PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing

PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing | 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 Methods Article PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing Kaiyuan Liu, Yuzhen Ye, Haixu Tang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1341615/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Dec, 2023 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract The de novo peptide sequencing, which does not rely on a comprehensive target sequence database, provided us a way to identify novel peptides from tandem mass (MS/MS) spectra. However, current de novo sequencing algorithms suffer from lower accuracy and coverage, which hinders their applications in proteomics. In this paper, we present PepNet, a fully convolutional neural network (CNN) for high accuracy de novo peptide sequencing. It takes an MS/MS spectrum (represented as a high dimensional vector) as input, and outputs the optimal peptide sequence along with its confidence score. Our model was trained using a total of 30 million high-energy collisional dissociation (HCD) MS/MS spectra from multiple human peptide spectral libraries. The evaluation results show that PepNet significantly outperformed currently best-performing de novo sequencing algorithms (e.g. PointNovo and DeepNovo) at both peptide level accuracy and positional level accuracy. In addition, PepNet can sequence a large fraction of spectra that were not identified by database search engines, and thus could be used as a complementary tool of database search engines for peptide identification in proteomics. Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Suppliment.pdf Cite Share Download PDF Status: Published Journal Publication published 02 Dec, 2023 Read the published version in Nature Communications → 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-1341615","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Methods Article","associatedPublications":[],"authors":[{"id":84387281,"identity":"12012f88-17c0-410c-8f3c-8047053ad064","order_by":0,"name":"Kaiyuan Liu","email":"","orcid":"https://orcid.org/0000-0002-3404-2802","institution":"Indiana University Bloomington","correspondingAuthor":false,"prefix":"","firstName":"Kaiyuan","middleName":"","lastName":"Liu","suffix":""},{"id":84387282,"identity":"c12549f7-c5ad-4037-bd7f-c010e6faacd0","order_by":1,"name":"Yuzhen Ye","email":"","orcid":"","institution":"School of Informatics and Computing, Indiana University Bloomington","correspondingAuthor":false,"prefix":"","firstName":"Yuzhen","middleName":"","lastName":"Ye","suffix":""},{"id":84387283,"identity":"f05a84bc-5b2c-4479-b1e7-fd3d87fff9ec","order_by":2,"name":"Haixu Tang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYBACAwhlw8PAkNgAYR8gqIUZRKWRruUwECcwEKfFnP38wc8Fv87LmLMnN34uqGGQ47uRgF+LZU8ys/TMvts8lj0Pm6VnHGMwliSkxeBAMoM0b89tHoMbiQ3SPGwMiRsIajn/mPk3b885kJbm3zz/GOoJa7mRzCbN8+MASEubNG8bQ4IBYS2Pzax5G5J5DM48bLPm7ZMwnHnmASGHJT6+zfPHzt7geDqQ8c1Gnu84AVvAgLENzpQgQjkY/CFW4SgYBaNgFIxIAAB4+UcvYHPzeQAAAABJRU5ErkJggg==","orcid":"","institution":"Indiana University Bloomington","correspondingAuthor":true,"prefix":"","firstName":"Haixu","middleName":"","lastName":"Tang","suffix":""}],"badges":[],"createdAt":"2022-02-09 07:40:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1341615/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1341615/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-023-43010-x","type":"published","date":"2023-12-02T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":18324038,"identity":"98d086e8-10ad-4ac1-a4f5-afd764c318b9","added_by":"auto","created_at":"2022-02-17 14:33:44","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1578566,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1341615/v1_covered.pdf"},{"id":18324036,"identity":"9bc8da59-3254-4e1a-80c7-c92461cf26d0","added_by":"auto","created_at":"2022-02-17 14:33:35","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":633403,"visible":true,"origin":"","legend":"","description":"","filename":"Suppliment.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1341615/v1/97aff8c20c541cfb877e454c.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"\u003cp\u003ePepNet: A Fully Convolutional Neural Network for \u003cem\u003eDe novo \u003c/em\u003ePeptide Sequencing\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-1341615/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"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-1341615/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1341615/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The de novo peptide sequencing, which does not rely on a comprehensive target sequence database, provided us a way to identify novel peptides from tandem mass (MS/MS) spectra. However, current de novo sequencing algorithms suffer from lower accuracy and coverage, which hinders their applications in proteomics. In this paper, we present PepNet, a fully convolutional neural network (CNN) for high accuracy de novo peptide sequencing. It takes an MS/MS spectrum (represented as a high dimensional vector) as input, and outputs the optimal peptide sequence along with its confidence score. Our model was trained using a total of 30 million high-energy collisional dissociation (HCD) MS/MS spectra from multiple human peptide spectral libraries. The evaluation results show that PepNet significantly outperformed currently best-performing de novo sequencing algorithms (e.g. PointNovo and DeepNovo) at both peptide level accuracy and positional level accuracy. In addition, PepNet can sequence a large fraction of spectra that were not identified by database search engines, and thus could be used as a complementary tool of database search engines for peptide identification in proteomics.","manuscriptTitle":"PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-02-17 14:33:34","doi":"10.21203/rs.3.rs-1341615/v1","editorialEvents":[],"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":"ad0310ac-0791-46ba-86d3-9216fa08a078","owner":[],"postedDate":"February 17th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-12-03T08:31:12+00:00","versionOfRecord":{"articleIdentity":"rs-1341615","link":"https://doi.org/10.1038/s41467-023-43010-x","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2023-12-02 05:00:00","publishedOnDateReadable":"December 2nd, 2023"},"versionCreatedAt":"2022-02-17 14:33:34","video":"","vorDoi":"10.1038/s41467-023-43010-x","vorDoiUrl":"https://doi.org/10.1038/s41467-023-43010-x","workflowStages":[]},"version":"v1","identity":"rs-1341615","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1341615","identity":"rs-1341615","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}