{"id":"https://openalex.org/W2122305935","doi":"https://doi.org/10.1093/bioinformatics/bth904","title":"Protein names precisely peeled off free text","display_name":"Protein names precisely peeled off free text","publication_year":2004,"publication_date":"2004-07-19","ids":{"openalex":"https://openalex.org/W2122305935","doi":"https://doi.org/10.1093/bioinformatics/bth904","mag":"2122305935","pmid":"https://pubmed.ncbi.nlm.nih.gov/15262805"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth904","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth904","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/A5113852506","display_name":"Sven Mika","orcid":null},"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":true,"raw_author_name":"Sven Mika","raw_affiliation_strings":["CUBIC, Department of Biochemistry and Molecular Biophysics, Columbia University, New York, NY 10032, USA. mika@cubic.bioc.columbia.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, New York, NY 10032, USA. mika@cubic.bioc.columbia.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":["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","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113852506"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.6344,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.89838698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"20","issue":"suppl_1","first_page":"i241","last_page":"i247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9868000149726868,"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":0.9868000149726868,"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":0.003800000064074993,"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":0.002300000051036477,"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":0.7885482311248779},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.7035156488418579},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.649214506149292},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5449948310852051},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5412603616714478},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5378832817077637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5006167888641357},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.47329726815223694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4589903950691223},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.45760369300842285},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40111976861953735},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3405079245567322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885482311248779},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7035156488418579},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.649214506149292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5449948310852051},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5412603616714478},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5378832817077637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006167888641357},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.47329726815223694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4589903950691223},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.45760369300842285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40111976861953735},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3405079245567322},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":"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":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004015","descriptor_name":"Dictionaries, Chemical as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004015","descriptor_name":"Dictionaries, Chemical as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004015","descriptor_name":"Dictionaries, Chemical as Topic","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":"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":"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":"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}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bth904","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth904","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:15262805","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15262805","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":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4474317619","display_name":null,"funder_award_id":"R01-LM07329-01","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"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/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"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"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1576520375","https://openalex.org/W1592053870","https://openalex.org/W1659313070","https://openalex.org/W1997755606","https://openalex.org/W2003144438","https://openalex.org/W2009341227","https://openalex.org/W2020801982","https://openalex.org/W2045340002","https://openalex.org/W2050006154","https://openalex.org/W2058856481","https://openalex.org/W2063753566","https://openalex.org/W2093723065","https://openalex.org/W2119821739","https://openalex.org/W2130260860","https://openalex.org/W2158505321","https://openalex.org/W2158714788","https://openalex.org/W2163107094","https://openalex.org/W2168267323"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W2099261052","https://openalex.org/W3209204065","https://openalex.org/W2105707930","https://openalex.org/W1755711892","https://openalex.org/W2160907113","https://openalex.org/W2090763504","https://openalex.org/W2070813941","https://openalex.org/W3046510185"],"abstract_inverted_index":{"MOTIVATION:":[0],"Automatically":[1],"identifying":[2],"protein":[3,56,71,157,176,197],"names":[4,57,72,112,177],"from":[5],"the":[6,13,59,122,125,165,172,179,189],"scientific":[7,180],"literature":[8,123],"is":[9,67,124],"a":[10,34,39,74,80,88],"pre-requisite":[11],"for":[12,134,195],"increasing":[14],"demand":[15],"in":[16,58,121,127,170,178],"data-mining":[17],"this":[18],"wealth":[19],"of":[20,69,77,83,105,175],"information.":[21],"Existing":[22],"approaches":[23],"are":[24],"based":[25],"on":[26,87],"dictionaries,":[27],"rules":[28],"and":[29,42,97,141,192],"machine-learning.":[30],"Here,":[31],"we":[32,108],"introduced":[33],"novel":[35],"system":[36,186],"that":[37,168,184],"combines":[38],"pre-processing":[40],"dictionary-":[41],"rule-based":[43],"filtering":[44],"step":[45],"with":[46,73],"several":[47],"separately":[48],"trained":[49],"support":[50],"vector":[51],"machines":[52],"(SVMs)":[53],"to":[54,151,164],"identify":[55],"MEDLINE":[60],"abstracts.":[61,101],"RESULTS:":[62],"Our":[63],"new":[64,146],"tagging-system":[65],"NLProt":[66,159],"capable":[68],"extracting":[70],"precision":[75],"(accuracy)":[76],"75%":[78],"at":[79],"recall":[81],"(coverage)":[82],"76%":[84],"after":[85],"training":[86,140],"corpus,":[89],"which":[90],"was":[91,160],"used":[92],"before":[93],"by":[94],"other":[95,154],"groups":[96],"contains":[98],"200":[99],"annotated":[100],"For":[102],"our":[103,148,185],"estimate":[104],"sustained":[106],"performance,":[107],"considered":[109],"partially":[110],"identified":[111],"as":[113],"false":[114],"positives.":[115],"One":[116],"important":[117],"issue":[118],"frequently":[119],"ignored":[120],"redundancy":[126],"evaluation":[128],"sets.":[129,143],"We":[130,182],"suggested":[131],"some":[132],"guidelines":[133],"removing":[135],"overly":[136],"inadequate":[137],"overlaps":[138],"between":[139],"testing":[142],"Applying":[144],"these":[145],"guidelines,":[147],"program":[149],"appeared":[150],"significantly":[152],"out-perform":[153],"methods":[155],"tagging":[156,196],"names.":[158,198],"so":[161],"successful":[162],"due":[163],"SVM-building":[166],"blocks":[167],"succeeded":[169],"utilizing":[171],"local":[173],"context":[174],"literature.":[181],"challenge":[183],"may":[187],"constitute":[188],"most":[190],"general":[191],"precise":[193],"method":[194],"AVAILABILITY:":[199],"http://cubic.bioc.columbia.edu/services/nlprot/":[200]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}