{"id":"https://openalex.org/W1530498595","doi":"https://doi.org/10.1186/1471-2105-7-58","title":"Identifying biological concepts from a protein-related corpus with a probabilistic topic model","display_name":"Identifying biological concepts from a protein-related corpus with a probabilistic topic model","publication_year":2006,"publication_date":"2006-02-08","ids":{"openalex":"https://openalex.org/W1530498595","doi":"https://doi.org/10.1186/1471-2105-7-58","mag":"1530498595","pmid":"https://pubmed.ncbi.nlm.nih.gov/16466569"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-58","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-58","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-58","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-58","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083330062","display_name":"Bin Zheng","orcid":"https://orcid.org/0000-0002-0998-7177"},"institutions":[{"id":"https://openalex.org/I153297377","display_name":"Medical University of South Carolina","ror":"https://ror.org/012jban78","country_code":"US","type":"education","lineage":["https://openalex.org/I153297377"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Zheng","raw_affiliation_strings":["Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, SC 29405, USA. zheng@musc.edu","Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, SC 29405, USA. zheng@musc.edu","institution_ids":["https://openalex.org/I153297377"]},{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, USA,","institution_ids":["https://openalex.org/I153297377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011840312","display_name":"David C. McLean","orcid":null},"institutions":[{"id":"https://openalex.org/I153297377","display_name":"Medical University of South Carolina","ror":"https://ror.org/012jban78","country_code":"US","type":"education","lineage":["https://openalex.org/I153297377"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David C McLean","raw_affiliation_strings":["Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, SC, 29405, USA","Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, SC, 29405, USA","institution_ids":["https://openalex.org/I153297377"]},{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, USA,","institution_ids":["https://openalex.org/I153297377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046515259","display_name":"Xinghua Lu","orcid":"https://orcid.org/0000-0002-8599-2269"},"institutions":[{"id":"https://openalex.org/I153297377","display_name":"Medical University of South Carolina","ror":"https://ror.org/012jban78","country_code":"US","type":"education","lineage":["https://openalex.org/I153297377"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinghua Lu","raw_affiliation_strings":["Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, SC, 29405, USA","Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, SC, 29405, USA","institution_ids":["https://openalex.org/I153297377"]},{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina, Charleston, USA,","institution_ids":["https://openalex.org/I153297377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046515259"],"corresponding_institution_ids":["https://openalex.org/I153297377"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.2709,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.76512317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"7","issue":"1","first_page":"58","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9965000152587891,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9965000152587891,"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":0.0010999999940395355,"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":0.00019999999494757503,"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":0.5791265964508057},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5217219591140747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5150942206382751},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.49283504486083984},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45404258370399475},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.45084619522094727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3651183843612671},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26966410875320435},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1942933201789856},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07342672348022461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5791265964508057},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5217219591140747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5150942206382751},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.49283504486083984},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45404258370399475},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.45084619522094727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3651183843612671},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26966410875320435},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1942933201789856},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07342672348022461},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-7-58","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-58","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-58","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16466569","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16466569","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:e29cd1b362c647a5a1ebefc3bc25f7b2","is_oa":true,"landing_page_url":"https://doaj.org/article/e29cd1b362c647a5a1ebefc3bc25f7b2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 