{"id":"https://openalex.org/W7214645914","doi":"https://doi.org/10.64898/2026.09.22.753614","title":"vep-rs: high-throughput Rust variant annotation with population-scale concordance to Ensembl VEP","display_name":"vep-rs: high-throughput Rust variant annotation with population-scale concordance to Ensembl VEP","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214645914","doi":"https://doi.org/10.64898/2026.09.22.753614"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.22.753614","doi":"https://doi.org/10.64898/2026.09.22.753614","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753614","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753614.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/2026/09/28/2026.09.22.753614.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152465914","display_name":"Matthew Porter","orcid":"https://orcid.org/0009-0001-4316-5185","observed_orcids":["https://orcid.org/0009-0001-4316-5185"]},"institutions":[{"id":"https://openalex.org/I4210124610","display_name":"Natera (United States)","ror":"https://ror.org/02anzyy56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124610"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew Porter","raw_affiliation_strings":["Real-World Data Engineering, Natera, Inc., 13011 McCallen Pass, Building A, Suite 100, Austin, TX 78753, USA"],"raw_orcid":"https://orcid.org/0009-0001-4316-5185","affiliations":[{"raw_affiliation_string":"Real-World Data Engineering, Natera, Inc., 13011 McCallen Pass, Building A, Suite 100, Austin, TX 78753, USA","institution_ids":["https://openalex.org/I4210124610"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153388836","display_name":"Robert Borkowski","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210124610","display_name":"Natera (United States)","ror":"https://ror.org/02anzyy56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124610"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Borkowski","raw_affiliation_strings":["Real-World Data Engineering, Natera, Inc., 13011 McCallen Pass, Building A, Suite 100, Austin, TX 78753, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Real-World Data Engineering, Natera, Inc., 13011 McCallen Pass, Building A, Suite 100, Austin, TX 78753, USA","institution_ids":["https://openalex.org/I4210124610"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5152465914"],"corresponding_institution_ids":["https://openalex.org/I4210124610"],"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":0.9550999999046326,"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":0.9550999999046326,"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":0.03739999979734421,"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"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.0026000000070780516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ensembl-vep","display_name":"Ensembl VEP","score":0.9089999794960022},{"id":"https://openalex.org/keywords/sequence-ontology","display_name":"Sequence Ontology","score":0.6859999895095825},{"id":"https://openalex.org/keywords/structural-variants","display_name":"structural variants","score":0.5690000057220459},{"id":"https://openalex.org/keywords/splice-site-variant","display_name":"splice site mutation","score":0.4959999918937683},{"id":"https://openalex.org/keywords/clinvar","display_name":"ClinVar","score":0.578000009059906},{"id":"https://openalex.org/keywords/gnomad","display_name":"gnomAD","score":0.9629999995231628},{"id":"https://openalex.org/keywords/1000-genomes-project","display_name":"1000 Genomes Project","score":0.9819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5863999724388123},{"id":"https://openalex.org/C141674004","wikidata":"https://www.wikidata.org/wiki/Q1344256","display_name":"Ensembl","level":5,"score":0.579200029373169},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.49129998683929443},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44940000772476196},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C197781089","wikidata":"https://www.wikidata.org/wiki/Q575650","display_name":"Rust (programming language)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3596999943256378},{"id":"https://openalex.org/C160798450","wikidata":"https://www.wikidata.org/wiki/Q4230870","display_name":"Concordance","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C2776408758","wikidata":"https://www.wikidata.org/wiki/Q10375461","display_name":"Symbiodinium","level":4,"score":0.329800009727478},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.2969000041484833},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.2874999940395355},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.2662999927997589},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.22.753614","doi":"https://doi.org/10.64898/2026.09.22.753614","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753614","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753614.