Oncogene and Tumor Suppressor Gene Classification Using Protein Language Model Embeddings and a Novel Optimization Strategy

Oncogene and Tumor Suppressor Gene Classification Using Protein Language Model Embeddings and a Novel Optimization Strategy | 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 Oncogene and Tumor Suppressor Gene Classification Using Protein Language Model Embeddings and a Novel Optimization Strategy Ahmet Emir Şaşmazlar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9066725/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 Background : Recent advances in protein language models (PLMs) and deep representation learning have enabled the creation of highly informative embeddings of protein sequences. Accurate classification of oncogenes and tumor suppressor genes (TSGs) from these embeddings has the potential to reveal biologically meaningful patterns relevant to cancer biology. Methods : We compiled a balanced dataset of 304 cancer-related human proteins, including both oncogenes and TSGs, mapped to UniProt IDs. Protein sequence embeddings were generated using ESM, and dimensionality reduction was performed with Principal Component Analysis (PCA). A novel neural network training pipeline was implemented using our custom optimizer, PCAGroupAdam. Its performance was benchmarked against traditional optimizers (Adam, SGD, RMSprop) and a classical Random Forest classifier. Model evaluation employed cross-validation, ROC-AUC analysis, confusion matrices, and advanced explainable AI (SHAP) techniques. Statistical comparisons between models were performed using paired t-tests. Results : The PCAGroupAdam-based neural network outperformed all baselines, achieving an accuracy of 0.66 and an ROC-AUC of 0.70 on the full dataset. SHAP analysis revealed that discriminative information was distributed across multiple embedding dimensions rather than concentrated in a single feature. Feature importance from both neural and tree-based models provided convergent insights. Statistical tests confirmed that PCAGroupAdam yielded significantly better performance than standard optimizers (p<0.05). Conclusions : Our results demonstrate that combining protein embeddings with a novel group-based optimizer provides improved classification of oncogenes and TSGs compared to standard approaches. The methodology is robust, reproducible, and extensible to larger protein datasets. This approach may contribute to a better understanding of cancer-related protein function and highlights the potential of explainable deep learning in computational oncology. Computational Biology Bioinformatics Oncology Artificial Intelligence and Machine Learning Full Text Additional Declarations The authors declare no competing interests. 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-9066725","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":602712034,"identity":"8c51843a-ecb7-404e-acec-ec1f989802ae","order_by":0,"name":"Ahmet Emir Şaşmazlar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYFACxgYogxnIqADRzA04FaNpATHOgLTARYixjrENxRDsgF/scNvHHzV10fz9Bxs/V86rjeZvB2r5UbENpxbJ2YnNs3mOHc6dceBgs+TZbcdzZxxmbGDsOXMbpxaD24nNzAxsB3IbDjY2SDZuO5bbANTCzNiGW4s9UAvjj391ufMPMzb/bJxzDMTAr8VAOrGZgbeNOXfDMcY2ycaGmtwNhLRIgBzG23c4d+MZxjbLhmMHcjcCtRzE5xf+2emPGX98q8udd/7w4ZsNNWDGwQc/KnBrQQeHweQBotUDQR0pikfBKBgFo2CEAAAwl2ILC9TlnAAAAABJRU5ErkJggg==","orcid":"","institution":"Hacettepe University","correspondingAuthor":true,"prefix":"","firstName":"Ahmet","middleName":"Emir","lastName":"Şaşmazlar","suffix":""}],"badges":[],"createdAt":"2026-03-08 22:16:50","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9066725/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9066725/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104406271,"identity":"17d4b8a5-102b-4379-be42-3c2b90cc72fb","added_by":"auto","created_at":"2026-03-11 12:25:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":770264,"visible":true,"origin":"","legend":"","description":"","filename":"proteinembeddings.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9066725/v1_covered_936ef021-d72b-4529-bcae-9ff2be8cf38b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eOncogene and Tumor Suppressor Gene Classification Using Protein\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLanguage Model Embeddings and a Novel Optimization Strategy\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Hacettepe University","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-9066725/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9066725/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground\u003c/strong\u003e: Recent advances in protein language models (PLMs) and deep representation learning have enabled the creation of highly informative embeddings of protein sequences. Accurate classification of oncogenes and tumor suppressor genes (TSGs) from these embeddings has the potential to reveal biologically meaningful patterns relevant to cancer biology.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e: We compiled a balanced dataset of 304 cancer-related human proteins, including both oncogenes and TSGs, mapped to UniProt IDs. Protein sequence embeddings were generated using ESM, and dimensionality reduction was performed with Principal Component Analysis (PCA). A novel neural network training pipeline was implemented using our custom optimizer, PCAGroupAdam. Its performance was benchmarked against traditional optimizers (Adam, SGD, RMSprop) and a classical Random Forest classifier. Model evaluation employed cross-validation, ROC-AUC analysis, confusion matrices, and advanced explainable AI (SHAP) techniques. Statistical comparisons between models were performed using paired t-tests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: The PCAGroupAdam-based neural network outperformed all baselines, achieving an accuracy of 0.66 and an ROC-AUC of 0.70 on the full dataset. SHAP analysis revealed that discriminative information was distributed across multiple embedding dimensions rather than concentrated in a single feature. Feature importance from both neural and tree-based models provided convergent insights. Statistical tests confirmed that PCAGroupAdam yielded significantly better performance than standard optimizers (p\u0026lt;0.05).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions\u003c/strong\u003e: Our results demonstrate that combining protein embeddings with a novel group-based optimizer provides improved classification of oncogenes and TSGs compared to standard approaches. The methodology is robust, reproducible, and extensible to larger protein datasets. This approach may contribute to a better understanding of cancer-related protein function and highlights the potential of explainable deep learning in computational oncology.\u003c/p\u003e","manuscriptTitle":"Oncogene and Tumor Suppressor Gene Classification Using Protein\nLanguage Model Embeddings and a Novel Optimization Strategy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-11 04:09:27","doi":"10.21203/rs.3.rs-9066725/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":"141b7d48-d670-4ed9-a341-01f0771c11c2","owner":[],"postedDate":"March 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64132379,"name":"Computational Biology"},{"id":64132380,"name":"Bioinformatics"},{"id":64132381,"name":"Oncology"},{"id":64132382,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-03-11T04:09:27+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-11 04:09:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9066725","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9066725","identity":"rs-9066725","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}