{"id":"https://openalex.org/W2800345240","doi":"https://doi.org/10.1504/ijdmb.2017.10012545","title":"Accurate annotation of metagenomic data without species-level references","display_name":"Accurate annotation of metagenomic data without species-level references","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2800345240","doi":"https://doi.org/10.1504/ijdmb.2017.10012545","mag":"2800345240"},"language":"en","primary_location":{"id":"doi:10.1504/ijdmb.2017.10012545","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijdmb.2017.10012545","pdf_url":null,"source":{"id":"https://openalex.org/S35771696","display_name":"International Journal of Data Mining and Bioinformatics","issn_l":"1748-5673","issn":["1748-5673","1748-5681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Mining and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5101612503","display_name":"Bo Liu","orcid":"https://orcid.org/0009-0005-9072-3046"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392447","display_name":"Yadong Wang","orcid":"https://orcid.org/0000-0001-6500-6217"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Wang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101886550","display_name":"Haobin Yao","orcid":"https://orcid.org/0000-0002-5845-2144"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haobin Yao","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110500992","display_name":"Siu\u2010Ming Yiu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"S.M. Yiu","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033934413","display_name":"Hing\u2010Fung Ting","orcid":"https://orcid.org/0000-0002-2807-2351"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"H.F. Ting","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077116003","display_name":"Tak\u2010Wah Lam","orcid":"https://orcid.org/0000-0003-4676-8587"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"T.W. Lam","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101612503"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17036033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"4","first_page":"283","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9932000041007996,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9932000041007996,"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":0.9883999824523926,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9689000248908997,"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/annotation","display_name":"Annotation","score":0.820537269115448},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.7291423082351685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6869970560073853},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.473716676235199},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4694254994392395},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.45270535349845886},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4398874044418335},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40461382269859314},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.33692437410354614},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30216118693351746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28010880947113037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1243959367275238},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09862032532691956},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09319472312927246}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.820537269115448},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7291423082351685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869970560073853},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.473716676235199},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4694254994392395},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.45270535349845886},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4398874044418335},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40461382269859314},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33692437410354614},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30216118693351746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28010880947113037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1243959367275238},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09862032532691956},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09319472312927246},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1504/ijdmb.2017.10012545","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijdmb.2017.10012545","pdf_url":null,"source":{"id":"https://openalex.org/S35771696","display_name":"International Journal of Data Mining and Bioinformatics","issn_l":"1748-5673","issn":["1748-5673","1748-5681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Mining and Bioinformatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.5799999833106995,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W638577851","https://openalex.org/W2968354375","https://openalex.org/W2359440920","https://openalex.org/W2889550857","https://openalex.org/W3013372948","https://openalex.org/W3135997498","https://openalex.org/W4242417330","https://openalex.org/W3198631238","https://openalex.org/W4388282505","https://openalex.org/W2361861616"],"abstract_inverted_index":{"Taxonomic":[0],"annotation":[1,45],"is":[2,21,119],"a":[3,13,28,43],"critical":[4],"first":[5],"step":[6],"for":[7,126],"analysis":[8],"of":[9,15,117,145],"metagenomic":[10,50],"data.":[11],"Despite":[12],"lot":[14],"tools":[16,56],"being":[17],"developed,":[18],"the":[19,36,64,80,107,121,146,172,178,185],"accuracy":[20],"still":[22],"not":[23,33],"satisfactory,":[24],"in":[25,35,63,142],"particular,":[26],"when":[27,58],"close":[29],"species-level":[30],"reference":[31,173],"does":[32],"exist":[34,62],"database.":[37,65],"In":[38],"this":[39],"paper,":[40],"we":[41,137,163],"propose":[42],"novel":[44],"tool,":[46],"MetaAnnotator,":[47],"to":[48,79,106,157,160,182],"annotate":[49],"reads,":[51],"which":[52],"outperforms":[53],"all":[54],"existing":[55,91],"significantly":[57],"only":[59,84,95,102,138],"genus-level":[60],"references":[61,147],"From":[66],"our":[67],"experiments,":[68],"MetaAnnotator":[69,118,134],"can":[70,94],"assign":[71,158],"87.5%":[72],"reads":[73,76,86,104,112,159],"correctly":[74],"(67.5%":[75],"are":[77],"assigned":[78,105],"exact":[81,108,140],"genus)":[82],"with":[83],"8.5%":[85],"wrongly":[87,113],"assigned.":[88],"The":[89,115,130],"best":[90],"tool":[92],"(MetaCluster-TA)":[93],"achieve":[96],"73.4%":[97],"correct":[98],"read":[99],"assignment":[100],"(with":[101],"50.9%":[103],"genus":[109],"and":[110,154,166,175],"22.6%":[111],"assigned).":[114],"speed":[116,183],"also":[120],"second":[122],"faster":[123],"(1":[124],"hour":[125],"20":[127],"million":[128],"reads).":[129],"core":[131],"concepts":[132],"behind":[133],"includes:":[135],"(i)":[136],"consider":[139],"k-mers":[141],"coding":[143],"regions":[144],"as":[148],"they":[149],"should":[150],"be":[151],"more":[152],"significant":[153],"accurate;":[155],"(ii)":[156],"taxonomy":[161,167],"nodes,":[162],"construct":[164],"genome":[165],"specific":[168],"probabilistic":[169],"models":[170],"from":[171],"database;":[174],"(iii)":[176],"using":[177],"BWT":[179],"data":[180],"structure":[181],"up":[184],"k-mer":[186],"matching":[187],"process.":[188]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
