Practical Machine Learning Framework for Designing and Predicting C-Amidated Antimicrobial Peptides

Practical Machine Learning Framework for Designing and Predicting C-Amidated Antimicrobial Peptides | 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 Article Practical Machine Learning Framework for Designing and Predicting C-Amidated Antimicrobial Peptides Tu Le, Dang-Huy Le, Wenyi Li, Andrew Hung, Shadi Houshyar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7764304/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 Antimicrobial peptides (AMPs) offer promising alternatives to conventional antibiotics, yet most predictive models fail to account for chemical modifications that influence real-world efficacy. Among these, C-terminal amidation is a widely adopted and effective strategy that improves structural stability, membrane interaction, and protease resistance. To address the limitations of existing models, we developed an integrated framework for the design and prediction of C-terminal amidated AMPs targeting Escherichia coli. Our approach combined a design-oriented model, based on an interpretable Explainable Boosting Machine (EBM), which extracts actionable sequence-level design rules, alongside with a high-accuracy deployment model, built on a fine-tuned ESM2 deep learning architecture. The resulting tool, CAmidPred, enables both predictive classification and amino acid pattern analysis, with outputs validated against published alanine-scanning experiments. This dual-model approach bridges computational modeling and wet-lab discovery, offering a robust and practical pipeline for the rational design of the targeted AMP design pipelines Biological sciences/Biochemistry/Peptides Biological sciences/Computational biology and bioinformatics/Machine learning Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupportingInformation.zip Supplementary information files 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-7764304","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":526684128,"identity":"ca7d74e2-cbfe-4df6-9da9-55d9e9187068","order_by":0,"name":"Tu Le","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYHACxgMMFQwMbCAmDzHqQYoOMJwBamEjSQtjGwPEGqK02EskMBz4OO9eNJ98A+ODt20M8gYHCNkC1HJw5rbi3DY2BmbDuW0MhhuI0XKYd1sCSAubNG8bAyNxWv7OAWth/w3UYk+cFsYGiC3MQC2JhLWcedhwsOcYSEtis+SccxLJMwlpYW9PPvjgR01C7vzmwwc/vCmzse0jpAUY+Q3IDAmC6kfBKBgFo2AUEAEADsA8x1tw4l0AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-3552-8211","institution":"RMIT University","correspondingAuthor":true,"prefix":"","firstName":"Tu","middleName":"","lastName":"Le","suffix":""},{"id":526684129,"identity":"6fdaf2f4-66f8-414b-8d88-d1a5908a8349","order_by":1,"name":"Dang-Huy Le","email":"","orcid":"https://orcid.org/0009-0005-0765-4271","institution":"RMIT University","correspondingAuthor":false,"prefix":"","firstName":"Dang-Huy","middleName":"","lastName":"Le","suffix":""},{"id":526684130,"identity":"f1900681-7e93-42b7-aeaa-43952caceed3","order_by":2,"name":"Wenyi Li","email":"","orcid":"https://orcid.org/0000-0003-3584-0301","institution":"La Trobe University","correspondingAuthor":false,"prefix":"","firstName":"Wenyi","middleName":"","lastName":"Li","suffix":""},{"id":526684131,"identity":"25e95d57-6235-449b-8221-d81a44e20dca","order_by":3,"name":"Andrew Hung","email":"","orcid":"https://orcid.org/0000-0003-3569-2951","institution":"School of Science, RMIT University","correspondingAuthor":false,"prefix":"","firstName":"Andrew","middleName":"","lastName":"Hung","suffix":""},{"id":526684132,"identity":"51b4a6be-a4a7-4a42-be85-a8bce769c237","order_by":4,"name":"Shadi Houshyar","email":"","orcid":"https://orcid.org/0000-0003-0288-8608","institution":"RMIT University","correspondingAuthor":false,"prefix":"","firstName":"Shadi","middleName":"","lastName":"Houshyar","suffix":""}],"badges":[],"createdAt":"2025-10-02 06:55:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7764304/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7764304/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93105239,"identity":"9383bd76-2309-4ca7-bf11-2271597a9b5d","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3002365,"visible":true,"origin":"","legend":"","description":"","filename":"FinalDraftNatureCommunications.docx","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/22d667740759fe6ef88b26d3.docx"},{"id":93105236,"identity":"cb61b34e-da5d-436d-9f3f-0e3c1d8228b1","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6221,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS2578978.json","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/962dc6d7737507d088d63980.json"},{"id":93105477,"identity":"92934c52-eefb-4b01-8ae5-0df71773528f","added_by":"auto","created_at":"2025-10-09 06:34:40","extension":"zip","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12564424,"visible":true,"origin":"","legend":"","description":"","filename":"SupportingInformation.zip","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/cd66a9d885fe7c0b0a791c0f.zip"},{"id":93105237,"identity":"e6f18148-0d2b-4800-9ca2-5d63775f46b8","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":147731,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS25789780enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/f4f0f2b7a29319b0dfe05894.xml"},{"id":93105240,"identity":"6780da0d-ba21-4bd3-a75b-1771fde20ae1","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":451383,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/5c215e5fb9c6ecfd630854f7.png"},{"id":93106228,"identity":"a77c6643-6564-4925-9695-90830a9412c8","added_by":"auto","created_at":"2025-10-09 