Interpretable machine learning classifiers implicate GPC6 in Parkinson’s disease from single-nuclei midbrain transcriptomes

Interpretable machine learning classifiers implicate GPC6 in Parkinson’s disease from single-nuclei midbrain transcriptomes | 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 Interpretable machine learning classifiers implicate GPC6 in Parkinson’s disease from single-nuclei midbrain transcriptomes Sali Farhan, Michael Fiorini, Jialun Li, Edward Fon, Rhalena Thomas This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5471740/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Parkinson’s disease (PD) is a progressive and devastating neurodegenerative disease. An incomplete understanding of its genetic architecture remains a major barrier to the clinical translation of targeted therapeutics, necessitating novel approaches to uncover elusive genetic determinants. Single-cell and single-nuclear RNA sequencing (scnRNAseq) can help bridge this gap by profiling individual cells for disease-associated differential gene expression and nominating genes for targeted genomic analyses. Here, we introduce a machine learning framework to identify molecular features that characterize post-mortem brain cells from PD patients. We train classifiers to distinguish between PD and healthy cells, then decode the models to unravel the ‘reasons’ behind the classifications, revealing key genes expression signatures that characterize cells from the parkinsonian brain. Application of this framework to three publicly available snRNAseq datasets characterizing the post-mortem midbrain identified cell-type-specific gene sets that accurately classify PD cells across all datasets, demonstrating our approach's capacity to identify robust molecular markers of disease. Targeted genomic analyses of the key genes characterizing PD cells revealed a previously undescribed association between PD and rare variants in GPC6 , a member of the heparan sulfate proteoglycan family, which have been implicated in the intracellular accumulation of α-synuclein preformed fibrils. We replicate this association in three separate case-control cohorts. Our method promises to enhance understanding of the genetic architecture in complex diseases like PD, representing a critical step toward targeted therapeutics. Our publicly available framework is readily applicable across diseases. Biological sciences/Genetics/Gene expression Biological sciences/Computational biology and bioinformatics/Machine learning single-cell RNA sequencing single-nuclei RNA sequencing machine learning deep learning supervised classifier interpretable explainer Parkinson’s disease dopaminergic neurons Full Text Additional Declarations There is NO Competing Interest. Supplementary Files TableS1.xlsx TableS2.xlsx TableS3.xlsx TableS4.xlsx TableS5.xlsx TableS6.xlsx TableS7.xlsx TableS8.xlsx AdditionalFile1.docx Cite Share Download PDF Status: Under Review 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-5471740","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":385695588,"identity":"95066283-3383-4907-a724-77b146c8312b","order_by":0,"name":"Sali Farhan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYFAC5oYDDDYMDAYMDIwPgFwePnaCWhiBWtLAWpgNQFrYmInQwgDVwiYB4hPUIt9+sPEAQ4Jdvjn72WNVN2pqZYBaGD/8wKPF4Ewi0GEJyZY7e/LSbuccOw5yGLNkDz4tDEAtjD+YDQwO5Jjdzm04BtLCxsCDz2H9D0G21BsYnH9jVgzTwvgHn2dugB122MDgRo4Zc25DDVgLMz5bDG4AbUlIOA7U8sZYOufYAaAWxmZpGbwOSz784UNCNdBhOYafc2rq7PnZmw9+fIPPYSCQgGAeZoDEFAmgjiTVo2AUjIJRMDIAAAp1SO5TJYwwAAAAAElFTkSuQmCC","orcid":"","institution":"McGill University","correspondingAuthor":true,"prefix":"","firstName":"Sali","middleName":"","lastName":"Farhan","suffix":""},{"id":385695589,"identity":"b2141d8a-b48f-461b-9000-046f22d4d98f","order_by":1,"name":"Michael Fiorini","email":"","orcid":"","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Fiorini","suffix":""},{"id":385695590,"identity":"60c07464-5890-45c4-86a8-c9693e8520c4","order_by":2,"name":"Jialun Li","email":"","orcid":"","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Jialun","middleName":"","lastName":"Li","suffix":""},{"id":385695591,"identity":"0cb5fae4-aa43-482f-a736-084ab4f16218","order_by":3,"name":"Edward Fon","email":"","orcid":"https://orcid.org/0000-0002-5520-6239","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Edward","middleName":"","lastName":"Fon","suffix":""},{"id":385695592,"identity":"6316cca9-edd6-4cc3-94de-0a72ae8938fa","order_by":4,"name":"Rhalena Thomas","email":"","orcid":"","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Rhalena","middleName":"","lastName":"Thomas","suffix":""}],"badges":[],"createdAt":"2024-11-17 23:15:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5471740/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5471740/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":71480639,"identity":"bc7984a7-4221-419d-ba8a-d25773758fa6","added_by":"auto","created_at":"2024-12-16 05:57:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1898937,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1_covered_9db0fdb4-1af5-4721-a3cd-a3227b2cbe23.pdf"},{"id":71478374,"identity":"d3021093-d194-43f8-bc6e-fc1ccb592a4f","added_by":"auto","created_at":"2024-12-16 05:32:44","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":23128,"visible":true,"origin":"","legend":"","description":"","filename":"TableS1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/bda9723d01ed34d3549483ec.xlsx"},{"id":71479421,"identity":"3a270711-823c-423e-b05b-3c849b927adf","added_by":"auto","created_at":"2024-12-16 05:40:45","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":15808,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"TableS2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/c8ca749b678f162b8798283c.xlsx"},{"id":71480634,"identity":"a070ea73-b267-4527-91c0-d38bc82b226e","added_by":"auto","created_at":"2024-12-16 05:57:48","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":53400,"visible":true,"origin":"","legend":"","description":"","filename":"TableS3.