The influence of reduced amino acid alphabets on prediction orthologous protein thermostability

The influence of reduced amino acid alphabets on prediction orthologous protein thermostability | 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 The influence of reduced amino acid alphabets on prediction orthologous protein thermostability Yuxin Jiang, Xiaoyu Yuan, Shizhe Zheng, Silin Luo, Haidong Chen, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5804597/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Apr, 2025 Read the published version in Biologia → Version 1 posted 5 You are reading this latest preprint version Abstract Sequence feature plays a vital role in determining protein thermostability. Considering the advantages of reduced amino acid alphabets (RAAs) in reducing data complexity and retaining key sequence information, we evaluate the performance of 672 RAAs on prediction orthologous protein thermostability. By calculating the Amino Acid Composition, Dipeptide Composition, Tripeptide Composition of reduced sequence features and building random forest regression models, we find that 10 RAAs based on the fuzzy clustering algorithm are suitable to predict the thermostability difference of orthologous protein pairs and significantly improve the prediction efficiency. Further, the melting temperature difference Δ T m caused by point mutation is predicted, and it is found that the RAA of EQ-H-K-DN-IL-P-T-FY-M-R-S-W-A-C-G-V could fit the tiny thermostability change caused by point mutation. Our work showcases that the reduction methods based on fuzzy clustering can effectively retain the key sequence features that affect protein thermostability, resulting in reducing the computational complexity and increasing the prediction accuracy. Reduced amino acid alphabet Thermostability Sequence feature Fuzzy clustering Orthologous protein Full Text Supplementary Files ESM1.xlsx ESM2.xlsx ESM3.xlsx ESM4.xlsx ESM5.xlsx Cite Share Download PDF Status: Published Journal Publication published 09 Apr, 2025 Read the published version in Biologia → Version 1 posted Editorial decision: Major revisions 05 Feb, 2025 Reviewers agreed at journal 22 Jan, 2025 Reviewers invited by journal 22 Jan, 2025 Editor assigned by journal 15 Jan, 2025 First submitted to journal 13 Jan, 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-5804597","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":405588739,"identity":"fb1f5e91-fed3-4f01-b823-51e40411689e","order_by":0,"name":"Yuxin Jiang","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Yuxin","middleName":"","lastName":"Jiang","suffix":""},{"id":405588740,"identity":"6580180f-b1d6-497f-9452-a2ba9bd962c4","order_by":1,"name":"Xiaoyu Yuan","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoyu","middleName":"","lastName":"Yuan","suffix":""},{"id":405588741,"identity":"6e997dbf-5260-4204-8015-0971d5376d3b","order_by":2,"name":"Shizhe Zheng","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Shizhe","middleName":"","lastName":"Zheng","suffix":""},{"id":405588742,"identity":"81c30ed1-0012-4697-a03a-b5e9097ad5e8","order_by":3,"name":"Silin Luo","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Silin","middleName":"","lastName":"Luo","suffix":""},{"id":405588743,"identity":"5d61d8aa-de8c-4aa3-8273-108cab737ac8","order_by":4,"name":"Haidong Chen","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Haidong","middleName":"","lastName":"Chen","suffix":""},{"id":405588744,"identity":"0d425015-e6a8-460f-938e-11c728f02592","order_by":5,"name":"Yanrui Ding","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYJACiQQGBjnGZoSAAVFajEnUAsSJDUgC+LUY3D7AeOPhjtr05nbmZw+/7rDLY2Bv3ibBUHMHt5ZzCcwWiWeO5zY2s5kby55JLmbgOVYmwXDsGW4tZxjYJBLbjgG1MJhJS7YxJzZI5JhJMDYcJqglnbGZ/RtQS31ig/wborTUJDA285hJfmw7DLSFB78WyTMMQL+0HTBsbOYpk2ZsO57YxpNWbJFwDLcWvjMMjDd/ttXJG/Yf3yb5s606sZ/98MYbH2pwa1E4wP8BSB1mMGxgYGDmATLZQMIJODUwMMg3gKk6BnkgyfgDj8pRMApGwSgYuQAAY/RSguOCDcQAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-8383-6900","institution":"Jiangnan University","correspondingAuthor":true,"prefix":"","firstName":"Yanrui","middleName":"","lastName":"Ding","suffix":""}],"badges":[],"createdAt":"2025-01-10 14:48:52","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5804597/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5804597/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11756-025-01935-2","type":"published","date":"2025-04-09T16:04:50+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":80558145,"identity":"624471e3-8284-474d-84b5-0824812fee5a","added_by":"auto","created_at":"2025-04-14 16:07:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":555183,"visible":true,"origin":"","legend":"","description":"","filename":"final4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5804597/v1_covered_cc277d98-765b-4b67-ba2b-11357323c347.pdf"},{"id":74694865,"identity":"b128d046-d808-479d-8024-67769fde3dcc","added_by":"auto","created_at":"2025-01-24 19:54:48","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":41614,"visible":true,"origin":"","legend":"","description":"","filename":"ESM1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5804597/v1/af81537c3a0488d5b9ed79cc.xlsx"},{"id":74694867,"identity":"7c8758a3-5757-4165-9f68-296919c8fa7c","added_by":"auto","created_at":"2025-01-24 19:54:48","extension":"xlsx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":343912,"visible":true,"origin":"","legend":"","description":"","filename":"ESM2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5804597/v1/0f0f0a628ff4f6bd18970423.xlsx"},{"id":74695081,"identity":"19fe4f83-48bb-4446-95fe-b953fe19e3ee","added_by":"auto","created_at":"2025-01-24 20:02:48","extension":"xlsx","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":153830,"visible":true,"origin":"","legend":"","description":"","filename":"ESM3.