Defining Peptides in ChEBI

Defining Peptides in ChEBI | 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 Defining Peptides in ChEBI Simon Flügel, Till Mossakowski, Fabian Neuhaus, Erik Pfanenstiel, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7767033/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 May, 2026 Read the published version in Journal of Cheminformatics → Version 1 posted 10 You are reading this latest preprint version Abstract Modern biochemistry is producing vast amounts of chemical knowledge. Ontologies, such as the Chemical Entities of Biological Interest (ChEBI) ontology, can help organising this knowledge. With manual classification alone however, ontologies cannot keep up with the growth of their domain. In this work, we propose a novel taxonomy of 67 classes related to peptides, a large branch in ChEBI with nearly 15,000 compounds. The existing natural language definitions in ChEBI have been expanded and specified more precisely. These natural language definitions are accompanied by a logical axiomatisation in monadic second-order logic (MSOL). To use the axiomatisation for automated classification, a methodology has been developed that translates monadic second-order definitions first into partial first-order definitions and finally into an algorithmic classification. This connects three aspects important to ontological definitions: They reflect the opinions of experts, they are unambiguous, and they can be checked automatically. In our evaluation, we compare the results of our classification to the current taxonomy of ChEBI. This reveals both potential inconsistencies in ChEBI as well as areas that might benefit from automated extensions. We also evaluate our natural-language definitions in an expert survey. Scientific Contribution: This work provides precise natural-language definitions of 14 current ChEBI-classes as well as 53 new peptide-related classes. These definitions are formalised in MSOL and come with an efficient implementation that allows for large-scale molecule classification, including a full classification of ChEBI and PubChem. monadic second-order logic ChEBI peptides Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 May, 2026 Read the published version in Journal of Cheminformatics → Version 1 posted Editorial decision: Revision requested 05 Feb, 2026 Reviews received at journal 05 Feb, 2026 Reviewers agreed at journal 19 Jan, 2026 Reviewers agreed at journal 04 Jan, 2026 Reviewers agreed at journal 09 Dec, 2025 Reviewers agreed at journal 20 Nov, 2025 Reviewers invited by journal 11 Nov, 2025 Editor assigned by journal 17 Oct, 2025 Submission checks completed at journal 17 Oct, 2025 First submitted to journal 02 Oct, 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-7767033","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":577119369,"identity":"0ca15447-52ad-4382-9228-d2b41bcc5fc2","order_by":0,"name":"Simon Flügel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYDACZjApJwOmHlSAKQNitBjzgKmEM8RoYUDWkthGhBb5du7ExwUMBjwGx9svPkicd1hOvoF54wN8WgwO8242ngHScuZMsUHitsPGBgfYivFaY8DMu02ah+EPj8GNnDQJoJbEDQw8ZhJ4HdYM1gK05f6b9B+Jcw4nzm/gMf+B1zOHYVpusB9jSGw4nNhwgMcMrw6wX3gMDHgkz+QwSyQcSzc2OMxWjN9h/Wc3PuapMJDjO3784YcPNdZy8u3NGz/gtQZiF4jggYYTM2H1MMD+gHi1o2AUjIJRMKIAANl3Q+cfxPNdAAAAAElFTkSuQmCC","orcid":"","institution":"Osnabrück University","correspondingAuthor":true,"prefix":"","firstName":"Simon","middleName":"","lastName":"Flügel","suffix":""},{"id":577119370,"identity":"4d054e36-f517-4dc4-8ff5-b18edc84ec86","order_by":1,"name":"Till Mossakowski","email":"","orcid":"","institution":"Osnabrück University","correspondingAuthor":false,"prefix":"","firstName":"Till","middleName":"","lastName":"Mossakowski","suffix":""},{"id":577119371,"identity":"34c6c1cc-a1ab-4389-85a3-a81421c2bdca","order_by":2,"name":"Fabian Neuhaus","email":"","orcid":"","institution":"Otto-von-Guericke University Magdeburg","correspondingAuthor":false,"prefix":"","firstName":"Fabian","middleName":"","lastName":"Neuhaus","suffix":""},{"id":577119372,"identity":"d14815ec-9388-4853-b531-03e8b59429c2","order_by":3,"name":"Erik Pfanenstiel","email":"","orcid":"","institution":"Otto-von-Guericke University Magdeburg","correspondingAuthor":false,"prefix":"","firstName":"Erik","middleName":"","lastName":"Pfanenstiel","suffix":""},{"id":577119373,"identity":"bedd041e-77c7-482b-b9a2-f2a59e0d689c","order_by":4,"name":"Martin Glauer","email":"","orcid":"","institution":"Otto-von-Guericke University Magdeburg","correspondingAuthor":false,"prefix":"","firstName":"Martin","middleName":"","lastName":"Glauer","suffix":""},{"id":577119374,"identity":"94bb2a47-03fe-4004-915b-1f061ec40b33","order_by":5,"name":"Edgar Haak","email":"","orcid":"","institution":"Otto-von-Guericke University Magdeburg","correspondingAuthor":false,"prefix":"","firstName":"Edgar","middleName":"","lastName":"Haak","suffix":""},{"id":577119375,"identity":"fcc908b0-8a9f-49e5-9e1d-b73c22b330d5","order_by":6,"name":"Adnan Malik","email":"","orcid":"","institution":"European