{"doi":"10.1101/2020.12.16.423102","title":"<i>De novo</i> assembly of 64 haplotype-resolved human genomes of diverse ancestry and integrated analysis of structural variation","abstract":"Abstract Long-read and strand-specific sequencing technologies together facilitate the de novo assembly of high-quality haplotype-resolved human genomes without parent–child trio data. We present 64 assembled haplotypes from 32 diverse human genomes. These highly contiguous haplotype assemblies (average contig N50: 26 Mbp) integrate all forms of genetic variation across even complex loci such as the major histocompatibility complex. We focus on 107,590 structural variants (SVs), of which 68% are inaccessible by short-read sequencing. We identify new SV hotspots (spanning megabases of gene-rich sequence), characterize 130 of the most active mobile element source elements, and find that 63% of all SVs arise by homology-mediated mechanisms—a twofold increase from previous studies. Our resource now enables reliable graph-based genotyping from short reads of up to 50,340 SVs, resulting in the identification of 1,525 expression quantitative trait loci (SV-eQTLs) as well as SV candidates for adaptive selection within the human population.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2020,"id":122415,"datarank":0.3224521072623828,"base_score":1.791759469228055,"endowment":1.791759469228055,"self_citation_contribution":0.26876392038420827,"citation_network_contribution":0.05368818687817453,"self_endowment_contribution":0.26876392038420827,"citer_contribution":0.05368818687817453,"corpus_percentile":47.21126324746654,"corpus_rank":6825,"citation_count":5,"citer_count":3,"citers_with_citation_signal":3,"citers_with_endowment":3,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.846,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":19694,"name":"Peter A. Audano","orcid":"0000-0002-5187-0415","position":1,"is_corresponding":false},{"id":19733,"name":"Qihui Zhu","orcid":"0000-0003-2401-8443","position":2,"is_corresponding":false},{"id":14431,"name":"Bernardo Rodríguez–Martín","orcid":"0000-0003-4693-3140","position":3,"is_corresponding":false},{"id":19696,"name":"David Porubsky","orcid":"0000-0001-8414-8966","position":4,"is_corresponding":false},{"id":19712,"name":"Marc Jan Bonder","orcid":"0000-0002-8431-3180","position":5,"is_corresponding":false},{"id":19729,"name":"Arvis Sulovari","orcid":"0000-0003-4354-9020","position":6,"is_corresponding":false},{"id":231857,"name":"Jana Ebler","orcid":"0000-0002-0382-3702","position":7,"is_corresponding":false},{"id":19732,"name":"Weichen Zhou","orcid":"0000-0003-4755-1072","position":8,"is_corresponding":false},{"id":563548,"name":"Rebecca Serra Mari","orcid":"0000-0002-2812-9653","position":9,"is_corresponding":false},{"id":19697,"name":"Feyza Yilmaz","orcid":"0000-0001-8795-5800","position":10,"is_corresponding":false},{"id":19703,"name":"Xuefang Zhao","orcid":"0000-0003-4036-9577","position":11,"is_corresponding":false},{"id":289887,"name":"PingHsun Hsieh","orcid":"0000-0001-8294-6227","position":12,"is_corresponding":false},{"id":92298,"name":"Joyce Lee","orcid":"0000-0002-3492-1102","position":13,"is_corresponding":false},{"id":563549,"name":"Sushant Kumar","orcid":"0000-0002-0317-8520","position":14,"is_corresponding":false},{"id":24409,"name":"Jiadong Lin","orcid":"0000-0002-8116-5901","position":15,"is_corresponding":false},{"id":13956,"name":"Tobias Rausch","orcid":"0000-0001-5773-5620","position":16,"is_corresponding":false},{"id":563550,"name":"Yu Chen","orcid":"0000-0002-2037-7337","position":17,"is_corresponding":false},{"id":563551,"name":"Jingwen Ren","orcid":"0000-0002-3356-3008","position":18,"is_corresponding":false},{"id":227379,"name":"Martín Santamarina","orcid":"0000-0001-5914-0540","position":19,"is_corresponding":false},{"id":290630,"name":"Wolfram Höps","orcid":null,"position":20,"is_corresponding":false},{"id":19709,"name":"Hufsah Ashraf","orcid":"0000-0001-7760-0627","position":21,"is_corresponding":false},{"id":563552,"name":"Nelson T. Chuang","orcid":"0000-0002-2015-8935","position":22,"is_corresponding":false},{"id":563553,"name":"Xiaofei Yang","orcid":"0000-0002-5118-7755","position":23,"is_corresponding":false},{"id":19706,"name":"Katherine