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/8638c68d43e4b91b6f25f77a.xlsx"},{"id":71478381,"identity":"0790e18f-1d9c-47cd-b0bb-74071e120779","added_by":"auto","created_at":"2024-12-16 05:32:45","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":11065,"visible":true,"origin":"","legend":"","description":"","filename":"TableS4.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/e02dc4a863d2f07878fc5413.xlsx"},{"id":71478380,"identity":"b4d35e48-8d31-43a6-9c29-600fd85233e6","added_by":"auto","created_at":"2024-12-16 05:32:45","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":10499,"visible":true,"origin":"","legend":"","description":"","filename":"TableS5.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/9d3dacb91c6f5c543297cdf7.xlsx"},{"id":71478375,"identity":"ebc93b05-1335-4193-8371-2458a2264539","added_by":"auto","created_at":"2024-12-16 05:32:45","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":10117,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"TableS6.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/70c9f254b590a6e6f4e05081.xlsx"},{"id":71478377,"identity":"59c67ac4-e86a-4220-8b92-d3337a70015f","added_by":"auto","created_at":"2024-12-16 05:32:45","extension":"xlsx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":14300,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"TableS7.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/af689e699c8ed86c2acbb839.xlsx"},{"id":71479422,"identity":"77106c0b-9888-4dac-ab25-50d57a318a00","added_by":"auto","created_at":"2024-12-16 05:40:45","extension":"xlsx","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":12630,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"TableS8.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/a1162d727d032ccec7dde7a3.xlsx"},{"id":71478383,"identity":"555196c6-4521-4781-a6b3-368b6d51c7ba","added_by":"auto","created_at":"2024-12-16 05:32:46","extension":"docx","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":11020338,"visible":true,"origin":"","legend":"","description":"","filename":"AdditionalFile1.docx","url":"https://assets-eu.researchsquare.com/files/rs-5471740/v1/54386743fff53c5699725cee.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Interpretable machine learning classifiers implicate GPC6 in Parkinson’s disease from single-nuclei midbrain transcriptomes","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"single-cell RNA sequencing, single-nuclei RNA sequencing, machine learning, deep learning, supervised classifier, interpretable explainer, Parkinson’s disease, dopaminergic neurons","lastPublishedDoi":"10.21203/rs.3.rs-5471740/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5471740/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eParkinson\u0026rsquo;s disease (PD) is a progressive and devastating neurodegenerative disease. An incomplete understanding of its genetic architecture remains a major barrier to the clinical translation of targeted therapeutics, necessitating novel approaches to uncover elusive genetic determinants. Single-cell and single-nuclear RNA sequencing (scnRNAseq) can help bridge this gap by profiling individual cells for disease-associated differential gene expression and nominating genes for targeted genomic analyses. Here, we introduce a machine learning framework to identify molecular features that characterize post-mortem brain cells from PD patients. We train classifiers to distinguish between PD and healthy cells, then decode the models to unravel the \u0026lsquo;reasons\u0026rsquo; behind the classifications, revealing key genes expression signatures that characterize cells from the parkinsonian brain. Application of this framework to three publicly available snRNAseq datasets characterizing the post-mortem midbrain identified cell-type-specific gene sets that accurately classify PD cells across all datasets, demonstrating our approach's capacity to identify robust molecular markers of disease. Targeted genomic analyses of the key genes characterizing PD cells revealed a previously undescribed association between PD and rare variants in \u003cem\u003eGPC6\u003c/em\u003e, a member of the heparan sulfate proteoglycan family, which have been implicated in the intracellular accumulation of α-synuclein preformed fibrils. We replicate this association in three separate case-control cohorts. Our method promises to enhance understanding of the genetic architecture in complex diseases like PD, representing a critical step toward targeted therapeutics. Our publicly available framework is readily applicable across diseases.\u003c/p\u003e","manuscriptTitle":"Interpretable machine learning classifiers implicate GPC6 in Parkinson’s disease from single-nuclei midbrain transcriptomes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-16 05:32:39","doi":"10.21203/rs.3.rs-5471740/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f4fbcfe4-826d-457a-a1d7-5fc947005cc2","owner":[],"postedDate":"December 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":41090988,"name":"Biological sciences/Genetics/Gene expression"},{"id":41090989,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2024-12-16T05:32:40+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-16 05:32:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5471740","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5471740","identity":"rs-5471740","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}