Easing accessibility to mass spectrometry imaging using convolutional autoencoders for deriving hypoxia-associated peptide candidates from tumors

Easing accessibility to mass spectrometry imaging using convolutional autoencoders for deriving hypoxia-associated peptide candidates from tumors | 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 Easing accessibility to mass spectrometry imaging using convolutional autoencoders for deriving hypoxia-associated peptide candidates from tumors Verena Bitto, Pia Hönscheid, María José Besso, Christian Sperling, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3755587/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 May, 2024 Read the published version in npj Systems Biology and Applications → Version 1 posted 9 You are reading this latest preprint version Abstract Spatial omics data promise to reveal novel insights into the intratumoral heterogenity of biological parameters of cancer. Mass spectrometry imaging (MSI) allows to study spatially-resolved peptides, metabolites and lipids. Yet, in biomedical research the technology is rarely used for biomarker discovery. Like all spatial omics data, its high dimensionality and multicollinearity imposes special challenges for analysis. Additionally, mass spectrometry technologies typically output mass-to-charge ratio values but not the biochemical compounds of interest. We propose a framework that addresses both issues to make MSI more accessible. We utilized convolutional autoencoders to aggregate intratumoral features of interest from MSI of cancer xenograft models. Exemplified for the parameter tumor hypoxia, which is known to show significant spatial heterogeneity, we highlight that MSI is able to capture these small intensity signals and that autoencoders can preserve them in a lower dimensional space. Complementing MSI with tandem MS data from the same tumor model, multiple promising peptide candidates were derived that were associated with hypoxia. Compared to random forest models, we showed that our autoencoder approach produced more plausible candidates. Considering other spatial omics modalities, the architecture of the convolutional autoencoder can be easily adapted while ensuring high explainability. Biological sciences/Cancer Biological sciences/Computational biology and bioinformatics Full Text Additional Declarations (Not answered) Supplementary Files SupplementaryTable1unsupervisedpeptidecandidatesmultiple0.80.95.xlsx SupplementaryTable2semisupervisedpeptidecandidatesmultiple0.80.95.xlsx Cite Share Download PDF Status: Published Journal Publication published 27 May, 2024 Read the published version in npj Systems Biology and Applications → Version 1 posted Editorial decision: revise 25 Feb, 2024 Review # 2 received at journal 25 Feb, 2024 Review # 1 received at journal 04 Feb, 2024 Reviewer # 2 agreed at journal 21 Jan, 2024 Reviewer # 1 agreed at journal 20 Jan, 2024 Reviewers invited by journal 20 Jan, 2024 Submission checks completed at journal 15 Jan, 2024 Editor assigned by journal 12 Jan, 2024 First submitted to journal 12 Jan, 2024 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-3755587","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":268230544,"identity":"bc3c004a-68db-4e8a-b44a-fd3430b8cc90","order_by":0,"name":"Verena Bitto","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0004-1303-3335","institution":"German Cancer Research Center (DKFZ)","correspondingAuthor":true,"prefix":"","firstName":"Verena","middleName":"","lastName":"Bitto","suffix":""},{"id":268230545,"identity":"6a37ee12-f78b-4b12-b436-9aefc77f6a1c","order_by":1,"name":"Pia Hönscheid","email":"","orcid":"","institution":"University Hospital Carl Gustav Carus","correspondingAuthor":false,"prefix":"","firstName":"Pia","middleName":"","lastName":"Hönscheid","suffix":""},{"id":268230546,"identity":"7cbd6d64-051d-4dc1-8eaa-d7316557ad63","order_by":2,"name":"María José Besso","email":"","orcid":"","institution":"German Cancer Research Center (DKFZ)","correspondingAuthor":false,"prefix":"","firstName":"María","middleName":"José","lastName":"Besso","suffix":""},{"id":268230547,"identity":"317480d1-6a02-43d2-bff1-0f714b8a23d4","order_by":3,"name":"Christian Sperling","email":"","orcid":"","institution":"University Hospital Carl Gustav Carus","correspondingAuthor":false,"prefix":"","firstName":"Christian","middleName":"","lastName":"Sperling","suffix":""},{"id":268230548,"identity":"71ab6d2d-facf-42b8-870e-b57079484043","order_by":4,"name":"Ina Kurth","email":"","orcid":"https://orcid.org/0000-0001-9261-5165","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ina","middleName":"","lastName":"Kurth","suffix":""},{"id":268230549,"identity":"5fced8f9-fd91-4cd3-b56a-a8b95dd5437e","order_by":5,"name":"Michael Baumann","email":"","orcid":"https://orcid.org/0000-0002-9340-974X","institution":"German Cancer Research Center (DKFZ) Heidelberg","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Baumann","suffix":""},{"id":268230550,"identity":"1aa0c26a-80b7-46b8-b586-d5c5b2dad47a","order_by":6,"name":"Benedikt Brors","email":"","orcid":"","institution":"German Cancer Research Center (DKFZ)","correspondingAuthor":false,"prefix":"","firstName":"Benedikt","middleName":"","lastName":"Brors","suffix":""}],"badges":[],"createdAt":"2023-12-14 22:20:58","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3755587/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3755587/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41540-024-00385-x","type":"published","date":"2024-05-27T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":57250569,"identity":"ef005a96-2f63-4c61-9ac7-23c52ab658e7","added_by":"auto","created_at":"2024-05-28 07:10:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1798371,"visible":true,"origin":"","legend":"","description":"","filename":"20240112Bitto2024Easingaccessibilitytomassspectrometryimagingusingconvolutional.