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5804597/v1/7866ed29e66c82e3d225f7e6.xlsx"},{"id":74694869,"identity":"a0cbee57-2111-4f69-9f2a-1355b22d3b22","added_by":"auto","created_at":"2025-01-24 19:54:48","extension":"xlsx","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":48931,"visible":true,"origin":"","legend":"","description":"","filename":"ESM4.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5804597/v1/3d816f60754e9b2ebdb909ab.xlsx"},{"id":74694870,"identity":"248b4bdb-ce9f-48ce-8413-fa898a3463a4","added_by":"auto","created_at":"2025-01-24 19:54:48","extension":"xlsx","order_by":10,"title":"","display":"","copyAsset":false,"role":"supplement","size":49269,"visible":true,"origin":"","legend":"","description":"","filename":"ESM5.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5804597/v1/825754e840597bbeaa0a3cee.xlsx"}],"financialInterests":"","formattedTitle":"The influence of reduced amino acid alphabets on prediction orthologous protein thermostability","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"biologia","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"biol","sideBox":"Learn more about [Biologia](http://link.springer.com/journal/11756)","snPcode":"11756","submissionUrl":"https://www.editorialmanager.com/biol/default2.aspx","title":"Biologia","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Reduced amino acid alphabet, Thermostability, Sequence feature, Fuzzy clustering, Orthologous protein","lastPublishedDoi":"10.21203/rs.3.rs-5804597/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5804597/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSequence feature plays a vital role in determining protein thermostability. Considering the advantages of reduced amino acid alphabets (RAAs) in reducing data complexity and retaining key sequence information, we evaluate the performance of 672 RAAs on prediction orthologous protein thermostability. By calculating the Amino Acid Composition, Dipeptide Composition, Tripeptide Composition of reduced sequence features and building random forest regression models, we find that 10 RAAs based on the fuzzy clustering algorithm are suitable to predict the thermostability difference of orthologous protein pairs and significantly improve the prediction efficiency. Further, the melting temperature difference Δ\u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003em\u003c/em\u003e\u003c/sub\u003e caused by point mutation is predicted, and it is found that the RAA of EQ-H-K-DN-IL-P-T-FY-M-R-S-W-A-C-G-V could fit the tiny thermostability change caused by point mutation. Our work showcases that the reduction methods based on fuzzy clustering can effectively retain the key sequence features that affect protein thermostability, resulting in reducing the computational complexity and increasing the prediction accuracy.\u003c/p\u003e","manuscriptTitle":"The influence of reduced amino acid alphabets on prediction orthologous protein thermostability","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-24 19:54:43","doi":"10.21203/rs.3.rs-5804597/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revisions","date":"2025-02-05T14:32:09+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2025-01-22T12:22:58+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-01-22T11:45:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-01-15T13:34:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Biologia","date":"2025-01-13T10:51:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"biologia","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"biol","sideBox":"Learn more about [Biologia](http://link.springer.com/journal/11756)","snPcode":"11756","submissionUrl":"https://www.editorialmanager.com/biol/default2.aspx","title":"Biologia","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3ed88cba-96cb-4a9e-ae1d-0eebab5894fb","owner":[],"postedDate":"January 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-04-14T16:06:07+00:00","versionOfRecord":{"articleIdentity":"rs-5804597","link":"https://doi.org/10.1007/s11756-025-01935-2","journal":{"identity":"biologia","isVorOnly":false,"title":"Biologia"},"publishedOn":"2025-04-09 16:04:50","publishedOnDateReadable":"April 9th, 2025"},"versionCreatedAt":"2025-01-24 19:54:43","video":"","vorDoi":"10.1007/s11756-025-01935-2","vorDoiUrl":"https://doi.org/10.1007/s11756-025-01935-2","workflowStages":[]},"version":"v1","identity":"rs-5804597","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5804597","identity":"rs-5804597","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}