{"id":"https://openalex.org/W2146638336","doi":"https://doi.org/10.1093/bioinformatics/bth938","title":"Filtering erroneous protein annotation","display_name":"Filtering erroneous protein annotation","publication_year":2004,"publication_date":"2004-07-19","ids":{"openalex":"https://openalex.org/W2146638336","doi":"https://doi.org/10.1093/bioinformatics/bth938","mag":"2146638336","pmid":"https://pubmed.ncbi.nlm.nih.gov/15262818"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth938","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth938","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/A5059765665","display_name":"Daniela Wieser","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":true,"raw_author_name":"D. Wieser","raw_affiliation_strings":["Sequence Database Group, European Bioinformatics Institute, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sequence Database Group, European Bioinformatics Institute, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","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":"E. Kretschmann","raw_affiliation_strings":["Sequence Database Group, European Bioinformatics Institute, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sequence Database Group, European Bioinformatics Institute, 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":"R. Apweiler","raw_affiliation_strings":["Sequence Database Group, European Bioinformatics Institute, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sequence Database Group, European Bioinformatics Institute, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059765665"],"corresponding_institution_ids":["https://openalex.org/I1303153112"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.9159,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.85213608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":"suppl_1","first_page":"i342","last_page":"i347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9508000016212463,"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":0.9508000016212463,"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":0.0142000000923872,"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":0.00989999994635582,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.9031222462654114},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8738237619400024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.819062352180481},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7200436592102051},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6329335570335388},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4649193584918976},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4321567714214325},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4268481135368347},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4142366647720337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2982264757156372}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.9031222462654114},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8738237619400024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819062352180481},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7200436592102051},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6329335570335388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4649193584918976},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4321567714214325},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4268481135368347},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4142366647720337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2982264757156372},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D008969","descriptor_name":"Molecular Sequence Data","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":"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":"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":"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":"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":"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/bth938","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth938","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:15262818","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15262818","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":[{"id":"https://metadata.un.org/sdg/10","score":0.5899999737739563,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G7129238461","display_name":null,"funder_award_id":"1 U01 HG02712-01","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1504694836","https://openalex.org/W2022366078","https://openalex.org/W2081269341","https://openalex.org/W2102424043","https://openalex.org/W2108401170","https://openalex.org/W2110041134","https://openalex.org/W2125055259","https://openalex.org/W2126775187","https://openalex.org/W2128379497","https://openalex.org/W2149589547","https://openalex.org/W2154139219","https://openalex.org/W2163105490"],"related_works":["https://openalex.org/W2102027645","https://openalex.org/W2107785922","https://openalex.org/W2059359052","https://openalex.org/W2035528219","https://openalex.org/W2402478170","https://openalex.org/W2946410450","https://openalex.org/W2999847357","https://openalex.org/W2901823680","https://openalex.org/W1995530145","https://openalex.org/W2146638336"],"abstract_inverted_index":{"MOTIVATION:":[0],"Automatically":[1],"generated":[2,123],"annotation":[3,51,113,126,171],"on":[4,18,84],"protein":[5,36,138],"data":[6,31,60,124],"of":[7,33,48,56,67,111,120,169,176,186,191],"UniProt":[8,20],"(Universal":[9],"Protein":[10],"Resource)":[11],"is":[12,27,82,101,148],"planned":[13],"to":[14,133,165],"be":[15,43,62,154,162,196],"publicly":[16],"available":[17],"the":[19,30,39,46,57,68,95,112,118,167,180,192],"web":[21],"pages":[22],"in":[23,38,137],"April":[24],"2004.":[25],"It":[26,100,160],"expected":[28],"that":[29,81,103,152],"content":[32],"over":[34],"500,000":[35],"entries":[37],"TrEMBL":[40],"section":[41],"will":[42,61],"enhanced":[44],"by":[45],"output":[47],"an":[49],"automated":[50,170],"pipeline.":[52],"However,":[53],"a":[54,76,85,90,108,131,149,173,183],"part":[55,110],"automatically":[58,122],"added":[59],"erroneous,":[63],"as":[64],"are":[65,143],"parts":[66],"information":[69],"coming":[70],"from":[71,127],"other":[72,128],"sources.":[73,129],"We":[74],"present":[75],"post-processing":[77],"system":[78],"called":[79],"Xanthippe":[80,104,147,193],"based":[83],"simple":[86],"exclusion":[87],"mechanism":[88],"and":[89,106,115,125,141],"decision":[91],"tree":[92],"approach":[93],"using":[94],"C4.5":[96],"data-mining":[97],"algorithm.":[98],"RESULTS:":[99],"shown":[102],"detects":[105],"flags":[107],"large":[109],"errors":[114,136],"considerably":[116],"increases":[117],"reliability":[119],"both":[121],"As":[130],"cross-validation":[132],"Swiss-Prot":[134],"shows,":[135],"descriptions,":[139],"comments":[140],"keywords":[142],"successfully":[144],"filtered":[145],"out.":[146],"contradictive":[150],"application":[151,190],"can":[153,161,195],"combined":[155],"seamlessly":[156],"with":[157],"predictive":[158],"systems.":[159],"used":[163],"either":[164],"improve":[166],"precision":[168],"at":[172,182,198],"constant":[174,184],"level":[175,185],"recall":[177,181],"or":[178],"increase":[179],"precision.":[187],"AVAILABILITY:":[188],"The":[189],"rules":[194],"browsed":[197],"http://www.ebi.uniprot.org/":[199]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
