{"id":"https://openalex.org/W4407113649","doi":"https://doi.org/10.1186/s12859-026-06453-9","title":"vcfsim: flexible simulation of all-sites VCFs with missing data","display_name":"vcfsim: flexible simulation of all-sites VCFs with missing data","publication_year":2026,"publication_date":"2026-04-28","ids":{"openalex":"https://openalex.org/W4407113649","doi":"https://doi.org/10.1186/s12859-026-06453-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/41040272"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06453-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06453-9","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-026-06453-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Paimon Goulart","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paimon Goulart","raw_affiliation_strings":["Department of Computer Science and Engineering, The University of California, Riverside","The University of California, Riverside"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"The University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001324802","display_name":"Kieran Samuk","orcid":"https://orcid.org/0000-0003-0396-465X"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kieran Samuk","raw_affiliation_strings":["Department of Evolution, Ecology, and Organismal Biology, The University of California, Riverside","The University of California, Riverside"],"raw_orcid":"https://orcid.org/0000-0003-0396-465X","affiliations":[{"raw_affiliation_string":"Department of Evolution, Ecology, and Organismal Biology, The University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"The University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001324802"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":11.65,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97120555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.46459999680519104,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.46459999680519104,"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/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.19840000569820404,"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/T10012","display_name":"Genetic diversity and population structure","score":0.1143999993801117,"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/missing-data","display_name":"Missing data","score":0.6438822746276855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5136279463768005},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10397914052009583}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6438822746276855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5136279463768005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10397914052009583}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1186/s12859-026-06453-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06453-9","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"doi:10.1101/2025.01.29.635540","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.01.29.635540","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/09/28/2025.01.29.635540.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,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:41040272","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41040272","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmid:42050398","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42050398","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:11298056","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12486129","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:4b00942d6b6f45dbb5a7dc1cca716943","is_oa":false,"landing_page_url":"https://doaj.org/article/4b00942d6b6f45dbb5a7dc1cca716943","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12486129","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12486129/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:13267514","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13267514/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06453-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06453-9","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2100155156","display_name":"The evolution and genetics of recombination rate variation","funder_award_id":"1r35gm154837-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2061939373","https://openalex.org/W2149992227","https://openalex.org/W2519552481","https://openalex.org/W2765745983","https://openalex.org/W2789779178","https://openalex.org/W2888809732","https://openalex.org/W3035965352","https://openalex.org/W3099878876","https://openalex.org/W3123129704","https://openalex.org/W3131055609","https://openalex.org/W4221069327","https://openalex.org/W4309026780","https://openalex.org/W6911590169","https://openalex.org/W6949489713"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W4289597203","https://openalex.org/W2085630472"],"abstract_inverted_index":{"BACKGROUND:":[0],"VCFs":[1,16,118,156,170],"are":[2,26,44,50,181],"the":[3,29,79,113,143,168,199,208,233,249,252],"most":[4],"widely":[5],"used":[6],"data":[7,20,43,49,70,191,202,256],"format":[8],"for":[9,28,125,153,232],"encoding":[10],"genetic":[11,84,178,241],"variation.":[12],"By":[13],"design,":[14],"standard":[15,98],"do":[17,36],"not":[18,37],"include":[19,93],"from":[21,40],"sites":[22,41,95,108],"where":[23,42],"all":[24,58],"individuals":[25],"homozygous":[27],"reference":[30],"allele":[31],"(\u201cinvariant":[32],"sites\u201d)":[33],"and":[34,62,106,149,162,197,218,229,248],"thus":[35],"differentiate":[38],"these":[39],"completely":[45],"missing.":[46],"However,":[47],"missing":[48,69,105,163,190,255],"a":[51,73,97,120,193,227],"key":[52,82],"feature":[53],"of":[54,60,75,81,116,160,195,201,210,235,244,251,254],"biological":[55],"datasets":[56],"across":[57],"domains":[59],"genomics,":[61],"many":[63],"recent":[64],"studies":[65],"have":[66],"shown":[67],"that":[68,140,167],"can":[71],"introduce":[72,134,189],"variety":[74,194],"statistical":[76],"biases":[77],"in":[78,96,192,257],"estimation":[80],"population":[83,177,219,240],"parameters.":[85],"A":[86],"solution":[87],"to":[88,92,112,184],"this":[89],"limitation":[90],"is":[91,119,226],"invariant":[94,107],"VCF,":[99],"creating":[100],"an":[101,135],"\u201call-sites":[102],"VCF\u201d,":[103],"exposing":[104],"explicitly.":[109],"One":[110],"hurdle":[111],"wider":[114],"adoption":[115],"all-sites":[117,129,155],"reliable":[121],"parameterized":[122],"simulation":[123,146,200,209],"framework":[124],"generating":[126],"biologically":[127],"realistic":[128],"VCFs.":[130],"RESULTS:":[131],"Here,":[132],"we":[133],"open-source":[136],"command-line":[137],"tool,":[138],"vcfsim,":[139],"interfaces":[141],"with":[142,157,176,203],"popular":[144],"coalescent":[145],"platform":[147],"msprime":[148,186],"provides":[150],"convenience":[151],"functions":[152],"simulating":[154],"variable":[158],"levels":[159],"ploidy":[161,205,212],"data.":[164],"We":[165],"show":[166],"post-processed":[169],"generated":[171],"using":[172],"vcfsim":[173,225],"align":[174],"precisely":[175],"expectations":[179],"(i.e.":[180],"statistically":[182],"identical":[183],"raw":[185],"output),":[187],"accurately":[188],"patterns,":[196],"permit":[198],"varying":[204],"levels,":[206],"including":[207],"intraindividual":[211],"variation":[213],"(e.g.":[214],"heterogametic":[215],"sex":[216],"chromosomes)":[217],"structures.":[220],"CONCLUSIONS:":[221],"Our":[222],"results":[223],"demonstrate":[224],"useful":[228],"easy-to-use":[230],"tool":[231],"benchmarking":[234],"new":[236],"software":[237],"tools,":[238],"performing":[239],"inference,":[242],"training":[243],"machine":[245],"learning":[246],"models,":[247],"exploration":[250],"effects":[253],"genomics":[258],"datasets.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}