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:10.64898/2026.09.22.753614","doi":"https://doi.org/10.64898/2026.09.22.753614","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753614","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753614.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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214645914.pdf","grobid_xml":"https://content.openalex.org/works/W7214645914.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7154601886"],"related_works":["https://openalex.org/W7154601886","https://openalex.org/W7161168368","https://openalex.org/W6911845606","https://openalex.org/W7098185140","https://openalex.org/W3175980491","https://openalex.org/W7100204906","https://openalex.org/W2145809383","https://openalex.org/W2417483443","https://openalex.org/W7096742743","https://openalex.org/W2747135357"],"abstract_inverted_index":{"Abstract":[0],"Summary":[1],"Ensembl":[2,45],"VEP":[3,46,52,102,116,155,180,205,254],"is":[4,25,152,161,177],"the":[5,20,133,147,236],"de":[6],"facto":[7],"reference":[8],"for":[9],"variant":[10,69,225,237],"consequence":[11,53,129,214,255],"annotation,":[12],"but":[13],"its":[14,34,296],"Perl":[15],"implementation":[16,294],"limits":[17],"throughput,":[18,282],"and":[19,74,80,84,95,146,164,174,188,242,269,272,283,293,300],"open":[21],"reimplementation":[22,43],"benchmarked":[23],"here":[24],"validated":[26],"on":[27,92,103,125,150,168,183,190,246,253],"a":[28,41,56,62,154,213,219,224,229,234,262],"set":[29,119],"too":[30],"small":[31],"to":[32,123,278,289],"bound":[33],"disagreement":[35],"with":[36,113],"it.":[37],"We":[38],"present":[39],"vep-rs,":[40,295],"Rust":[42],"of":[44,132,201],"release":[47,206],"115.2,":[48],"audited":[49],"over":[50],"260,638,766":[51],"tuples,":[54,105],"each":[55],"(location,":[57],"allele,":[58],"feature)":[59],"key":[60],"carrying":[61,138],"Sequence":[63,135],"Ontology":[64,136],"term":[65,221],"set,":[66],"from":[67,101,223],"six":[68,94],"datasets":[70],"(ClinVar,":[71],"gnomAD":[72],"chr21,":[73],"1000":[75],"Genomes":[76],"chr21":[77],"across":[78],"GRCh37":[79],"GRCh38).":[81],"On":[82,157],"SNPs":[83],"indels":[85],"vep-rs":[86,176,209,260],"emits":[87],"exactly":[88],"VEP\u2019s":[89,267,281],"tuple":[90],"count":[91],"all":[93,126],"attains":[96],"F1":[97,121,144,160],"\u2265":[98],"0.999974,":[99],"differing":[100],"3,169":[104],"at":[106,139,276,287,309,314,323],"most":[107],"one":[108],"in":[109,204,228],"38,000":[110],"per":[111,172],"dataset;":[112],"two":[114],"documented":[115],"defect":[117],"shapes":[118],"aside,":[120],"rounds":[122],"1.000000":[124],"six.":[127],"Per":[128],"class,":[130],"29":[131],"30":[134],"terms":[137,256],"least":[140],"1,000":[141],"tuples":[142],"exceed":[143],"0.99,":[145],"lowest,":[148],"0.540":[149],"start_retained_variant,":[151],"entirely":[153],"defect.":[156],"structural":[158],"variants,":[159],"0.975395":[162],"(GRCh37)":[163],"0.909998":[165],"(GRCh38).":[166],"Timed":[167],"20":[169],"independent":[170],"machines":[171],"engine":[173],"architecture,":[175],"faster":[178],"than":[179],"by":[181],"101\u00d7-284\u00d7":[182],"ARM":[184],"(geometric":[185,192],"mean":[186,193],"176\u00d7)":[187],"78.3\u00d7-192\u00d7":[189],"x86":[191],"135\u00d7).":[194],"Five":[195],"divergence":[196],"classes":[197],"are":[198,305,321],"documented,":[199],"four":[200],"them":[202],"defects":[203],"115":[207],"that":[208,216,226,244],"does":[210,238],"not":[211,239],"reproduce:":[212],"call":[215],"contradicts":[217],"itself,":[218],"splice-region":[220],"dropped":[222],"lies":[227],"splice":[230],"region,":[231],"annotation":[232],"against":[233,261],"chromosome":[235],"lie":[240],"on,":[241],"output":[243],"depends":[245],"input":[247],"batch":[248],"composition.":[249],"A":[250],"pipeline":[251],"keyed":[252],"can":[257],"therefore":[258],"adopt":[259],"measured,":[263],"per-term":[264],"bound,":[265],"shed":[266],"contradictory":[268],"batch-dependent":[270],"calls,":[271],"annotate":[273],"population-scale":[274],"inputs":[275],"78.3":[277],"284":[279],"times":[280],"per-file":[284],"structural-variant":[285],"sets":[286],"22.5":[288],"52.9":[290],"times.":[291],"Availability":[292],"harness,":[297],"both":[298],"comparators,":[299],"every":[301],"per-machine":[302],"wall":[303],"time":[304],"released":[306],"under":[307],"Apache-2.0":[308],"https://github.com/natera-open-source/vep-rs":[310],"(release":[311],"v0.1.0,":[312],"archived":[313],"https://doi.org/10.5281/zenodo.22837897":[315],").":[316],"Supplementary":[317,319],"information":[318],"data":[320],"available":[322],"Bioinformatics":[324],"online.":[325]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-29T00:00:00"}