Interpretable Machine Learning Identifies Paediatric Systemic Lupus Erythematosus Subtypes Based On Gene Expression Data

Interpretable Machine Learning Identifies Paediatric Systemic Lupus Erythematosus Subtypes Based On Gene Expression Data | 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 Interpretable Machine Learning Identifies Paediatric Systemic Lupus Erythematosus Subtypes Based On Gene Expression Data Sara A.Yones, Alva Annett, Patricia Stoll, Klev Diamanti, Linda Holmfeldt, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-588542/v2 This work is licensed under a CC BY 4.0 License Status: Under Review Version 2 posted 10 You are reading this latest preprint version Show more versions Abstract Transcriptomic analyses are commonly used to identify differentially expressed genes between patients and controls, or within individuals across disease courses. These methods, whilst effective, cannot encompass the combinatorial effects of genes driving disease. We applied rule-based machine learning (RBML) models and rule networks (RN) to an existing paediatric Systemic Lupus Erythematosus (SLE) blood expression dataset, with the goal of developing gene networks to separate low and high disease activity (DA1 and DA3). The resultant model had an 81% accuracy to distinguish between DA1 and DA3, with unsupervised hierarchical clustering revealing additional subgroups indicative of the immune axis involved or state of disease flare. These subgroups correlated with clinical variables, suggesting that the gene sets identified may further the understanding of gene networks that act in concert to drive disease progression. This included roles for genes i) induced by interferons ( IFI35 and OTOF ), ii) key to SLE cell types ( KLRB1 encoding CD161), or iii) with roles in autophagy and NF-κB pathway responses ( CKAP4 ). As demonstrated here, RBML approaches have the potential to reveal novel gene patterns from within a heterogeneous disease, facilitating patient clinical and therapeutic stratification. Computational Biology Bioinformatics Immunology machine learning RBML SLE KLRB1 Full Text Additional Declarations No competing interests reported. Supplementary Files YonesetalSupplementaryTables.xlsx YonesetalSupplementaryMaterial.pdf Cite Share Download PDF Status: Under Review Version 2 posted Editorial decision: Major revision 06 Oct, 2021 Reviews received at journal 05 Oct, 2021 Reviewers agreed at journal 16 Sep, 2021 Reviews received at journal 04 Sep, 2021 Reviewers agreed at journal 26 Aug, 2021 Reviewers invited by journal 25 Jul, 2021 Editor assigned by journal 25 Jul, 2021 Editor invited by journal 10 Jun, 2021 Submission checks completed at journal 10 Jun, 2021 First submitted to journal 08 Jun, 2021 You are reading this latest preprint version Show more versions 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-588542","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[{"code":1,"date":"2021-06-03 19:19:21","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}}],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":37670894,"identity":"b50fad03-6be2-4add-b093-3735f1965085","order_by":0,"name":"Sara A.Yones","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIiWNgGAWjYJADxgcJpGphNiBZC5sEUcrk288+/MDYZpO4nb39WcWDmm0MBjcSmD98wKPF4Ey6sQRjW1rizp4zZjcSjt0GaWGTnIFPC0MaA1DL4cQNN3LYbiQ2QLQw8+BzWP8z5h9gLfefPyuAamH+/AefZ26ksUFtYTBjgGphkManw+DGMzaLhHNpxhvO5BhLAP3CI3nmYZtkD16HpTHf+FBmI7vh+PGHH3/U3JbjO558+MMPfNaAQCIbgg30OGMDIQ1AgNe3o2AUjIJRMOIBAJUIUTxO5DuLAAAAAElFTkSuQmCC","orcid":"","institution":"Science for Life Laboratory, Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Sara","middleName":"","lastName":"A.Yones","suffix":""},{"id":37670895,"identity":"d89de986-970a-47c8-b3ef-ee97648968b9","order_by":1,"name":"Alva Annett","email":"","orcid":"","institution":"Science for Life Laboratory, Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Alva","middleName":"","lastName":"Annett","suffix":""},{"id":37670896,"identity":"3a3d2b77-fa85-4544-9cca-2172eae8e1d7","order_by":2,"name":"Patricia Stoll","email":"","orcid":"","institution":"Department of Biosystems Science and Engineering, ETH Zurich, Zurich, Switzerland","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Patricia","middleName":"","lastName":"Stoll","suffix":""},{"id":37670897,"identity":"0068af3f-9700-4bbf-bd64-b9db44671ecf","order_by":3,"name":"Klev Diamanti","email":"","orcid":"","institution":"Department of Immunology, Genetics and Pathology, Science for Life Laboratory, Uppsala University, Sweden","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Klev","middleName":"","lastName":"Diamanti","suffix":""},{"id":37670898,"identity":"eb01b13a-f195-4caa-a00f-4f5ca3cff915","order_by":4,"name":"Linda Holmfeldt","email":"","orcid":"","institution":"Department of Immunology, Genetics and Pathology, Science for Life Laboratory, Uppsala University, Sweden","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Linda","middleName":"","lastName":"Holmfeldt","suffix":""},{"id":37670899,"identity":"e7067c10-e74e-4b58-9780-271b431c94f9","order_by":5,"name":"Carl Fredrik Barrenäs","email":"","orcid":"","institution":"Science for Life Laboratory, Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Carl","middleName":"Fredrik","lastName":"Barrenäs","suffix":""},{"id":37670900,"identity":"f94cafce-c602-43d2-9a53-76cd81237ac7","order_by":6,"name":"Jennifer Meadows","email":"","orcid":"","institution":"Science for Life Laboratory, Department of Medical Biochemistry and Microbiology, Uppsala