06:42:40","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":315293,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/5a49a2a0cc109d0c1cd221ad.png"},{"id":93105474,"identity":"cb428cac-544c-45e6-a30a-3418a0212066","added_by":"auto","created_at":"2025-10-09 06:34:40","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":439300,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/2736b770dc333a78cacd5fde.png"},{"id":93105243,"identity":"5bbdcab3-8234-4285-afa4-4c6a817056c9","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":351184,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/3167e5425fbc1ac282cf3213.jpeg"},{"id":93105473,"identity":"2b1ffc79-d2d1-42f7-937b-303f342ab9b2","added_by":"auto","created_at":"2025-10-09 06:34:40","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1318570,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/386894effd4d5a5b7cdf837e.jpeg"},{"id":93105244,"identity":"1c5daca1-5ac8-4aa0-94fd-efb924e88622","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":58688,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/78f715786a1a6dd0367ad428.png"},{"id":93105249,"identity":"2e85a596-b386-4c1f-9d66-63651dfa7d11","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42699,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/3f83ad143f6f578bf248a623.png"},{"id":93105245,"identity":"10046e96-3ec1-41ec-86c5-2f2bcc0890bf","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85766,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/05562c5061ea18438c31e1d0.png"},{"id":93105246,"identity":"2bd04b94-6106-46a4-b359-117b692e3334","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103454,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/f883a60e20e51dd4f400d460.png"},{"id":93105252,"identity":"21f668dd-cf88-4bf1-af2d-e5980501438a","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119597,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/5de0c0f9e13bf129a522326e.png"},{"id":93105250,"identity":"4bf8704c-d433-48f0-8769-f55ce3486b3d","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"xml","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":144619,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS25789780structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/d2f7d5c8fec0204b36a14517.xml"},{"id":93105251,"identity":"c271a501-e759-40fe-9425-d6674e25f574","added_by":"auto","created_at":"2025-10-09 06:26:40","extension":"html","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":161955,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/6bff7e6133fe7fbc0930bd6b.html"},{"id":93107696,"identity":"bc6237b6-e14a-47ad-b799-4d6dd1ef1ecc","added_by":"auto","created_at":"2025-10-09 06:58:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1375887,"visible":true,"origin":"","legend":"","description":"","filename":"FinalDraftNatureCommunications.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1_covered_8f443f82-e1a5-4b23-a662-cb903cbb16e2.pdf"},{"id":93105476,"identity":"2f0d6c3d-74c0-410a-9fa1-3634332521f5","added_by":"auto","created_at":"2025-10-09 06:34:40","extension":"zip","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12564424,"visible":true,"origin":"","legend":"Supplementary information files","description":"","filename":"SupportingInformation.zip","url":"https://assets-eu.researchsquare.com/files/rs-7764304/v1/db06b9dad2bb92d6aa64f94f.zip"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Practical Machine Learning Framework for Designing and Predicting C-Amidated Antimicrobial Peptides","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"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-7764304/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7764304/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAntimicrobial peptides (AMPs) offer promising alternatives to conventional antibiotics, yet most predictive models fail to account for chemical modifications that influence real-world efficacy. Among these, C-terminal amidation is a widely adopted and effective strategy that improves structural stability, membrane interaction, and protease resistance. To address the limitations of existing models, we developed an integrated framework for the design and prediction of C-terminal amidated AMPs targeting Escherichia coli. Our approach combined a design-oriented model, based on an interpretable Explainable Boosting Machine (EBM), which extracts actionable sequence-level design rules, alongside with a high-accuracy deployment model, built on a fine-tuned ESM2 deep learning architecture. The resulting tool, CAmidPred, enables both predictive classification and amino acid pattern analysis, with outputs validated against published alanine-scanning experiments. This dual-model approach bridges computational modeling and wet-lab discovery, offering a robust and practical pipeline for the rational design of the targeted AMP design pipelines\u003c/p\u003e","manuscriptTitle":"Practical Machine Learning Framework for Designing and Predicting C-Amidated Antimicrobial Peptides","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-09 06:26:35","doi":"10.21203/rs.3.rs-7764304/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":"9459d991-e9a9-42ba-a0b6-491b8a054789","owner":[],"postedDate":"October 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55983070,"name":"Biological sciences/Biochemistry/Peptides"},{"id":55983071,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2025-10-09T06:26:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-09 06:26:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7764304","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7764304","identity":"rs-7764304","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}