Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning

Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning | 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 Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning Mikael Lassen, Benjamin Lundquist Thomsen, Jesper Christensen, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1797587/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract The worldwide increase of antimicrobial resistance (AMR) is a serious threat to human health. To avert the spread of AMR, fast reliable diagnostics tools that facilitate optimal antibiotic stewardship are an unmet need. In this regard, Raman spectroscopy promises rapid label- and culture-free identification and antimicrobial susceptibility testing (AST) in a single step. However, even though many Raman-based bacteria-identification and AST studies have demonstrated impressive results, some shortcomings must be addressed. To bridge the gap between proof-of-concept studies and clinical application, we have developed machine learning techniques in combination with a novel data-augmentation algorithm, for fast identification of minimally prepared bacteria phenotypes and the distinctions of methicillin-resistant (MR) from methicillin-susceptible (MS) bacteria. For this we have implemented a spectral transformer model for hyper-spectral Raman images of bacteria. We show that our model outperforms the standard convolutional neural network models on a multitude of classification problems, both in terms of accuracy and in terms of training time. We attain more than 96$%$ classification accuracy on a dataset consisting of 15 different classes and 95.6$%$ classification accuracy for six MR-MS bacteria species. More importantly, our results are obtained using only fast and easy-to-produce training and test data. Full Text Additional Declarations No competing interests reported. Supplementary Files supplementaryScientificReports.pdf Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Major revision 07 Sep, 2022 Reviews received at journal 21 Aug, 2022 Reviewers agreed at journal 04 Aug, 2022 Reviewers invited by journal 02 Aug, 2022 Editor assigned by journal 02 Aug, 2022 Editor invited by journal 28 Jun, 2022 Submission checks completed at journal 28 Jun, 2022 First submitted to journal 26 Jun, 2022 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-1797587","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":116925659,"identity":"2c553a2e-d00e-4bf9-b48f-ae03de3152a5","order_by":0,"name":"Mikael Lassen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAf0lEQVRIiWNgGAWjYDACduYDEhUMDIwziNfCzJYgcYZELTwGJGrRbeb5eONgDoPszAZitZgd5t1scXAbg/Fsom0Batkm/XEbQ+I8ErTwPJM4SKoWNrAWUhzGZgz0i4QxCd4/3vzwxsFtNrIzDhBtDQRIkKh+FIyCUTAKRgF+AAB4LiX+RXwIvAAAAABJRU5ErkJggg==","orcid":"","institution":"Danish Fundamental Metrology A/S","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Mikael","middleName":"","lastName":"Lassen","suffix":""},{"id":116925660,"identity":"41cd29da-1f9f-4549-bb28-575fa175a604","order_by":1,"name":"Benjamin Lundquist Thomsen","email":"","orcid":"","institution":"Danish Fundamental Metrology A/S","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Benjamin","middleName":"Lundquist","lastName":"Thomsen","suffix":""},{"id":116925661,"identity":"b1eb0072-a66f-48e8-9741-6c9fda7b3f31","order_by":2,"name":"Jesper Christensen","email":"","orcid":"","institution":"Danish Fundamental Metrology A/S","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jesper","middleName":"","lastName":"Christensen","suffix":""},{"id":116925662,"identity":"6a8bc32e-1bf8-4cdf-a332-c853f95558d5","order_by":3,"name":"Olga Rodenko","email":"","orcid":"","institution":"Danish Fundamental Metrology A/S","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Olga","middleName":"","lastName":"Rodenko","suffix":""},{"id":116925663,"identity":"a1dc0608-0622-401f-885d-52f51821d978","order_by":4,"name":"Iskander Usenov","email":"","orcid":"","institution":"Technical University of Berlin","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Iskander","middleName":"","lastName":"Usenov","suffix":""},{"id":116925664,"identity":"7cd99664-d015-4713-afac-9649751d65e1","order_by":5,"name":"Rasmus Birkholm Grønnemose","email":"","orcid":"","institution":"University of Southern Denmark","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Rasmus","middleName":"Birkholm","lastName":"Grønnemose","suffix":""},{"id":116925665,"identity":"ae44b36b-5cab-4744-bbe9-f65538a22858","order_by":6,"name":"Thomas Emil Andersen","email":"","orcid":"","institution":"University of Southern Denmark","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Thomas","middleName":"Emil","lastName":"Andersen","suffix":""}],"badges":[],"createdAt":"2022-06-26 22:44:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1797587/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1797587/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":23525043,"identity":"d1f145c0-3fcb-42ce-9fd6-c55e10f7fc4f","added_by":"auto","created_at":"2022-07-06 14:31:58","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6925653,"visible":true,"origin":"","legend":"","description":"","filename":"SubmitScientificreports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1797587/v1_covered.pdf"},{"id":23525024,"identity":"804d2e5c-c2b1-4e77-a9f1-2f6d9235ee19","added_by":"auto","created_at":"2022-07-06 14:31:41","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":197289,"visible":true,"origin":"","legend":"","description":"","filename":"supplementaryScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1797587/v1/a4bb0659309e084b4b0d395a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-1797587/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"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":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-1797587/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1797587/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The worldwide increase of antimicrobial resistance (AMR) is a serious threat to human health. To avert the spread of AMR, fast reliable diagnostics tools that facilitate optimal antibiotic stewardship are an unmet need. In this regard, Raman spectroscopy promises rapid label- and culture-free identification and antimicrobial susceptibility testing (AST) in a single step. However, even though many Raman-based bacteria-identification and AST studies have demonstrated impressive results, some shortcomings must be addressed. To bridge the gap between proof-of-concept studies and clinical application, we have developed machine learning techniques in combination with a novel data-augmentation algorithm, for fast identification of minimally prepared bacteria phenotypes and the distinctions of methicillin-resistant (MR) from methicillin-susceptible (MS) bacteria. For this we have implemented a spectral transformer model for hyper-spectral Raman images of bacteria. We show that our model outperforms the standard convolutional neural network models on a multitude of classification problems, both in terms of accuracy and in terms of training time. We attain more than 96$\\%$ classification accuracy on a dataset consisting of 15 different classes and 95.6$\\%$ classification accuracy for six MR-MS bacteria species. More importantly, our results are obtained using only fast and easy-to-produce training and test data.","manuscriptTitle":"Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-07-06 14:31:36","doi":"10.21203/rs.3.rs-1797587/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2022-09-07T06:34:33+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2022-08-21T15:12:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"766bd965-329a-4e50-a4c4-6d36f649755e","date":"2022-08-04T11:38:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2022-08-02T07:50:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2022-08-02T07:34:08+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2022-06-28T08:57:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-06-28T07:58:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2022-06-26T22:36:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"54b50726-1a64-405e-a517-4f0fd75bfc15","owner":[],"postedDate":"July 6th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2022-09-20T04:59:25+00:00","versionOfRecord":[],"versionCreatedAt":"2022-07-06 14:31:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-1797587","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1797587","identity":"rs-1797587","version":["v1"]},"buildId":"FbvkV6FR0MCFSLy54lSbu","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}