{"id":"https://openalex.org/W7223859657","doi":"https://doi.org/10.64898/2026.10.24.761512","title":"Variant effect predictors are shaping the ClinVar classifications used to train and evaluate them","display_name":"Variant effect predictors are shaping the ClinVar classifications used to train and evaluate them","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7223859657","doi":"https://doi.org/10.64898/2026.10.24.761512"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.24.761512","doi":"https://doi.org/10.64898/2026.10.24.761512","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761512","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/27/2026.10.24.761512.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/27/2026.10.24.761512.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089444542","display_name":"Minyu Tao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210158898","display_name":"Institute of Genetics and Cancer","ror":"https://ror.org/05hygey35","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4210158898","https://openalex.org/I90344618","https://openalex.org/I98677209"]},{"id":"https://openalex.org/I4387154614","display_name":"MRC Human Genetics Unit","ror":"https://ror.org/011jsc803","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4387154614","https://openalex.org/I90344618","https://openalex.org/I98677209"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minyu Tao","raw_affiliation_strings":["MRC Human Genetics Unit, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MRC Human Genetics Unit, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I4210158898","https://openalex.org/I4387154614","https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002238592","display_name":"Joseph A. Marsh","orcid":"https://orcid.org/0000-0003-4132-0628","observed_orcids":["https://orcid.org/0000-0003-4132-0628"]},"institutions":[{"id":"https://openalex.org/I4210158898","display_name":"Institute of Genetics and Cancer","ror":"https://ror.org/05hygey35","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4210158898","https://openalex.org/I90344618","https://openalex.org/I98677209"]},{"id":"https://openalex.org/I4387154614","display_name":"MRC Human Genetics Unit","ror":"https://ror.org/011jsc803","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4387154614","https://openalex.org/I90344618","https://openalex.org/I98677209"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Joseph A. Marsh","raw_affiliation_strings":["MRC Human Genetics Unit, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK"],"raw_orcid":"https://orcid.org/0000-0003-4132-0628","affiliations":[{"raw_affiliation_string":"MRC Human Genetics Unit, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I4210158898","https://openalex.org/I4387154614","https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002238592"],"corresponding_institution_ids":["https://openalex.org/I4210158898","https://openalex.org/I4387154614","https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variant-effect-predictor","display_name":"variant effect predictors","score":0.9890000224113464},{"id":"https://openalex.org/keywords/clinvar","display_name":"ClinVar","score":0.9160000085830688},{"id":"https://openalex.org/keywords/circularity","display_name":"circularity","score":0.7089999914169312},{"id":"https://openalex.org/keywords/missense-mutations","display_name":"missense mutations","score":0.6919999718666077}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.505299985408783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49050000309944153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3741999864578247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.24.761512","doi":"https://doi.org/10.64898/2026.10.24.761512","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761512","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/27/2026.10.24.761512.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.24.761512","doi":"https://doi.org/10.64898/2026.10.24.761512","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.24.761512","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/27/2026.10.24.761512.