{"id":"https://openalex.org/W4237520300","doi":"https://doi.org/10.12688/f1000research.15895.1","title":"NovoGraph: Genome graph construction from multiple long-read de novo assemblies","display_name":"NovoGraph: Genome graph construction from multiple long-read de novo assemblies","publication_year":2018,"publication_date":"2018-09-03","ids":{"openalex":"https://openalex.org/W4237520300","doi":"https://doi.org/10.12688/f1000research.15895.1"},"language":"en","primary_location":{"id":"doi:10.12688/f1000research.15895.1","is_oa":true,"landing_page_url":"https://doi.org/10.12688/f1000research.15895.1","pdf_url":"https://f1000research.com/articles/7-1391/v1/pdf","source":{"id":"https://openalex.org/S4210239046","display_name":"F1000Research","issn_l":"2046-1402","issn":["2046-1402"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320357","host_organization_name":"Faculty of 1000","host_organization_lineage":["https://openalex.org/P4310320357"],"host_organization_lineage_names":["Faculty of 1000"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"F1000Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://f1000research.com/articles/7-1391/v1/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088011223","display_name":"Evan Biederstedt","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4210151462","display_name":"New York Genome Center","ror":"https://ror.org/05wf2ga96","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210151462"]},{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan Biederstedt","raw_affiliation_strings":["New York Genome Center, New York, NY, 10013","Weill Cornell Medicine, New York, NY, 10065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York Genome Center, New York, NY, 10013","institution_ids":["https://openalex.org/I4210151462"]},{"raw_affiliation_string":"Weill Cornell Medicine, New York, NY, 10065","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061875763","display_name":"Jeffrey C. Oliver","orcid":"https://orcid.org/0000-0003-2160-1086"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey C. Oliver","raw_affiliation_strings":["Office of Digital Innovation and Stewardship, University Libraries, University of Arizona, Tucson, AZ, 85721"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Office of Digital Innovation and Stewardship, University Libraries, University of Arizona, Tucson, AZ, 85721","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057230759","display_name":"Nancy F. Hansen","orcid":"https://orcid.org/0000-0002-0950-0699"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210090236","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210090236"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nancy F. Hansen","raw_affiliation_strings":["National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, 20817"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, 20817","institution_ids":["https://openalex.org/I4210090236","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011137240","display_name":"Aarti Jajoo","orcid":null},"institutions":[{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aarti Jajoo","raw_affiliation_strings":["Baylor College of Medicine, Houston, TX, 77030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baylor College of Medicine, Houston, TX, 77030","institution_ids":["https://openalex.org/I181547552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103111584","display_name":"Nathan Dunn","orcid":"https://orcid.org/0000-0002-4862-3181"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Dunn","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, 94720"],"raw_orcid":"https://orcid.org/0000-0002-4862-3181","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, 94720","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089477212","display_name":"Andrew Olson","orcid":"https://orcid.org/0000-0003-4946-9021"},"institutions":[{"id":"https://openalex.org/I2750212522","display_name":"Cold Spring Harbor Laboratory","ror":"https://ror.org/02qz8b764","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2750212522"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Olson","raw_affiliation_strings":["Cold Spring Harbor Laboratory, Cold Spring Harbor, NY, 11724"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cold Spring Harbor Laboratory, Cold Spring Harbor, NY, 11724","institution_ids":["https://openalex.org/I2750212522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070603357","display_name":"Ben Busby","orcid":"https://orcid.org/0000-0001-5267-4988"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Busby","raw_affiliation_strings":["National