Bioinformatics Institute","correspondingAuthor":false,"prefix":"","firstName":"Adnan","middleName":"","lastName":"Malik","suffix":""},{"id":577119376,"identity":"40bab9be-e15c-4686-8cc0-35f79cb34dfd","order_by":7,"name":"Noel M O'Boyle","email":"","orcid":"","institution":"European Bioinformatics Institute","correspondingAuthor":false,"prefix":"","firstName":"Noel","middleName":"M","lastName":"O'Boyle","suffix":""}],"badges":[],"createdAt":"2025-10-02 13:53:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7767033/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7767033/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13321-026-01196-4","type":"published","date":"2026-05-02T15:57:29+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":109069203,"identity":"a466d7dd-46df-4923-86c8-ed30e494c891","added_by":"auto","created_at":"2026-05-12 10:21:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1828153,"visible":true,"origin":"","legend":"","description":"","filename":"DefiningPeptidesinChEBIJCIsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7767033/v1_covered_1466595a-cf4f-4c33-8475-1121cb0876ed.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Defining Peptides in ChEBI","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":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"monadic second-order logic, ChEBI, peptides","lastPublishedDoi":"10.21203/rs.3.rs-7767033/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7767033/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Modern biochemistry is producing vast amounts of chemical knowledge. Ontologies, such as the Chemical Entities of Biological Interest (ChEBI) ontology, can help organising this knowledge. With manual classification alone however, ontologies cannot keep up with the growth of their domain.\nIn this work, we propose a novel taxonomy of 67 classes related to peptides, a large branch in ChEBI with nearly 15,000 compounds. The existing natural language definitions in ChEBI have been expanded and specified more precisely. These natural language definitions are accompanied by a logical axiomatisation in monadic second-order logic (MSOL). To use the axiomatisation for automated classification, a methodology has been developed that translates monadic second-order definitions first into partial first-order definitions and finally into an algorithmic classification.\nThis connects three aspects important to ontological definitions: They reflect the opinions of experts, they are unambiguous, and they can be checked automatically. In our evaluation, we compare the results of our classification to the current taxonomy of ChEBI. This reveals both potential inconsistencies in ChEBI as well as areas that might benefit from automated extensions. We also evaluate our natural-language definitions in an expert survey.\nScientific Contribution: This work provides precise natural-language definitions of 14 current ChEBI-classes as well as 53 new peptide-related classes. These definitions are formalised in MSOL and come with an efficient implementation that allows for large-scale molecule classification, including a full classification of ChEBI and PubChem.\n","manuscriptTitle":"Defining Peptides in ChEBI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-28 03:27:45","doi":"10.21203/rs.3.rs-7767033/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-05T16:35:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-05T08:43:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"188174851604820153917373615569516753553","date":"2026-01-19T23:44:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"203332017236565797769755369623378118241","date":"2026-01-04T19:31:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"171230877397731508335938458044272601748","date":"2025-12-09T09:04:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"252476784548119125238121854081197970317","date":"2025-11-20T07:41:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-11T12:55:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-17T12:30:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-17T12:27:36+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Cheminformatics","date":"2025-10-02T13:49:16+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"4ec7031e-ccbf-4e45-9535-4ac83dca6e08","owner":[],"postedDate":"January 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T09:54:40+00:00","versionOfRecord":{"articleIdentity":"rs-7767033","link":"https://doi.org/10.1186/s13321-026-01196-4","journal":{"identity":"journal-of-cheminformatics","isVorOnly":false,"title":"Journal of Cheminformatics"},"publishedOn":"2026-05-02 15:57:29","publishedOnDateReadable":"May 2nd, 2026"},"versionCreatedAt":"2026-01-28 03:27:45","video":"","vorDoi":"10.1186/s13321-026-01196-4","vorDoiUrl":"https://doi.org/10.1186/s13321-026-01196-4","workflowStages":[]},"version":"v1","identity":"rs-7767033","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7767033","identity":"rs-7767033","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}