","manuscriptTitle":"Macon: Enhance Protein Mutation Representation using Contrastive Learning with Effect Prediction on Protein–protein Interactions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-09 20:07:35","doi":"10.21203/rs.3.rs-7469880/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-23T11:39:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-21T12:15:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-13T14:45:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"330481701306078494290491529952474245405","date":"2025-09-26T14:30:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"196465459872481107768415016562405349337","date":"2025-09-26T13:21:12+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-26T12:44:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-26T12:37:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-24T11:36:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-24T08:51:27+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Bioinformatics","date":"2025-09-24T08:48:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"01f16cc3-7be3-4588-8b90-0650fc71bb0d","owner":[],"postedDate":"October 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-19T20:53:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-09 20:07:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7469880","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7469880","identity":"rs-7469880","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}