{"id":"https://openalex.org/W2121869529","doi":"https://doi.org/10.1093/bioinformatics/18.suppl_1.s78","title":"Inferring sub-cellular localization through automated lexical analysis","display_name":"Inferring sub-cellular localization through automated lexical analysis","publication_year":2002,"publication_date":"2002-07-01","ids":{"openalex":"https://openalex.org/W2121869529","doi":"https://doi.org/10.1093/bioinformatics/18.suppl_1.s78","mag":"2121869529","pmid":"https://pubmed.ncbi.nlm.nih.gov/12169534"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/18.suppl_1.s78","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/18.suppl_1.s78","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067912188","display_name":"Rajesh Nair","orcid":"https://orcid.org/0000-0001-7911-4972"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajesh Nair","raw_affiliation_strings":["CUBIC, Department of Biochemistry and Molecular Biophysics, Columbia University, 650 West 168th Street BB217, New York, NY 10032, USA. nair@cubic.bioc.coplumbia.edu","CUBIC, Department of Biochemistry and Molecular Biophysics, Columbia University, 650 West 168th Street, BB217, New York, NY 10032, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUBIC, Department of Biochemistry and Molecular Biophysics, Columbia University, 650 West 168th Street BB217, New York, NY 10032, USA. nair@cubic.bioc.coplumbia.edu","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"CUBIC, Department of Biochemistry and Molecular Biophysics, Columbia University, 650 West 168th Street, BB217, New York, NY 10032, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064905883","display_name":"Burkhard Rost","orcid":"https://orcid.org/0000-0003-0179-8424"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burkhard Rost","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.8775,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.91342302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"suppl_1","first_page":"S78","last_page":"S86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9304999709129333,"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":0.9304999709129333,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.021400000900030136,"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":0.016899999231100082,"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":0.6681230068206787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5589578747749329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536867082118988},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.35163605213165283},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.227286696434021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6681230068206787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5589578747749329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536867082118988},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35163605213165283},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.227286696434021}],"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":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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D009323","descriptor_name":"Natural Language Processing","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":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"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":"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":"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":"D014018","descriptor_name":"Tissue Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014018","descriptor_name":"Tissue Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014018","descriptor_name":"Tissue Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","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},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","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},{"descriptor_ui":"D022082","descriptor_name":"Cellular Structures","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D022082","descriptor_name":"Cellular Structures","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D022082","descriptor_name":"Cellular Structures","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/18.suppl_1.s78","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/18.suppl_1.s78","pdf_url":null,"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:12169534","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12169534","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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5600436576","display_name":null,"funder_award_id":"1-P50-GM62413-01","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G7921001194","display_name":null,"funder_award_id":"R01-GM63029-01","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1494075612","https://openalex.org/W1570542661","https://openalex.org/W1610836425","https://openalex.org/W1659313070","https://openalex.org/W1774728382","https://openalex.org/W1805475080","https://openalex.org/W1952076072","https://openalex.org/W1971403296","https://openalex.org/W1975796937","https://openalex.org/W1983995085","https://openalex.org/W1987379494","https://openalex.org/W1991570251","https://openalex.org/W2003144438","https://openalex.org/W2015292449","https://openalex.org/W2018567795","https://openalex.org/W2022679416","https://openalex.org/W2024022608","https://openalex.org/W2032838501","https://openalex.org/W2036792999","https://openalex.org/W2039267000","https://openalex.org/W2055043387","https://openalex.org/W2057099031","https://openalex.org/W2058982198","https://openalex.org/W2060014742","https://openalex.org/W2073064803","https://openalex.org/W2078680823","https://openalex.org/W2079145130","https://openalex.org/W2081269341","https://openalex.org/W2094560491","https://openalex.org/W2096358531","https://openalex.org/W2101220662","https://openalex.org/W2101783948","https://openalex.org/W2110743132","https://openalex.org/W2111876537","https://openalex.org/W2115595474","https://openalex.org/W2117019496","https://openalex.org/W2126775187","https://openalex.org/W2128329041","https://openalex.org/W2133790733","https://openalex.org/W2137601093","https://openalex.org/W2137995988","https://openalex.org/W2141652419","https://openalex.org/W2146741765","https://openalex.org/W2148622452","https://openalex.org/W2153283265","https://openalex.org/W2153294290","https://openalex.org/W2158714788","https://openalex.org/W2164565068","https://openalex.org/W2166233246","https://openalex.org/W2167188257","https://openalex.org/W2435251607","https://openalex.org/W2613359208","https://openalex.org/W2916193864"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"The":[2,86],"SWISS-PROT":[3,49],"sequence":[4,60,174],"database":[5],"contains":[6],"keywords":[7,34,50],"of":[8,48,65,91,105,116,146,156,164],"functional":[9,80,106],"annotations":[10,155],"for":[11,23,45,78,112,159,166],"many":[12],"proteins.":[13,27,149],"In":[14],"contrast,":[15],"information":[16,81],"about":[17,152],"the":[18,56,62],"sub-cellular":[19,53,157,177],"localization":[20,32,111,158,165],"is":[21],"available":[22],"only":[24],"a":[25,41,75,89,97,103,144],"few":[26],"Experts":[28],"can":[29],"often":[30],"infer":[31,110],"from":[33],"describing":[35],"protein":[36,179],"function.":[37],"We":[38,121],"developed":[39],"LOCkey,":[40],"fully":[42],"automated":[43],"method":[44,72,87],"lexical":[46,181],"analysis":[47],"that":[51],"assigns":[52],"localization.":[54],"With":[55],"rapid":[57],"growth":[58],"in":[59,96,119],"data,":[61],"biochemical":[63],"characterisation":[64],"sequences":[66],"has":[67],"been":[68],"falling":[69],"behind.":[70],"Our":[71],"may":[73],"be":[74,187],"useful":[76],"tool":[77],"supplementing":[79],"already":[82],"automatically":[83],"available.":[84],"Results:":[85],"reached":[88],"level":[90],"more":[92],"than":[93,114],"82%":[94],"accuracy":[95],"full":[98],"cross-validation":[99],"test.":[100],"Due":[101],"to":[102,124],"lack":[104],"annotations,":[107],"we":[108],"could":[109],"fewer":[113],"half":[115],"all":[117,147],"proteins":[118],"SWISS-PROT.":[120],"applied":[122],"LOCkey":[123,150],"annotate":[125],"five":[126],"entirely":[127],"sequenced":[128],"proteomes,":[129],"namely":[130],"Saccharomyces":[131],"cerevisiae":[132],"(yeast),":[133],"Caenorhabditis":[134],"elegans":[135],"(worm),":[136],"Drosophila":[137],"melanogaster":[138],"(fly),":[139],"Arabidopsis":[140],"thaliana":[141],"(plant)":[142],"and":[143],"subset":[145],"human":[148],"found":[151],"8000":[153],"new":[154],"these":[160],"eukaryotes.":[161],"Availability:":[162],"Annotations":[163],"eukaryotes":[167],"at:":[168],"http://cubic.bioc.columbia.edu/services/LOCkey":[169],"Contact:":[170],"nair@cubic.bioc.coplumbia.edurost@columbia.edu":[171],"Keywords:":[172],"genome":[173],"analysis;":[175],"predicting":[176],"localization;":[178],"function;":[180],"analysis.":[182],"*To":[183],"whom":[184],"correspondence":[185],"should":[186],"addressed.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