7, Iss 1, p 58 (2006)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1420333","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1420333","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-7-58","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-58","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-58","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1526982958","display_name":null,"funder_award_id":"T15 LM007438","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G2729011264","display_name":null,"funder_award_id":"5 P20 RR016434-04","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G2846702645","display_name":null,"funder_award_id":"RR016434","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6789608322","display_name":null,"funder_award_id":"5T15-LM007438-02","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G8178873417","display_name":null,"funder_award_id":"P20 RR016434","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G8360978036","display_name":null,"funder_award_id":"5T15LM007438-03","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320309383","display_name":"Medical University of South Carolina","ror":"https://ror.org/012jban78"},{"id":"https://openalex.org/F4320310846","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1530498595.pdf","grobid_xml":"https://content.openalex.org/works/W1530498595.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W617060359","https://openalex.org/W1607198972","https://openalex.org/W1660390307","https://openalex.org/W1669437150","https://openalex.org/W1880262756","https://openalex.org/W1982114217","https://openalex.org/W2001082470","https://openalex.org/W2057506443","https://openalex.org/W2097106271","https://openalex.org/W2098162425","https://openalex.org/W2103017472","https://openalex.org/W2107743791","https://openalex.org/W2109176692","https://openalex.org/W2123273303","https://openalex.org/W2124617249","https://openalex.org/W2126276057","https://openalex.org/W2135194391","https://openalex.org/W2135230352","https://openalex.org/W2137297622","https://openalex.org/W2147152072","https://openalex.org/W2149942697","https://openalex.org/W2150452501","https://openalex.org/W2152183901","https://openalex.org/W2158266063","https://openalex.org/W2161062388","https://openalex.org/W2168662600","https://openalex.org/W2405856141","https://openalex.org/W2482128004","https://openalex.org/W2595840341","https://openalex.org/W2978329087","https://openalex.org/W3140968660","https://openalex.org/W4211177544","https://openalex.org/W4237791300"],"related_works":["https://openalex.org/W2494523064","https://openalex.org/W2943623134","https://openalex.org/W2215759665","https://openalex.org/W2960358116","https://openalex.org/W2030292806","https://openalex.org/W3041172967","https://openalex.org/W2749065928","https://openalex.org/W2147155098","https://openalex.org/W4287727129","https://openalex.org/W2938171715"],"abstract_inverted_index":{"BACKGROUND:":[0],"Biomedical":[1],"literature,":[2],"e.g.,":[3],"MEDLINE,":[4],"contains":[5],"a":[6,43,53,129,153],"wealth":[7],"of":[8,12,25,28,32,45,85,111,131,149],"knowledge":[9],"regarding":[10],"functions":[11],"proteins.":[13],"Major":[14],"recurring":[15,125],"biological":[16,40,97,126],"concepts":[17,127],"within":[18,128],"such":[19],"text":[20],"corpora":[21],"represent":[22],"the":[23,38,67,71,81,108,112,138,150],"domains":[24],"this":[26,33],"body":[27],"knowledge.":[29],"The":[30,58,83,101,122,141],"goal":[31],"research":[34],"is":[35],"to":[36,66,90,107,163],"identify":[37],"major":[39,76,123],"topics/concepts":[41,87,103,143],"from":[42,80],"corpus":[44],"protein-related":[46],"MEDLINE":[47,132],"titles":[48],"and":[49,94,124,146,159],"abstracts":[50],"by":[51,137],"applying":[52],"probabilistic":[54],"topic":[55],"model.":[56,140],"RESULTS:":[57],"latent":[59],"Dirichlet":[60],"allocation":[61],"(LDA)":[62],"model":[63,73],"was":[64,88],"applied":[65],"corpus.":[68,82],"Based":[69],"on":[70,118],"Bayesian":[72],"selection,":[74],"300":[75],"topics":[77],"were":[78,104],"extracted":[79,136],"majority":[84],"identified":[86,102,142],"found":[89],"be":[91,135,161],"semantically":[92],"coherent":[93],"most":[95],"represented":[96],"objects":[98],"or":[99],"concepts.":[100],"further":[105],"mapped":[106],"controlled":[109],"vocabulary":[110],"Gene":[113],"Ontology":[114],"(GO)":[115],"terms":[116],"based":[117],"mutual":[119],"information.":[120],"CONCLUSION:":[121],"collection":[130],"documents":[133],"can":[134,160],"LDA":[139],"provide":[144],"parsimonious":[145],"semantically-enriched":[147],"representation":[148],"texts":[151],"in":[152],"semantic":[154],"space":[155],"with":[156],"reduced":[157],"dimensionality":[158],"used":[162],"index":[164],"text.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}