{"id":"https://openalex.org/W2171057071","doi":"https://doi.org/10.1136/amiajnl-2013-002147","title":"HUGO: Hierarchical mUlti-reference Genome cOmpression for aligned reads","display_name":"HUGO: Hierarchical mUlti-reference Genome cOmpression for aligned reads","publication_year":2013,"publication_date":"2013-12-25","ids":{"openalex":"https://openalex.org/W2171057071","doi":"https://doi.org/10.1136/amiajnl-2013-002147","mag":"2171057071"},"language":"en","primary_location":{"id":"doi:10.1136/amiajnl-2013-002147","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2013-002147","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/2/363/17375891/21-2-363.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/jamia/article-pdf/21/2/363/17375891/21-2-363.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056560880","display_name":"Pinghao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pinghao Li","raw_affiliation_strings":["EE Department, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"EE Department, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458864","display_name":"Xiaoqian Jiang","orcid":"https://orcid.org/0000-0001-9933-2205"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoqian Jiang","raw_affiliation_strings":["Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA"],"affiliations":[{"raw_affiliation_string":"Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375563","display_name":"Shuang Wang","orcid":"https://orcid.org/0000-0001-9193-4324"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Wang","raw_affiliation_strings":["Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA"],"affiliations":[{"raw_affiliation_string":"Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377802","display_name":"Ji\u2010Hoon Kim","orcid":"https://orcid.org/0000-0002-5212-1686"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jihoon Kim","raw_affiliation_strings":["Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA"],"affiliations":[{"raw_affiliation_string":"Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["EE Department, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"EE Department, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084415954","display_name":"Lucila Ohno\u2010Machado","orcid":"https://orcid.org/0000-0002-8005-7327"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucila Ohno-Machado","raw_affiliation_strings":["Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA"],"affiliations":[{"raw_affiliation_string":"Division of Biomedical Informatics, University of California\u2013San Diego, La Jolla, California, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056560880"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":{"value":3967,"currency":"USD","value_usd":3967},"fwci":1.6444,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.83987102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"21","issue":"2","first_page":"363","last_page":"373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987999796867371,"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":0.9987999796867371,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.663296103477478},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6064454317092896},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5472939610481262},{"id":"https://openalex.org/keywords/whole-genome-sequencing","display_name":"Whole genome sequencing","score":0.49002134799957275},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44186466932296753},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4196200966835022},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.37557855248451233},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.3725156784057617},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3501654863357544},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34086737036705017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2448507845401764},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18210896849632263},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15380948781967163},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12209761142730713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.663296103477478},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6064454317092896},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5472939610481262},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.49002134799957275},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44186466932296753},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4196200966835022},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37557855248451233},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3725156784057617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3501654863357544},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34086737036705017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2448507845401764},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18210896849632263},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15380948781967163},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12209761142730713}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1136/amiajnl-2013-002147","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2013-002147","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/2/363/17375891/21-2-363.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:2913796","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3932469","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1136/amiajnl-2013-002147","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2013-002147","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/2/363/17375891/21-2-363.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2171057071.pdf","grobid_xml":"https://content.openalex.org/works/W2171057071.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1513515886","https://openalex.org/W1973878786","https://openalex.org/W1977922553","https://openalex.org/W2010928148","https://openalex.org/W2012016911","https://openalex.org/W2013733655","https://openalex.org/W2015292449","https://openalex.org/W2032046925","https://openalex.org/W2049881004","https://openalex.org/W2051929999","https://openalex.org/W2055043387","https://openalex.org/W2086399100","https://openalex.org/W2092880969","https://openalex.org/W2096791516","https://openalex.org/W2108234281","https://openalex.org/W2111044311","https://openalex.org/W2117683095","https://openalex.org/W2119180969","https://openalex.org/W2120989936","https://openalex.org/W2124985265","https://openalex.org/W2127218421","https://openalex.org/W2128114769","https://openalex.org/W2135771747","https://openalex.org/W2138196010","https://openalex.org/W2159084616","https://openalex.org/W2161628678","https://openalex.org/W2166588423","https://openalex.org/W2168133698","https://openalex.org/W2171777347","https://openalex.org/W2885727518","https://openalex.org/W4236236547"],"related_works":["https://openalex.org/W2921363728","https://openalex.org/W2279684808","https://openalex.org/W3217304749","https://openalex.org/W2066142713","https://openalex.org/W2894932706","https://openalex.org/W2582968398","https://openalex.org/W4223446368","https://openalex.org/W4232517363","https://openalex.org/W3214020344","https://openalex.org/W4367367790"],"abstract_inverted_index":{"Background":[0],"and":[1,42,78,117,143],"objective":[2],"Short-read":[3],"sequencing":[4],"is":[5,35],"becoming":[6],"the":[7,12,22,32,38,63,86,106,110,126,138,160],"standard":[8],"of":[9,14,24,44,157,162],"practice":[10],"for":[11,59,83,125],"study":[13],"structural":[15],"variants":[16],"associated":[17],"with":[18,21,37],"disease.":[19],"However,":[20],"growth":[23],"sequence":[25,45],"data":[26],"largely":[27],"surpassing":[28],"reasonable":[29],"storage":[30,43],"capability,":[31],"biomedical":[33],"community":[34],"challenged":[36],"management,":[39],"transfer,":[40],"archiving,":[41],"data.":[46],"Methods":[47],"We":[48,69],"developed":[49],"Hierarchical":[50],"mUlti-reference":[51],"Genome":[52],"cOmpression":[53],"(HUGO),":[54],"a":[55,75,134],"novel":[56],"compression":[57,119,123,144,148],"algorithm":[58],"aligned":[60,71],"reads":[61,73,82],"in":[62],"sorted":[64],"Sequence":[65],"Alignment/Map":[66],"(SAM)":[67],"format.":[68],"first":[70],"short":[72],"against":[74,95],"reference":[76,97],"genome":[77],"stored":[79],"exactly":[80],"mapped":[81,88],"compression.":[84],"For":[85],"inexact":[87],"or":[89],"unmapped":[90],"reads,":[91],"we":[92,114],"realigned":[93],"them":[94],"different":[96,163],"genomes":[98],"using":[99],"an":[100],"adaptive":[101],"scheme":[102],"by":[103,152],"gradually":[104],"shortening":[105],"read":[107],"length.":[108],"Regarding":[109],"base":[111,127],"quality":[112,128,142,164],"value,":[113],"offer":[115],"lossy":[116,122],"lossless":[118,147],"mechanisms.":[120],"The":[121,146],"mechanism":[124],"values":[129],"uses":[130],"k-means":[131],"clustering,":[132],"where":[133],"user":[135],"can":[136,149],"adjust":[137],"balance":[139],"between":[140],"decompression":[141],"rate.":[145],"be":[150],"produced":[151],"setting":[153],"k":[154],"(the":[155],"number":[156,161],"clusters)":[158],"to":[159],"values.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
