{"id":"https://openalex.org/W2148279834","doi":"https://doi.org/10.1093/bioinformatics/bti801","title":"Application of latent semantic analysis to protein remote homology detection","display_name":"Application of latent semantic analysis to protein remote homology detection","publication_year":2005,"publication_date":"2005-11-29","ids":{"openalex":"https://openalex.org/W2148279834","doi":"https://doi.org/10.1093/bioinformatics/bti801","mag":"2148279834","pmid":"https://pubmed.ncbi.nlm.nih.gov/16317074"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti801","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti801","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/3/285/48839521/bioinformatics_22_3_285.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/22/3/285/48839521/bioinformatics_22_3_285.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100608345","display_name":"Qiwen Dong","orcid":"https://orcid.org/0000-0002-3166-0541"},"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":"Qi-wen Dong","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology \u00a0 Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology \u00a0 Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424254","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0001-9003-4252"},"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":"Xiao-long Wang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology \u00a0 Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology \u00a0 Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048326379","display_name":"Lei Lin","orcid":"https://orcid.org/0000-0002-1161-8565"},"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":"Lei Lin","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology \u00a0 Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology \u00a0 Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100608345"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.3861,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.88595014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"3","first_page":"285","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9311000108718872,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9311000108718872,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.031099999323487282,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.006399999838322401,"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":0.7519053220748901},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.7316077947616577},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6710588932037354},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6101855635643005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6039007902145386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5881787538528442},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46517395973205566},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.45825377106666565},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4329959750175476},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4217260181903839},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.2232080101966858},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14760783314704895},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11411777138710022},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06788960099220276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519053220748901},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.7316077947616577},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6710588932037354},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6101855635643005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6039007902145386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5881787538528442},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46517395973205566},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.45825377106666565},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4329959750175476},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4217260181903839},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2232080101966858},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14760783314704895},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11411777138710022},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06788960099220276},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","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":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti801","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti801","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/3/285/48839521/bioinformatics_22_3_285.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16317074","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16317074","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti801","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti801","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/3/285/48839521/bioinformatics_22_3_285.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2148279834.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W26015397","https://openalex.org/W605716199","https://openalex.org/W1217346921","https://openalex.org/W1518399713","https://openalex.org/W1558365920","https://openalex.org/W1592870802","https://openalex.org/W1973714307","https://openalex.org/W1982025738","https://openalex.org/W1991022130","https://openalex.org/W2020816856","https://openalex.org/W2028903194","https://openalex.org/W2043764234","https://openalex.org/W2055043387","https://openalex.org/W2084787613","https://openalex.org/W2087064593","https://openalex.org/W2092067718","https://openalex.org/W2102122585","https://openalex.org/W2104983234","https://openalex.org/W2106882534","https://openalex.org/W2114659440","https://openalex.org/W2118714763","https://openalex.org/W2121085676","https://openalex.org/W2121950477","https://openalex.org/W2124709175","https://openalex.org/W2125725297","https://openalex.org/W2127464112","https://openalex.org/W2128328428","https://openalex.org/W2133657429","https://openalex.org/W2140244239","https://openalex.org/W2141224484","https://openalex.org/W2141915888","https://openalex.org/W2143763906","https://openalex.org/W2148603752","https://openalex.org/W2158714788","https://openalex.org/W2158997610","https://openalex.org/W2170960297","https://openalex.org/W2283504545","https://openalex.org/W2792561556","https://openalex.org/W6601040707","https://openalex.org/W6628161473","https://openalex.org/W6635200387","https://openalex.org/W6655478935","https://openalex.org/W6681073388"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"MOTIVATION:":[0],"Remote":[1],"homology":[2,125,226],"detection":[3,227],"between":[4],"protein":[5,42,92,96,123,132,150,183,192],"sequences":[6,133],"is":[7,24,109,152,158,165,170,206,240],"a":[8,102,155],"central":[9],"problem":[10],"in":[11,61,122,228],"computational":[12],"biology.":[13],"The":[14,162,168,194,204,213],"discriminative":[15],"method":[16,205,239],"such":[17,249,260],"as":[18,137,154,250,261],"the":[19,27,33,58,66,138,173,177,209,217,222,231,235,245],"support":[20],"vector":[21,48],"machine":[22],"(SVM)":[23],"one":[25],"of":[26,32,41,91,131,140,160,182,191,224,237,244,256],"most":[28],"effective":[29],"methods.":[30],"Many":[31],"SVM-based":[34],"methods":[35,64,248,259],"focus":[36],"on":[37,79,85,172,208],"finding":[38],"useful":[39],"representations":[40,49,54],"sequence,":[43],"using":[44],"either":[45],"explicit":[46],"feature":[47,86,112],"or":[50],"kernel":[51,247],"functions.":[52],"Such":[53],"may":[55,75],"suffer":[56],"from":[57,115],"peaking":[59],"phenomenon":[60],"many":[62],"machine-learning":[63],"because":[65],"features":[67],"are":[68,199],"usually":[69],"very":[70],"large":[71],"and":[72,88,147,188,252,263],"noise":[73],"data":[74],"be":[76],"introduced.":[77],"Based":[78],"these":[80],"observations,":[81],"this":[82,100,238],"research":[83],"focuses":[84],"extraction":[87,113],"efficient":[89,111],"representation":[90,180,197],"vectors":[93,181,198],"for":[94],"SVM":[95],"classification.":[97],"RESULTS:":[98],"In":[99],"study,":[101],"latent":[103,178,195],"semantic":[104,179,196],"analysis":[105],"(LSA)":[106],"model,":[107],"which":[108],"an":[110],"technique":[114],"natural":[116],"language":[117],"processing,":[118],"has":[119],"been":[120,135],"introduced":[121],"remote":[124,225],"detection.":[126],"Several":[127],"basic":[128,232],"building":[129],"blocks":[130],"have":[134],"investigated":[136],"'words'":[139],"'protein":[141],"sequence":[142,151],"language',":[143],"including":[144],"N-grams,":[145],"patterns":[146],"motifs.":[148],"Each":[149],"taken":[153],"'document'":[156],"that":[157,216,243,255],"composed":[159],"bags-of-word.":[161],"word-document":[163],"matrix":[164,174],"constructed":[166],"first.":[167],"LSA":[169,218],"performed":[171],"to":[175,186],"produce":[176],"sequences,":[184],"leading":[185],"noise-removal":[187],"smart":[189],"description":[190],"sequences.":[193],"then":[200],"evaluated":[201],"by":[202],"SVM.":[203],"tested":[207],"SCOP":[210],"1.53":[211],"database.":[212],"results":[214],"show":[215],"model":[219],"significantly":[220],"improves":[221],"performance":[223,236],"comparison":[229],"with":[230,242],"formalisms.":[233],"Furthermore,":[234],"comparable":[241],"complex":[246],"SVM-LA":[251],"better":[253],"than":[254],"other":[257],"sequence-based":[258],"PSI-BLAST":[262],"SVM-pairwise.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}