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3755587/v1_covered_653ac469-3114-4880-a842-0fef5bf8ec4e.pdf"},{"id":50008108,"identity":"d81b4042-b4cc-481c-83da-dabe2fe24a36","added_by":"auto","created_at":"2024-01-23 03:56:32","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12681,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTable1unsupervisedpeptidecandidatesmultiple0.80.95.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-3755587/v1/7f96478bc3a2d83349a18ccf.xlsx"},{"id":50008107,"identity":"b9362a8a-7dd9-4148-8728-ae6ecc2e2d7d","added_by":"auto","created_at":"2024-01-23 03:56:31","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":12090,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"SupplementaryTable2semisupervisedpeptidecandidatesmultiple0.80.95.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-3755587/v1/086cd46ab4dca6cae0485fe2.xlsx"}],"financialInterests":"(Not answered)","formattedTitle":"Easing accessibility to mass spectrometry imaging using convolutional autoencoders for deriving hypoxia-associated peptide candidates from tumors","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":"npj-systems-biology-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjsba","sideBox":"Learn more about [npj Systems Biology and Applications](http://www.nature.com/npjsba/)","snPcode":"41540","submissionUrl":"https://submission.springernature.com/new-submission/41540/3","title":"npj Systems Biology and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-3755587/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3755587/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Spatial omics data promise to reveal novel insights into the intratumoral heterogenity of biological parameters of cancer.\r\nMass spectrometry imaging (MSI) allows to study spatially-resolved peptides, metabolites and lipids.\r\nYet, in biomedical research the technology is rarely used for biomarker discovery. Like all spatial omics data, its high dimensionality and multicollinearity imposes special challenges for analysis. Additionally, mass spectrometry technologies typically output mass-to-charge ratio values but not the biochemical compounds of interest. \r\n\r\nWe propose a framework that addresses both issues to make MSI more accessible. We utilized convolutional autoencoders to aggregate intratumoral features of interest from MSI of cancer xenograft models. Exemplified for the parameter tumor hypoxia, which is known to show significant spatial heterogeneity, we highlight that MSI is able to capture these small intensity signals and that autoencoders can preserve them in a lower dimensional space. Complementing MSI with tandem MS data from the same tumor model, multiple promising peptide candidates were derived that were associated with hypoxia. Compared to random forest models, we showed that our autoencoder approach produced more plausible candidates.\r\nConsidering other spatial omics modalities, the architecture of the convolutional autoencoder can be easily adapted while ensuring high explainability.","manuscriptTitle":"Easing accessibility to mass spectrometry imaging using convolutional autoencoders for deriving hypoxia-associated peptide candidates from tumors","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-23 03:56:27","doi":"10.21203/rs.3.rs-3755587/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"revise","date":"2024-02-26T03:28:26+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"This content is not available.","date":"2024-02-25T14:19:40+00:00","index":2,"fulltext":"This content is not available."},{"type":"editorInvitedReview","content":"This content is not available.","date":"2024-02-04T20:16:01+00:00","index":1,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2024-01-22T03:41:57+00:00","index":2,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2024-01-20T22:38:44+00:00","index":1,"fulltext":"This content is not available."},{"type":"reviewersInvited","content":"","date":"2024-01-20T14:15:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-01-15T13:35:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-12T14:14:19+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Systems Biology and Applications","date":"2024-01-12T14:14:18+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-systems-biology-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjsba","sideBox":"Learn more about [npj Systems Biology and Applications](http://www.nature.com/npjsba/)","snPcode":"41540","submissionUrl":"https://submission.springernature.com/new-submission/41540/3","title":"npj Systems Biology and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"55bfd3f6-c8ff-4758-a87c-2a078c07967d","owner":[],"postedDate":"January 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":28262577,"name":"Biological sciences/Cancer"},{"id":28262578,"name":"Biological sciences/Computational biology and bioinformatics"}],"tags":[],"updatedAt":"2024-05-28T07:10:47+00:00","versionOfRecord":{"articleIdentity":"rs-3755587","link":"https://doi.org/10.1038/s41540-024-00385-x","journal":{"identity":"npj-systems-biology-and-applications","isVorOnly":false,"title":"npj Systems Biology and Applications"},"publishedOn":"2024-05-27 04:00:00","publishedOnDateReadable":"May 27th, 2024"},"versionCreatedAt":"2024-01-23 03:56:27","video":"","vorDoi":"10.1038/s41540-024-00385-x","vorDoiUrl":"https://doi.org/10.1038/s41540-024-00385-x","workflowStages":[]},"version":"v1","identity":"rs-3755587","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3755587","identity":"rs-3755587","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}