{"id":"https://openalex.org/W2129911187","doi":"https://doi.org/10.1109/bibm.2010.5706554","title":"Probabilistic topic modeling for genomic data interpretation","display_name":"Probabilistic topic modeling for genomic data interpretation","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2129911187","doi":"https://doi.org/10.1109/bibm.2010.5706554","mag":"2129911187"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2010.5706554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2010.5706554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-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/A5069150872","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-5208-2154"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Chen","raw_affiliation_strings":["College of Information Science and Technology, Drexel University, Philadelphia, PA, USA","College of Information Science & Technology, Drexel University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"College of Information Science & Technology, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101569679","display_name":"Xiaohua Hu","orcid":"https://orcid.org/0000-0002-4777-3022"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohua Hu","raw_affiliation_strings":["College of Information Science and Technology, Drexel University, Philadelphia, PA, USA","College of Information Science & Technology, Drexel University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"College of Information Science & Technology, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043810277","display_name":"Xiajiong Shen","orcid":"https://orcid.org/0000-0002-9407-0637"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]},{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiajiong Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","[College of Computer and Information Engineering, Henan University, Henan, China]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"[College of Computer and Information Engineering, Henan University, Henan, China]","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023224900","display_name":"Gail Rosen","orcid":"https://orcid.org/0000-0003-1763-5750"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]},{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Gail Rosen","raw_affiliation_strings":["College of Computer and Information Engineering, Henan University, Henan, China","Department of Electrical and Computer Engineering at Drexel University in Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Henan University, Henan, China","institution_ids":["https://openalex.org/I173899330"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering at Drexel University in Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069150872"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":0.5287,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.66183921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976999759674072,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9923999905586243,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6942352652549744},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6172986030578613},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6117507815361023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.529371976852417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47865426540374756},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.45415961742401123},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.41899242997169495},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4043278098106384},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36116451025009155},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3039088845252991},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2665932774543762},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2629632353782654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24314314126968384}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6942352652549744},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6172986030578613},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6117507815361023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.529371976852417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47865426540374756},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45415961742401123},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.41899242997169495},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4043278098106384},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36116451025009155},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3039088845252991},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2665932774543762},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2629632353782654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24314314126968384},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2010.5706554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2010.5706554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5699999928474426,"display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320310343","display_name":"Drexel University","ror":"https://ror.org/04bdffz58"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337396","display_name":"Division of Industrial Innovation and Partnerships","ror":"https://ror.org/03xyg3m20"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1530498595","https://openalex.org/W1880262756","https://openalex.org/W1933643226","https://openalex.org/W2001082470","https://openalex.org/W2021497754","https://openalex.org/W2055615325","https://openalex.org/W2100827887","https://openalex.org/W2101305949","https://openalex.org/W2103017472","https://openalex.org/W2116895571","https://openalex.org/W2127641304","https://openalex.org/W2133181292","https://openalex.org/W2146657580","https://openalex.org/W2153990926","https://openalex.org/W2162536033","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4389543811"],"abstract_inverted_index":{"Recently,":[0],"the":[1,14,37,55,81,85,93,101,109,121,125,128,134,142,180,195,207,212],"concept":[2],"of":[3,40,49,108,120,127,138,192,214],"a":[4,29,47,70,117],"species":[5,57,159],"containing":[6],"both":[7],"core":[8,162],"and":[9,58,83,163,166,186,203],"distributed":[10,164],"genes,":[11],"known":[12],"as":[13],"supra-":[15],"or":[16],"pangenome":[17],"theory,":[18],"has":[19],"been":[20],"introduced.":[21],"In":[22],"this":[23,65],"paper,":[24],"we":[25,67,91,131,189],"aim":[26],"to":[27,35,45,73,99,133,151,200,206],"develop":[28],"new":[30],"method":[31],"that":[32],"is":[33,198],"able":[34],"analyze":[36],"genome-level":[38,102],"composition":[39],"DNA":[41,76],"sequences,":[42],"in":[43],"order":[44],"characterize":[46],"set":[48],"common":[50],"genomic":[51],"features":[52],"shared":[53],"by":[54,87],"same":[56],"tell":[59],"their":[60],"functional":[61,172],"roles.":[62],"To":[63],"achieve":[64],"end,":[66],"firstly":[68],"apply":[69],"composition-based":[71],"approach":[72],"break":[74],"down":[75],"sequences":[77,86,140],"into":[78],"sub-reads":[79],"called":[80],"`N-mer'":[82,110],"represent":[84],"N-mer":[88],"frequencies.":[89],"Then,":[90],"introduce":[92],"Latent":[94],"Dirichlet":[95],"Allocation":[96],"(LDA)":[97],"model":[98],"study":[100],"statistic":[103],"patterns":[104],"(a.k.a.":[105],"latent":[106,114,176,184],"topics)":[107],"features.":[111],"Each":[112],"estimated":[113],"topic":[115],"represents":[116],"certain":[118],"component":[119],"whole":[122],"genome.":[123],"With":[124],"help":[126],"BioJava":[129],"toolkit,":[130],"access":[132],"gene":[135,187],"region":[136],"information":[137,182,205],"reference":[139],"from":[141],"NCBI":[143],"database.":[144],"We":[145],"use":[146],"our":[147],"data":[148],"mining":[149],"framework":[150],"investigate":[152],"two":[153],"areas:":[154],"1)":[155],"do":[156,168],"strains":[157],"within":[158],"share":[160],"similar":[161,171,175],"topics?":[165,177],"2)":[167],"genes":[169],"with":[170],"roles":[173],"contain":[174],"After":[178],"studying":[179],"mutual":[181],"between":[183],"topics":[185],"regions,":[188],"provide":[190],"examples":[191,210],"each,":[193],"where":[194],"BioCyc":[196],"database":[197],"used":[199],"correlate":[201],"pathway":[202],"reaction":[204],"genes.":[208],"The":[209],"demonstrate":[211],"effectiveness":[213],"proposed":[215],"method.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":26},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