Center for Biotechnology Information, National Institutes of Health, Bethesda, MD, 20817"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Institutes of Health, Bethesda, MD, 20817","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061035699","display_name":"Alexander Dilthey","orcid":"https://orcid.org/0000-0002-6394-4581"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210090236","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210090236"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Alexander T. Dilthey","raw_affiliation_strings":["Institute of Medical Microbiology and Hospital Hygiene, Heinrich Heine University D\u00fcsseldorf, D\u00fcsseldorf, 40225","National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, 20817"],"raw_orcid":"https://orcid.org/0000-0002-6394-4581","affiliations":[{"raw_affiliation_string":"Institute of Medical Microbiology and Hospital Hygiene, Heinrich Heine University D\u00fcsseldorf, D\u00fcsseldorf, 40225","institution_ids":["https://openalex.org/I44260953"]},{"raw_affiliation_string":"National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, 20817","institution_ids":["https://openalex.org/I4210090236","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.4942,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.63122003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"1391","last_page":"1391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9977999925613403,"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/genome","display_name":"Genome","score":0.7460620403289795},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6186242699623108},{"id":"https://openalex.org/keywords/contig","display_name":"Contig","score":0.5858339071273804},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.49729207158088684},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4832933247089386},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.45314037799835205},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.44323915243148804},{"id":"https://openalex.org/keywords/structural-variation","display_name":"Structural variation","score":0.442994624376297},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.43143680691719055},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.20929065346717834}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7460620403289795},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6186242699623108},{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.5858339071273804},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.49729207158088684},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4832933247089386},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.45314037799835205},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.44323915243148804},{"id":"https://openalex.org/C151020129","wikidata":"https://www.wikidata.org/wiki/Q7625067","display_name":"Structural variation","level":4,"score":0.442994624376297},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.43143680691719055},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.20929065346717834},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.12688/f1000research.15895.1","is_oa":true,"landing_page_url":"https://doi.org/10.12688/f1000research.15895.1","pdf_url":"https://f1000research.com/articles/7-1391/v1/pdf","source":{"id":"https://openalex.org/S4210239046","display_name":"F1000Research","issn_l":"2046-1402","issn":["2046-1402"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320357","host_organization_name":"Faculty of 1000","host_organization_lineage":["https://openalex.org/P4310320357"],"host_organization_lineage_names":["Faculty of 1000"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"F1000Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.12688/f1000research.15895.1","is_oa":true,"landing_page_url":"https://doi.org/10.12688/f1000research.15895.1","pdf_url":"https://f1000research.com/articles/7-1391/v1/pdf","source":{"id":"https://openalex.org/S4210239046","display_name":"F1000Research","issn_l":"2046-1402","issn":["2046-1402"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320357","host_organization_name":"Faculty of 1000","host_organization_lineage":["https://openalex.org/P4310320357"],"host_organization_lineage_names":["Faculty of 1000"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"F1000Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320311808","display_name":"J\u00fcrgen Manchot Stiftung","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4237520300.pdf","grobid_xml":"https://content.openalex.org/works/W4237520300.