Current Structural Variant Calling Biases Compromise Clinical Genome Diagnostics

Current Structural Variant Calling Biases Compromise Clinical Genome Diagnostics | 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 Current Structural Variant Calling Biases Compromise Clinical Genome Diagnostics Blaž Vrhovšek, Ana Markež Vrhovšek, Doroteja Vujinović, Jernej Kovač, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9179453/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Structural variants (SVs) account for a substantial proportion of pathogenic mutations in rare diseases, yet their detection remains challenging in clinically relevant coding regions. We systematically benchmarked SV detection across Illumina WGS, Illumina WES, ONT WGS, and PacBio WGS using the HG002 GIAB truth set on GRCh37 and GRCh38. Performance was assessed within three nested interval sets: high-confidence intervals (HCI), a pediatric disorders gene panel (GP), and exons plus UTRs (EX + UTR). To isolate genomic context effects from interval size, we developed a novel simulation framework generating exon-like target sets outside coding regions. Long-read platforms outperformed short-read sequencing across all intervals, with PacBio Pbsv achieving F1 = 0.94 in HCI versus 0.62 for Illumina WGS. SV detection performance consistently dropped in EX + UTR regions compared to simulated counterparts, indicating systematic bias beyond interval size effects. Analysis on GRCh38 revealed that region-dependent performance gaps persisted, although they were less pronounced and predominantly affecting precision. These results demonstrate that SV detection accuracy is both technology- and region-dependent, underscoring the need for interval-specific benchmarking in clinical genomics. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Biological sciences/Genetics Full Text Additional Declarations No competing interests reported. Supplementary Files supp.zip Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 07 May, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviewers agreed at journal 27 Apr, 2026 Reviewers agreed at journal 24 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers invited by journal 08 Apr, 2026 Editor assigned by journal 06 Apr, 2026 Submission checks completed at journal 24 Mar, 2026 First submitted to journal 20 Mar, 2026 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-9179453","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":623888883,"identity":"303339a7-35d7-4bd6-8f85-363fbcc39f84","order_by":0,"name":"Blaž Vrhovšek","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Blaž","middleName":"","lastName":"Vrhovšek","suffix":""},{"id":623888885,"identity":"2b23b03f-e65d-42b6-a5d4-601ef324d47f","order_by":1,"name":"Ana Markež Vrhovšek","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Ana","middleName":"Markež","lastName":"Vrhovšek","suffix":""},{"id":623888889,"identity":"1724c099-96fe-41b2-ac77-62dfe1b52304","order_by":2,"name":"Doroteja Vujinović","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Doroteja","middleName":"","lastName":"Vujinović","suffix":""},{"id":623888890,"identity":"3ee36031-ffb3-4834-9d1a-b6d10472f254","order_by":3,"name":"Jernej Kovač","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Jernej","middleName":"","lastName":"Kovač","suffix":""},{"id":623888892,"identity":"f602a3ad-4f6a-4aff-8c01-c98b767b46ef","order_by":4,"name":"Maruša Debeljak","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Maruša","middleName":"","lastName":"Debeljak","suffix":""},{"id":623888895,"identity":"1b028267-d8a1-4595-a041-0c63d1993487","order_by":5,"name":"Tadej Battelino","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Tadej","middleName":"","lastName":"Battelino","suffix":""},{"id":623888897,"identity":"9200da0c-44b7-4283-aa29-60bb2ceda23e","order_by":6,"name":"Barbara Jenko Bizjan","email":"data:image/png;base64,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","orcid":"","institution":"University of Ljubljana","correspondingAuthor":true,"prefix":"","firstName":"Barbara","middleName":"Jenko","lastName":"Bizjan","suffix":""}],"badges":[],"createdAt":"2026-03-20 13:38:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9179453/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9179453/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107480897,"identity":"da1ae4c3-7580-403c-bfbb-8aec38985e91","added_by":"auto","created_at":"2026-04-22 02:14:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":671863,"visible":true,"origin":"","legend":"","description":"","filename":"CurrentStructuralVariantCallingBiasesCompromiseClinicalGenomeDiagnosticsr1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9179453/v1_covered_2411a376-5eb3-4b2f-91f4-5fc349d1548f.pdf"},{"id":107101134,"identity":"b173a437-03ce-4a4e-bf92-246ac933501a","added_by":"auto","created_at":"2026-04-16 18:59:31","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":418931,"visible":true,"origin":"","legend":"","description":"","filename":"supp.zip","url":"https://assets-eu.researchsquare.com/files/rs-9179453/v1/96d455e77593e3f867512645.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Current Structural Variant Calling Biases Compromise Clinical Genome Diagnostics","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"npj-genomic-medicine","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjgenmed","sideBox":"Learn more about [npj Genomic Medicine](http://www.nature.com/npjgenmed/)","snPcode":"41525","submissionUrl":"https://mts-npjgenmed.nature.com/","title":"npj Genomic Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9179453/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9179453/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eStructural variants (SVs) account for a substantial proportion of pathogenic mutations in rare diseases, yet their detection remains challenging in clinically relevant coding regions. We systematically benchmarked SV detection across Illumina WGS, Illumina WES, ONT WGS, and PacBio WGS using the HG002 GIAB truth set on GRCh37 and GRCh38. Performance was assessed within three nested interval sets: high-confidence intervals (HCI), a pediatric disorders gene panel (GP), and exons plus UTRs (EX\u0026thinsp;+\u0026thinsp;UTR). To isolate genomic context effects from interval size, we developed a novel simulation framework generating exon-like target sets outside coding regions. Long-read platforms outperformed short-read sequencing across all intervals, with PacBio Pbsv achieving F1\u0026thinsp;=\u0026thinsp;0.94 in HCI versus 0.62 for Illumina WGS. SV detection performance consistently dropped in EX\u0026thinsp;+\u0026thinsp;UTR regions compared to simulated counterparts, indicating systematic bias beyond interval size effects. Analysis on GRCh38 revealed that region-dependent performance gaps persisted, although they were less pronounced and predominantly affecting precision. These results demonstrate that SV detection accuracy is both technology- and region-dependent, underscoring the need for interval-specific benchmarking in clinical genomics.\u003c/p\u003e","manuscriptTitle":"Current Structural Variant Calling Biases Compromise Clinical Genome Diagnostics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-16 18:59:27","doi":"10.21203/rs.3.rs-9179453/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-07T09:58:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"96998039560514054443704764075874368347","date":"2026-04-29T12:08:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"166563505509698289994544229773242383292","date":"2026-04-27T10:47:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"267354887637470320242198745683269224261","date":"2026-04-24T06:22:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"77741718411450985202901176318150029256","date":"2026-04-09T08:51:16+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-09T02:56:14+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-06T14:02:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-24T11:25:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Genomic Medicine","date":"2026-03-20T13:23:32+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-genomic-medicine","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjgenmed","sideBox":"Learn more about [npj Genomic Medicine](http://www.nature.com/npjgenmed/)","snPcode":"41525","submissionUrl":"https://mts-npjgenmed.nature.com/","title":"npj Genomic Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2b7fda0d-5a33-4c47-bac1-387f2ea253f4","owner":[],"postedDate":"April 16th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-07T09:58:04+00:00","index":24,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66399447,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66399448,"name":"Health sciences/Diseases"},{"id":66399449,"name":"Biological sciences/Genetics"}],"tags":[],"updatedAt":"2026-04-16T18:59:27+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-16 18:59:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9179453","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9179453","identity":"rs-9179453","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}