University, Uppsala, Sweden","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jennifer","middleName":"","lastName":"Meadows","suffix":""},{"id":37670901,"identity":"6a321d7d-fef8-457d-afc2-370553861bb7","order_by":7,"name":"Jan Komorowski","email":"","orcid":"","institution":"Science for Life Laboratory, Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jan","middleName":"","lastName":"Komorowski","suffix":""}],"badges":[],"createdAt":"2021-06-03 16:14:11","currentVersionCode":2,"declarations":"","doi":"10.21203/rs.3.rs-588542/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-588542/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":13654516,"identity":"ff280d04-3191-4b17-aaf6-c3cd2918d826","added_by":"auto","created_at":"2021-09-17 09:58:02","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1392901,"visible":true,"origin":"","legend":"","description":"","filename":"YonesetalManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-588542/v2_covered.pdf"},{"id":11197925,"identity":"73b486ac-df19-4391-8826-c813b575ec51","added_by":"auto","created_at":"2021-07-07 11:22:10","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1388900,"visible":true,"origin":"","legend":"","description":"","filename":"YonesetalManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-588542/v2_covered.pdf"},{"id":11197917,"identity":"bd2c930c-e9a3-4fa7-becd-aa59e89137f3","added_by":"auto","created_at":"2021-07-07 11:22:01","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":72909,"visible":true,"origin":"","legend":"","description":"","filename":"YonesetalSupplementaryTables.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-588542/v2/ba9293608d111c795a3768e4.xlsx"},{"id":11197918,"identity":"26c5bf93-285e-41c5-802a-4e95ddde8a6d","added_by":"auto","created_at":"2021-07-07 11:22:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5069818,"visible":true,"origin":"","legend":"","description":"","filename":"YonesetalSupplementaryMaterial.pdf","url":"https://assets-eu.researchsquare.com/files/rs-588542/v2/dd9f24cc32bef5f5f0e58bdb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eInterpretable Machine Learning Identifies Paediatric Systemic Lupus Erythematosus Subtypes Based On Gene Expression Data\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-588542/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":"machine learning, RBML, SLE, KLRB1","lastPublishedDoi":"10.21203/rs.3.rs-588542/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-588542/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTranscriptomic analyses are commonly used to identify differentially expressed genes between patients and controls, or within individuals across disease courses. These methods, whilst effective, cannot encompass the combinatorial effects of genes driving disease. We applied rule-based machine learning (RBML) models and rule networks (RN) to an existing paediatric Systemic Lupus Erythematosus (SLE) blood expression dataset, with the goal of developing gene networks to separate low and high disease activity (DA1 and DA3). The resultant model had an 81% accuracy to distinguish between DA1 and DA3, with unsupervised hierarchical clustering revealing additional subgroups indicative of the immune axis involved or state of disease flare. These subgroups correlated with clinical variables, suggesting that the gene sets identified may further the understanding of gene networks that act in concert to drive disease progression. This included roles for genes i) induced by interferons (\u003cem\u003eIFI35 \u003c/em\u003eand \u003cem\u003eOTOF\u003c/em\u003e), ii) key to SLE cell types (\u003cem\u003eKLRB1 \u003c/em\u003eencoding CD161), or iii) with roles in autophagy and NF-κB pathway responses (\u003cem\u003eCKAP4\u003c/em\u003e). As demonstrated here, RBML approaches have the potential to reveal novel gene patterns from within a heterogeneous disease, facilitating patient clinical and therapeutic stratification.\u003c/p\u003e","manuscriptTitle":"Interpretable Machine Learning Identifies Paediatric Systemic Lupus Erythematosus Subtypes Based On Gene Expression Data","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2021-07-07 11:22:00","doi":"10.21203/rs.3.rs-588542/v2","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2021-10-06T09:25:02+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-10-05T11:57:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"d8b2adae-8cbd-4350-b00d-a9502d5a8b75","date":"2021-09-16T06:50:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-09-04T18:41:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"78ba27fb-877d-4d51-b6f0-62b611b2f5bf","date":"2021-08-26T20:21:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2021-07-25T20:47:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2021-07-25T20:25:36+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2021-06-10T10:23:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2021-06-10T09:09:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2021-06-08T15:27:27+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":"cf6957e0-35aa-492f-8526-7be31d6f3553","owner":[],"postedDate":"July 7th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":5534064,"name":"Computational Biology"},{"id":5534065,"name":"Bioinformatics"},{"id":5534066,"name":"Immunology"}],"tags":[],"updatedAt":"2022-04-13T10:29:08+00:00","versionOfRecord":[],"versionCreatedAt":"2021-07-07 11:22:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-588542","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-588542","identity":"rs-588542","version":["v2"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}