{"doi":"10.1101/187096","title":"KoVariome: Korean National Standard Reference Variome database of whole genomes with comprehensive SNV, indel, CNV, and SV analyses","abstract":"<jats:title>Abstract</jats:title>\n                <jats:p>High-coverage whole-genome sequencing data of a single ethnicity can provide a useful catalogue of population-specific genetic variations. Herein, we report a comprehensive analysis of the Korean population, and present the Korean National Standard Reference Variome (KoVariome). As a part of the Korean Personal Genome Project (KPGP), we constructed the KoVariome database using 5.5 terabases of whole genome sequence data from 50 healthy Korean individuals with an average coverage depth of 31×. In total, KoVariome includes 12.7M single-nucleotide variants (SNVs), 1.7M short insertions and deletions (indels), 4K structural variations (SVs), and 3.6K copy number variations (CNVs). Among them, 2.4M (19%) SNVs and 0.4M (24%) indels were identified as novel. We also discovered selective enrichment of 3.8M SNVs and 0.5M indels in Korean individuals, which were used to filter out 1,271 coding-SNVs not originally removed from the 1,000 Genomes Project data when prioritizing disease-causing variants. CNV analyses revealed gene losses related to bone mineral densities and duplicated genes involved in brain development and fat reduction. Finally, KoVariome health records were used to identify novel disease-causing variants in the Korean population, demonstrating the value of high-quality ethnic variation databases for the accurate interpretation of individual genomes and the precise characterization of genetic variations.</jats:p>","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":null,"id":14359,"datarank":0.45113664213549576,"base_score":1.791759469228055,"endowment":1.791759469228055,"self_citation_contribution":0.26876392038420827,"citation_network_contribution":0.18237272175128746,"self_endowment_contribution":0.26876392038420827,"citer_contribution":0.18237272175128746,"corpus_percentile":58.21149531987314,"corpus_rank":5403,"citation_count":5,"citer_count":5,"citers_with_citation_signal":5,"citers_with_endowment":5,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":111118,"name":"Jessica A. Weber","orcid":"0000-0001-8405-4396","position":1,"is_corresponding":false},{"id":111119,"name":"Sungwoong Jho","orcid":null,"position":2,"is_corresponding":false},{"id":111120,"name":"Jinho Jang","orcid":null,"position":3,"is_corresponding":false},{"id":111121,"name":"JeHoon Jun","orcid":null,"position":4,"is_corresponding":false},{"id":31943,"name":"Yun Sung Cho","orcid":"0000-0003-4490-8769","position":5,"is_corresponding":false},{"id":111122,"name":"Hak-Min Kim","orcid":null,"position":6,"is_corresponding":false},{"id":111123,"name":"Hyunho Kim","orcid":null,"position":7,"is_corresponding":false},{"id":111124,"name":"Yumi Kim","orcid":null,"position":8,"is_corresponding":false},{"id":111125,"name":"OkSung Chung","orcid":null,"position":9,"is_corresponding":false},{"id":31986,"name":"Chang Geun Kim","orcid":"0009-0003-3422-8361","position":10,"is_corresponding":false},{"id":111126,"name":"HyeJin Lee","orcid":null,"position":11,"is_corresponding":false},{"id":111127,"name":"Byung Chul Kim","orcid":null,"position":12,"is_corresponding":false},{"id":111128,"name":"Kyudong Han","orcid":null,"position":13,"is_corresponding":false},{"id":111129,"name":"InSong Koh","orcid":null,"position":14,"is_corresponding":false},{"id":31985,"name":"Kyun Shik Chae","orcid":"0000-0002-3038-6974","position":15,"is_corresponding":false},{"id":20472,"name":"Semin Lee","orcid":"0000-0002-9015-6046","position":16,"is_corresponding":false},{"id":111130,"name":"Jeremy S. Edwards","orcid":null,"position":17,"is_corresponding":false},{"id":31992,"name":"Jong Bhak","orcid":"0000-0002-4228-1299","position":18,"is_corresponding":false},{"id":31941,"name":"Jungeun Kim","orcid":"0000-0002-6576-5456","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":1.791759469228055,"endowment":1.791759469228055,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"24259432","pmcid":null,"openalex_id":"https://openalex.org/W2754643976","authors":[],"funders":[],"total_grants":0,"fwci":null,"citation_percentile":null,"influential_citations":0,"citation_trend":[{"year":2021,"count":3},{"year":2023,"count":1},{"year":2024,"count":1}],"oa_status":"green","license":"https://www.biorxiv.org/about/FAQ#license","oa_locations":[{"url":"https://www.biorxiv.org/content/biorxiv/early/2017/09/12/187096.full.pdf","host_type":"repository"},{"url":"https://www.biorxiv.org/content/biorxiv/early/2017/09/12/187096.full.pdf","host_type":"repository"},{"url":"https://syndication.highwire.org/content/doi/10.1101/187096","host_type":"publisher"},{"url":"https://doi.org/10.1101/187096","host_type":"repository"}],"fields_of_study":["Genomic variations and chromosomal abnormalities","Genomics and Rare Diseases","Genetic Associations and Epidemiology"],"mesh_terms":[],"keywords":["Indel","1000 Genomes Project","Genome","Copy-number variation","Reference genome","Genetics","Biology","Whole genome sequencing","Population","Structural variation","Human genome","Single-nucleotide polymorphism","Gene","Coding region","Computational biology","Medicine","Genotype"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-01T09:00:22.104843Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}