{"id":"https://openalex.org/W2944186186","doi":"https://doi.org/10.1109/tcbb.2019.2915811","title":"Enabling Massive XML-Based Biological Data Management in HBase","display_name":"Enabling Massive XML-Based Biological Data Management in HBase","publication_year":2019,"publication_date":"2019-05-10","ids":{"openalex":"https://openalex.org/W2944186186","doi":"https://doi.org/10.1109/tcbb.2019.2915811","mag":"2944186186","pmid":"https://pubmed.ncbi.nlm.nih.gov/31094692"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2019.2915811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2019.2915811","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100414626","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0001-7732-1505"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0001-7732-1505","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009281052","display_name":"Qiuru Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuru Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658393","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-0826-169X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Zhejiang University of Science and Technology, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Science and Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003344827","display_name":"Shuhui Su","orcid":"https://orcid.org/0009-0004-5995-6362"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Su","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009730904","display_name":"Yongzhuang Liu","orcid":"https://orcid.org/0000-0002-2572-7420"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzhuang Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100414626"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"],"apc_list":null,"apc_paid":null,"fwci":3.5279,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94840688,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"17","issue":"6","first_page":"1994","last_page":"2004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9873999953269958,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9864000082015991,"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/computer-science","display_name":"Computer science","score":0.8758736848831177},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.7980892658233643},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.7562538385391235},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.7544229030609131},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.7473875284194946},{"id":"https://openalex.org/keywords/xml-encryption","display_name":"XML Encryption","score":0.6371119022369385},{"id":"https://openalex.org/keywords/xml-framework","display_name":"XML framework","score":0.5757051706314087},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5605853199958801},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.5119953751564026},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.508630633354187},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5010743141174316},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.4859091341495514},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4768458604812622},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24161800742149353},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.09311464428901672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8758736848831177},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.7980892658233643},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.7562538385391235},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.7544229030609131},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.7473875284194946},{"id":"https://openalex.org/C173242113","wikidata":"https://www.wikidata.org/wiki/Q607488","display_name":"XML Encryption","level":4,"score":0.6371119022369385},{"id":"https://openalex.org/C21761406","wikidata":"https://www.wikidata.org/wiki/Q8042330","display_name":"XML framework","level":3,"score":0.5757051706314087},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5605853199958801},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.5119953751564026},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.508630633354187},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5010743141174316},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.4859091341495514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4768458604812622},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24161800742149353},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.09311464428901672},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000079803","descriptor_name":"Data Management","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000079803","descriptor_name":"Data Management","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000079803","descriptor_name":"Data Management","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2019.2915811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2019.2915811","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31094692","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31094692","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1630635859","display_name":null,"funder_award_id":"2016T90294","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3677793330","display_name":null,"funder_award_id":"61602130","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4210662038","display_name":null,"funder_award_id":"61872115","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5397948391","display_name":null,"funder_award_id":"QC2015067","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"},{"id":"https://openalex.org/G7672982789","display_name":null,"funder_award_id":"HIT.NSRIF.2017036","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7820713342","display_name":null,"funder_award_id":"2015M581449","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1601061354","https://openalex.org/W1948418367","https://openalex.org/W1969709265","https://openalex.org/W1984531538","https://openalex.org/W2026657534","https://openalex.org/W2044330111","https://openalex.org/W2067072887","https://openalex.org/W2067865319","https://openalex.org/W2078823509","https://openalex.org/W2083331780","https://openalex.org/W2084594458","https://openalex.org/W2093410900","https://openalex.org/W2098195118","https://openalex.org/W2103129584","https://openalex.org/W2115546496","https://openalex.org/W2115583184","https://openalex.org/W2117306286","https://openalex.org/W2122425433","https://openalex.org/W2133938042","https://openalex.org/W2139035000","https://openalex.org/W2139242647","https://openalex.org/W2149059931","https://openalex.org/W2154139219","https://openalex.org/W2159670728","https://openalex.org/W2160923181","https://openalex.org/W2170726912","https://openalex.org/W2174058075","https://openalex.org/W2177729144","https://openalex.org/W2204224788","https://openalex.org/W2280346092","https://openalex.org/W2313483714","https://openalex.org/W2403949620","https://openalex.org/W2515138983","https://openalex.org/W2569138550","https://openalex.org/W2585969625","https://openalex.org/W2588327067","https://openalex.org/W2770026599","https://openalex.org/W2807077960","https://openalex.org/W2915374113","https://openalex.org/W4210702584","https://openalex.org/W4243649771"],"related_works":["https://openalex.org/W202492310","https://openalex.org/W2385975321","https://openalex.org/W2047342127","https://openalex.org/W2560505635","https://openalex.org/W1591876566","https://openalex.org/W2117064692","https://openalex.org/W2552861811","https://openalex.org/W585825282","https://openalex.org/W1510854604","https://openalex.org/W2540621130"],"abstract_inverted_index":{"Publishing":[0],"biological":[1,32,48,87,99,138,158],"data":[2,33,49,88,100,159],"in":[3,18,66],"XML":[4,113],"formats":[5],"is":[6,35,52,102,121,140,162],"attractive":[7],"for":[8,93],"organizations":[9],"who":[10],"would":[11],"like":[12],"to":[13,55,61,81,110],"provide":[14,62],"their":[15],"bioinformatics":[16],"resources":[17],"an":[19,124],"extensible":[20],"and":[21,71,83,105],"machine-readable":[22],"format.":[23],"In":[24,73],"the":[25,42,46,112,117,127,131,135,144,148,155],"era":[26],"of":[27,45,68,126,130,147,154],"big":[28],"data,":[29],"massive":[30,85,156],"XML-based":[31,47,86,98,137,157],"management":[34,160],"emerged":[36],"as":[37],"a":[38,78,107],"challengeable":[39],"issue.":[40],"With":[41],"continuous":[43],"growth":[44],"sets,":[50],"it":[51],"usually":[53],"frustrating":[54],"use":[56],"traditional":[57],"declarative":[58],"query":[59,64,84,114,119,128],"languages":[60],"efficient":[63],"capabilities":[65],"terms":[67],"processing":[69],"speed":[70],"scale.":[72],"this":[74],"study,":[75],"we":[76],"report":[77],"novel":[79],"platform":[80,161],"store":[82],"collections.":[89],"A":[90],"prototype":[91],"tool":[92],"constructing":[94],"HBase":[95],"tables":[96],"from":[97],"collections":[101],"first":[103],"developed,":[104],"then":[106],"formal":[108],"approach":[109,133],"transform":[111],"model":[115,120],"into":[116],"MapReduce":[118],"proposed.":[122],"Finally,":[123],"evaluation":[125],"performance":[129,145],"proposed":[132,149],"on":[134],"existing":[136],"databases":[139],"presented,":[141],"showing":[142],"that":[143],"advantages":[146],"solution.":[150],"The":[151],"source":[152],"code":[153],"freely":[163],"available":[164],"at":[165],"https://github.com/lyotvincent/X2H.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