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.4043000042438507,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G7564801717","display_name":"Protein Variant Interpretation","funder_award_id":"MC_UU_00035/9","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320320615","display_name":"Lister Institute of Preventive Medicine","ror":"https://ror.org/03356n642"},{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223859657.pdf","grobid_xml":"https://content.openalex.org/works/W7223859657.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1496259696","https://openalex.org/W2051978340","https://openalex.org/W2100867326","https://openalex.org/W2109372707","https://openalex.org/W2164004777","https://openalex.org/W2521967673","https://openalex.org/W2561724945","https://openalex.org/W3045929934","https://openalex.org/W3104285666","https://openalex.org/W3209435229","https://openalex.org/W4225399111","https://openalex.org/W4303671988","https://openalex.org/W4309643822","https://openalex.org/W4384201327","https://openalex.org/W4385637034","https://openalex.org/W4385737488","https://openalex.org/W4386572989","https://openalex.org/W4386861232","https://openalex.org/W4390616142","https://openalex.org/W4394946907","https://openalex.org/W4398197278","https://openalex.org/W4401763802","https://openalex.org/W4403891900","https://openalex.org/W4404641556","https://openalex.org/W4408278568","https://openalex.org/W4409669254","https://openalex.org/W4414111067","https://openalex.org/W7130504743","https://openalex.org/W7133919624","https://openalex.org/W7139982825","https://openalex.org/W7165968561"],"related_works":["https://openalex.org/W7130504743","https://openalex.org/W4408278568","https://openalex.org/W7143933748","https://openalex.org/W4324116893","https://openalex.org/W4409669254","https://openalex.org/W7130725107","https://openalex.org/W4394946907","https://openalex.org/W4408532029","https://openalex.org/W4405434042","https://openalex.org/W7204063505"],"abstract_inverted_index":{"Summary":[0],"Variant":[1],"effect":[2],"predictors":[3,121],"(VEPs)":[4],"are":[5],"playing":[6],"an":[7],"increasingly":[8],"influential":[9],"role":[10],"in":[11,82,131,184],"clinical":[12,60],"variant":[13],"classification.":[14],"Following":[15],"recent":[16],"calibration":[17],"efforts":[18],"and":[19,67,101,151,166,178],"the":[20,49,59,108,175],"development":[21],"of":[22,37,112,191],"points-based":[23],"classification":[24,183],"standards,":[25],"computational":[26,74,141,179],"predictions":[27,56],"can":[28],"now":[29],"carry":[30],"enough":[31],"weight":[32],"to":[33,64,117,127],"move":[34],"variants":[35,87],"out":[36],"uncertain":[38],"significance":[39],"with":[40],"little":[41],"additional":[42],"evidence.":[43],"While":[44],"clinically":[45],"valuable,":[46],"this":[47,156],"increases":[48],"potential":[50],"for":[51],"classification-level":[52],"circularity,":[53],"where":[54],"VEP":[55],"help":[57],"determine":[58],"classifications":[61,94],"later":[62],"used":[63,130],"train,":[65],"benchmark":[66],"calibrate":[68],"VEPs.":[69],"Here,":[70],"we":[71,168],"show":[72,102],"that":[73,170],"evidence":[75,142,176],"is":[76],"already":[77],"leaving":[78],"a":[79,89,103,160,185],"detectable":[80],"signature":[81],"ClinVar.":[83],"Among":[84],"rare":[85],"missense":[86],"from":[88],"major":[90],"submitter,":[91],"likely":[92],"benign":[93,99],"shifted":[95],"markedly":[96],"towards":[97],"more":[98],"scores":[100],"sharp":[104],"step":[105],"change":[106],"at":[107],"calibrated":[109],"moderate-evidence":[110],"threshold":[111],"BayesDel_noAF.":[113],"This":[114],"signal":[115],"extends":[116],"nearly":[118],"all":[119],"52":[120],"examined,":[122],"including":[123],"population-free":[124],"models":[125],"unlikely":[126],"have":[128],"been":[129],"classification,":[132,167],"probably":[133],"reflecting":[134],"shared":[135],"evolutionary":[136],"information.":[137],"Classifications":[138],"informed":[139],"by":[140],"therefore":[143],"cannot":[144,154],"be":[145],"treated":[146],"as":[147],"independent":[148],"ground":[149],"truth,":[150],"temporal":[152],"holdouts":[153],"eliminate":[155],"circularity.":[157],"To":[158],"prevent":[159],"self-reinforcing":[161],"feedback":[162],"loop":[163],"between":[164],"prediction":[165],"recommend":[169],"ClinVar":[171],"submissions":[172],"routinely":[173],"record":[174],"criteria":[177],"tools":[180],"supporting":[181],"each":[182],"standardised":[186],"format,":[187],"alongside":[188],"greater":[189],"use":[190],"classification-independent":[192],"benchmarks.":[193]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-28T00:00:00"}