{"id":"https://openalex.org/W2126775187","doi":"https://doi.org/10.1093/bioinformatics/17.10.920","title":"Automatic rule generation for protein annotation with the C4.5 data mining algorithm applied on SWISS-PROT","display_name":"Automatic rule generation for protein annotation with the C4.5 data mining algorithm applied on SWISS-PROT","publication_year":2001,"publication_date":"2001-10-01","ids":{"openalex":"https://openalex.org/W2126775187","doi":"https://doi.org/10.1093/bioinformatics/17.10.920","mag":"2126775187","pmid":"https://pubmed.ncbi.nlm.nih.gov/11673236"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/17.10.920","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/17.10.920","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/17/10/920/697976/170920.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/17/10/920/697976/170920.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022580365","display_name":"Ernst Kretschmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ernst Kretschmann","raw_affiliation_strings":["The EMBL Outstation, The European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The EMBL Outstation, The European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058002996","display_name":"Wolfgang Fleischmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wolfgang Fleischmann","raw_affiliation_strings":["The EMBL Outstation, The European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The EMBL Outstation, The European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066667859","display_name":"Rolf Apweiler","orcid":"https://orcid.org/0000-0001-7078-200X"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rolf Apweiler","raw_affiliation_strings":["The EMBL Outstation, The European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The EMBL Outstation, The European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1303153112"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.7823,"has_fulltext":false,"cited_by_count":137,"citation_normalized_percentile":{"value":0.9094575,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"10","first_page":"920","last_page":"926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.42750000953674316,"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":0.42750000953674316,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.305400013923645,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.048700001090765,"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/annotation","display_name":"Annotation","score":0.890174150466919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719318270683289},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.550103485584259},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.5166113972663879},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4985055923461914},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.48552656173706055},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3685004711151123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21314966678619385}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.890174150466919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719318270683289},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.550103485584259},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.5166113972663879},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4985055923461914},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.48552656173706055},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3685004711151123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21314966678619385},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/17.10.920","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/17.10.920","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/17/10/920/697976/170920.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:11673236","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11673236","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/17.10.920","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/17.10.920","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/17/10/920/697976/170920.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W225115502","https://openalex.org/W1504694836","https://openalex.org/W1970074386","https://openalex.org/W1994025789","https://openalex.org/W2003144438","https://openalex.org/W2034281973","https://openalex.org/W2074511040","https://openalex.org/W2103017472","https://openalex.org/W2111876537","https://openalex.org/W2117019496","https://openalex.org/W2125055259","https://openalex.org/W2146827656","https://openalex.org/W2149706766","https://openalex.org/W2150486269","https://openalex.org/W2153294290","https://openalex.org/W2916193864"],"related_works":["https://openalex.org/W24553703","https://openalex.org/W4211000692","https://openalex.org/W4212920271","https://openalex.org/W2102027645","https://openalex.org/W2107785922","https://openalex.org/W2035528219","https://openalex.org/W2402478170","https://openalex.org/W2999847357","https://openalex.org/W2946410450","https://openalex.org/W2901823680"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,165,196,217],"gap":[2],"between":[3],"the":[4,31,44,86,113,147,150,154,169,200,220],"amount":[5,87],"of":[6,33,48,88,149,162,168,183,194,199,214,219],"newly":[7],"submitted":[8],"protein":[9,136,155],"data":[10,49,66,103,222],"and":[11,26,91,129,138,158],"reliable":[12,89],"functional":[13],"annotation":[14,22,35,115,186,202],"in":[15,96,116,126,152],"public":[16],"databases":[17,58],"is":[18,37,51,232],"growing.":[19],"Traditional":[20],"manual":[21,82],"by":[23,172,176,208],"literature":[24],"curation":[25],"sequence":[27],"analysis":[28],"tools":[29,77],"without":[30],"use":[32],"automated":[34],"systems":[36],"not":[38],"able":[39],"to":[40,55,93,109,133,206],"keep":[41],"up":[42],"with":[43,190],"ever":[45],"increasing":[46],"quantity":[47],"that":[50,80,175],"submitted.":[52],"Automated":[53],"supplements":[54],"manually":[56,97],"curated":[57],"such":[59],"as":[60],"TrEMBL":[61],"or":[62],"GenPept":[63],"cover":[64],"raw":[65],"but":[67],"provide":[68],"only":[69],"limited":[70],"annotation.":[71],"To":[72],"improve":[73],"this":[74],"situation":[75],"automatic":[76,221],"are":[78,124],"needed":[79],"support":[81],"annotation,":[83],"automatically":[84],"increase":[85],"information":[90],"help":[92],"detect":[94],"inconsistencies":[95],"generated":[98,170,189],"annotations.":[99],"RESULTS:":[100],"A":[101],"standard":[102],"mining":[104,223],"algorithm":[105],"was":[106,156],"successfully":[107],"applied":[108,132],"gain":[110],"knowledge":[111],"about":[112],"Keyword":[114],"SWISS-PROT.":[117],"11":[118],"306":[119],"rules":[120,171],"were":[121],"generated,":[122],"which":[123,153],"provided":[125],"a":[127,141,210],"database":[128],"can":[130,187,203,225],"be":[131,188,204,226],"yet":[134],"unannotated":[135],"sequences":[137],"viewed":[139],"using":[140],"web":[142],"browser.":[143],"They":[144],"rely":[145],"on":[146,159,179,228],"taxonomy":[148],"organism,":[151],"found":[157],"signature":[160],"matches":[161],"its":[163],"sequence.":[164],"statistical":[166],"evaluation":[167],"cross-validation":[173],"suggests":[174],"applying":[177],"them":[178],"arbitrary":[180],"proteins":[181],"33%":[182],"their":[184],"keyword":[185,201],"an":[191],"error":[192,212],"rate":[193,198,213],"1.5%.":[195],"coverage":[197],"increased":[205],"60%":[207],"tolerating":[209],"higher":[211],"5%.":[215],"AVAILABILITY:":[216],"results":[218],"process":[224],"browsed":[227],"http://golgi.ebi.ac.uk:8080/Spearmint/":[229],"Source":[230],"code":[231],"available":[233],"upon":[234],"request.":[235],"CONTACT:":[236],"kretsch@ebi.ac.uk.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