M. Munson","orcid":"0000-0001-8413-6498","position":24,"is_corresponding":false},{"id":30887,"name":"Alexandra P. Lewis","orcid":"0000-0002-6195-4786","position":25,"is_corresponding":false},{"id":563554,"name":"Susan Fairley","orcid":"0000-0001-9425-0788","position":26,"is_corresponding":false},{"id":290866,"name":"Luke J. Tallon","orcid":"0000-0002-4656-4480","position":27,"is_corresponding":false},{"id":87011,"name":"Wayne E. Clarke","orcid":"0000-0003-2471-0712","position":28,"is_corresponding":false},{"id":343977,"name":"Anna O. Basile","orcid":"0000-0001-5112-5880","position":29,"is_corresponding":false},{"id":550914,"name":"Marta Byrska-Bishop","orcid":"0000-0002-9118-1032","position":30,"is_corresponding":false},{"id":87010,"name":"André Corvelo","orcid":"0000-0003-0989-7806","position":31,"is_corresponding":false},{"id":19738,"name":"Mark J. P. Chaisson","orcid":"0000-0001-5395-1457","position":32,"is_corresponding":false},{"id":474710,"name":"Junjie Chen","orcid":"0000-0002-0483-303X","position":33,"is_corresponding":false},{"id":563555,"name":"Chong Li","orcid":"0000-0002-3802-1507","position":34,"is_corresponding":false},{"id":975,"name":"Harrison Brand","orcid":"0000-0002-7901-0812","position":35,"is_corresponding":false},{"id":24565,"name":"Aaron M. Wenger","orcid":"0000-0003-1183-0432","position":36,"is_corresponding":false},{"id":243998,"name":"Maryam Ghareghani","orcid":null,"position":37,"is_corresponding":false},{"id":19702,"name":"William T. Harvey","orcid":"0000-0003-0646-7528","position":38,"is_corresponding":false},{"id":13950,"name":"Benjamin Raeder","orcid":"0000-0002-9494-8884","position":39,"is_corresponding":false},{"id":19715,"name":"Patrick Hasenfeld","orcid":"0000-0003-2319-2482","position":40,"is_corresponding":false},{"id":30918,"name":"Allison A. Regier","orcid":"0000-0002-1932-8714","position":41,"is_corresponding":false},{"id":30913,"name":"Haley Abel","orcid":"0000-0003-3110-8041","position":42,"is_corresponding":false},{"id":108062,"name":"Ira M. Hall","orcid":"0000-0003-4442-6655","position":43,"is_corresponding":false},{"id":105371,"name":"Paul Flicek","orcid":"0000-0002-3897-7955","position":44,"is_corresponding":false},{"id":3589,"name":"Oliver Stegle","orcid":"0000-0002-8818-7193","position":45,"is_corresponding":false},{"id":108504,"name":"Mark Gerstein","orcid":"0000-0002-9746-3719","position":46,"is_corresponding":false},{"id":14457,"name":"José M. C. Tubío","orcid":"0000-0003-3540-2459","position":47,"is_corresponding":false},{"id":295012,"name":"Zepeng Mu","orcid":"0000-0002-7717-3247","position":48,"is_corresponding":false},{"id":295014,"name":"Yang Li","orcid":"0000-0002-0736-251X","position":49,"is_corresponding":false},{"id":19736,"name":"Xinghua Shi","orcid":"0000-0003-4662-3177","position":50,"is_corresponding":false},{"id":92296,"name":"Alex Hastie","orcid":"0000-0001-5829-2649","position":51,"is_corresponding":false},{"id":14259,"name":"Kai Ye","orcid":"0000-0002-2851-6741","position":52,"is_corresponding":false},{"id":13351,"name":"Zechen Chong","orcid":"0000-0001-5750-1808","position":53,"is_corresponding":false},{"id":30904,"name":"Ashley D. Sanders","orcid":"0000-0003-3945-0677","position":54,"is_corresponding":false},{"id":6273,"name":"Michael C. Zody","orcid":"0000-0001-6594-7199","position":55,"is_corresponding":false},{"id":1025,"name":"Michael E. Talkowski","orcid":"0000-0003-2889-0992","position":56,"is_corresponding":false},{"id":19734,"name":"Ryan E. Mills","orcid":"0000-0003-3425-6998","position":57,"is_corresponding":false},{"id":19735,"name":"Scott E. Devine","orcid":"0000-0001-7629-8331","position":58,"is_corresponding":false},{"id":19741,"name":"Charles Lee","orcid":"0000-0001-7317-6662","position":59,"is_corresponding":false},{"id":108507,"name":"Jan O. Korbel","orcid":"0000-0002-2798-3794","position":60,"is_corresponding":false},{"id":6321,"name":"Tobias Marschall","orcid":"0000-0002-9376-1030","position":61,"is_corresponding":false},{"id":2125,"name":"Evan E. Eichler","orcid":"0000-0002-8246-4014","position":62,"is_corresponding":false},{"id":19693,"name":"Peter Ebert","orcid":"0000-0001-7441-532X","position":0,"is_corresponding":true}],"reference_count":86,"raw_metadata":null,"created_at":"2026-07-18T23:14:51.076430Z","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":[]}