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W13438323","https://openalex.org/W1912672559","https://openalex.org/W1978981589","https://openalex.org/W2002438422","https://openalex.org/W2021341670","https://openalex.org/W2095680943","https://openalex.org/W2108234281","https://openalex.org/W2117131162","https://openalex.org/W2149992227","https://openalex.org/W2159084616","https://openalex.org/W2160378127","https://openalex.org/W2166593999","https://openalex.org/W2170215295","https://openalex.org/W2208231423","https://openalex.org/W2336256486","https://openalex.org/W2464063823","https://openalex.org/W2513582464","https://openalex.org/W2527072329","https://openalex.org/W2527708324","https://openalex.org/W2543066836","https://openalex.org/W2603734366","https://openalex.org/W2607669908","https://openalex.org/W2759456806","https://openalex.org/W2760599003","https://openalex.org/W2776539412","https://openalex.org/W2808544288","https://openalex.org/W2950121474","https://openalex.org/W2952366981","https://openalex.org/W2952379406","https://openalex.org/W2952870794","https://openalex.org/W2953263404","https://openalex.org/W4394666350"],"related_works":["https://openalex.org/W54719527","https://openalex.org/W4283384467","https://openalex.org/W2327661880","https://openalex.org/W4225379983","https://openalex.org/W2794975275","https://openalex.org/W2903971379","https://openalex.org/W2952558289","https://openalex.org/W3179112149","https://openalex.org/W2128222086","https://openalex.org/W4402988713"],"abstract_inverted_index":{"<ns4:p>":[0,122],"Genome":[1],"graphs":[2,49,99,175],"are":[3,50],"emerging":[4],"as":[5],"an":[6],"important":[7],"novel":[8],"approach":[9],"to":[10,109,163],"the":[11,33,43,80,102,130,165,227,231],"analysis":[12,35],"of":[13,36,42,74,83,89,105,132,140,151,160,208,235,249],"high-throughput":[14],"sequencing":[15,62],"data.":[16],"By":[17],"explicitly":[18],"representing":[19],"genetic":[20,106],"variants":[21,117],"and":[22,39,66,118,155,200],"alternative":[23],"haplotypes":[24],"in":[25,176],"a":[26,77,84,127,133,138,146,157,170,193,245],"mappable":[27],"data":[28],"structure,":[29],"they":[30],"can":[31,180],"enable":[32],"improved":[34],"structurally":[37],"variable":[38],"hyperpolymorphic":[40],"regions":[41],"genome.":[44],"In":[45],"most":[46],"existing":[47],"approaches,":[48],"constructed":[51,228],"from":[52,57,87,137,204,237],"variant":[53,198,202],"call":[54],"sets":[55,88],"derived":[56],"short-read":[58],"sequencing.":[59],"As":[60],"long-read":[61],"becomes":[63],"more":[64],"cost-effective":[65],"enables":[67],"<ns4:italic>de":[68,111,141,205],"novo</ns4:italic>":[69,112,142,206],"assembly":[70],"for":[71,79,129],"increasing":[72],"numbers":[73],"whole":[75],"genomes,":[76],"method":[78,128],"direct":[81],"construction":[82,131],"genome":[85,98,134,185,194],"graph":[86,135,186,195,229],"assembled":[90],"human":[91,212],"genomes":[92,213],"would":[93,100],"be":[94,181],"desirable.":[95],"Such":[96],"assembly-based":[97],"encompass":[101],"wide":[103],"spectrum":[104],"variation":[107],"accessible":[108],"long-read-based":[110],"assembly,":[113],"including":[114],"large":[115],"structural":[116],"divergent":[119],"haplotypes.":[120],"</ns4:p>":[121,254],"Here":[123],"we":[124,191],"present":[125],"NovoGraph,":[126,190],"directly":[136],"set":[139],"assemblies.":[143],"NovoGraph":[144,172],"constructs":[145],"genome-wide":[147],"multiple":[148,166],"sequence":[149,167],"alignment":[150,168],"all":[152],"input":[153],"contigs":[154],"uses":[156],"simple":[158],"criterion":[159],"homologous-identical":[161],"recombination":[162],"convert":[164],"into":[169,183],"graph.":[171],"outputs":[173],"resulting":[174],"VCF":[177],"format":[178],"that":[179,224,251],"loaded":[182],"third-party":[184],"toolkits.":[187],"To":[188],"demonstrate":[189],"construct":[192],"with":[196],"23,478,835":[197],"sites":[199],"30,582,795":[201],"alleles":[203],"assemblies":[207],"seven":[209],"ethnically":[210],"diverse":[211],"(AK1,":[214],"CHM1,":[215],"CHM13,":[216],"HG003,":[217],"HG004,":[218],"HX1,":[219],"NA19240).":[220],"Initial":[221],"evaluations":[222],"show":[223],"mapping":[225],"against":[226],"reduces":[230],"average":[232],"mismatch":[233],"rate":[234,248],"reads":[236,250],"sample":[238],"NA12878":[239],"by":[240],"approximately":[241],"0.2%,":[242],"albeit":[243],"at":[244],"slightly":[246],"increased":[247],"remain":[252],"unmapped.":[253]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}