{"id":"https://openalex.org/W1517588910","doi":"https://doi.org/10.1186/1471-2105-6-302","title":"Probabilistic annotation of protein sequences based on functional classifications","display_name":"Probabilistic annotation of protein sequences based on functional classifications","publication_year":2005,"publication_date":"2005-12-14","ids":{"openalex":"https://openalex.org/W1517588910","doi":"https://doi.org/10.1186/1471-2105-6-302","mag":"1517588910","pmid":"https://pubmed.ncbi.nlm.nih.gov/16354297"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-6-302","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-302","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-302","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041977335","display_name":"Emmanuel D. Levy","orcid":"https://orcid.org/0000-0001-8959-7365"},"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"]},{"id":"https://openalex.org/I170203145","display_name":"MRC Laboratory of Molecular Biology","ror":"https://ror.org/00tw3jy02","country_code":"GB","type":"facility","lineage":["https://openalex.org/I170203145","https://openalex.org/I4210087105","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Emmanuel D Levy","raw_affiliation_strings":["Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge CB10 1SD, UK. elevy@mrc-lmb.cam.ac.uk","EMBL Cambridge Outstation","MRC Laboratory of Molecular Biology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge CB10 1SD, UK. elevy@mrc-lmb.cam.ac.uk","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"EMBL Cambridge Outstation","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"MRC Laboratory of Molecular Biology","institution_ids":["https://openalex.org/I170203145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022717154","display_name":"Christos Ouzounis","orcid":"https://orcid.org/0000-0002-0086-8657"},"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"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christos A Ouzounis","raw_affiliation_strings":["Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge, CB10 1SD, UK","Computational Genomics Group, The European Bioinformatics Institute EMBL Cambridge Outstation, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I4210151791"]},{"raw_affiliation_string":"Computational Genomics Group, The European Bioinformatics Institute EMBL Cambridge Outstation, Cambridge, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I4210151791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111634829","display_name":"Walter R. Gilks","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134973","display_name":"MRC Biostatistics Unit","ror":"https://ror.org/046vje122","country_code":"GB","type":"facility","lineage":["https://openalex.org/I241749","https://openalex.org/I4210087105","https://openalex.org/I4210134973","https://openalex.org/I90344618"]},{"id":"https://openalex.org/I90344618","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210087105","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Walter R Gilks","raw_affiliation_strings":["Medical Research Council Biostatistics Unit, Institute of Public Health, Cambridge, CB2 2SR, UK","Medical Research Council, Biostatistics Unit, Institute of Public Health, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Research Council Biostatistics Unit, Institute of Public Health, Cambridge, CB2 2SR, UK","institution_ids":["https://openalex.org/I4210134973","https://openalex.org/I90344618"]},{"raw_affiliation_string":"Medical Research Council, Biostatistics Unit, Institute of Public Health, Cambridge, UK","institution_ids":["https://openalex.org/I4210134973","https://openalex.org/I90344618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046565506","display_name":"Benjamin Audit","orcid":"https://orcid.org/0000-0003-2683-9990"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"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"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210096929","display_name":"Laboratoire de Physique de l'ENS de Lyon","ror":"https://ror.org/00w5ay796","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I4210096929"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["BI","FR","GB"],"is_corresponding":false,"raw_author_name":"Benjamin Audit","raw_affiliation_strings":["Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge, CB10 1SD, UK","Laboratoire Joliot-Curie and Laboratoire de Physique, CNRS UMR5672, Ecole Normale Sup\u00e9rieure, 46 All\u00e9e d'Italie, 69364, Lyon Cedex 07, France","CNRS UMR5672, Ecole Normale Sup\u00e9rieure","EMBL Cambridge Outstation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I4210151791"]},{"raw_affiliation_string":"Laboratoire Joliot-Curie and Laboratoire de Physique, CNRS UMR5672, Ecole Normale Sup\u00e9rieure, 46 All\u00e9e d'Italie, 69364, Lyon Cedex 07, France","institution_ids":["https://openalex.org/I4210103330","https://openalex.org/I113428412","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CNRS UMR5672, Ecole Normale Sup\u00e9rieure","institution_ids":["https://openalex.org/I4210096929","https://openalex.org/I29607241","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"EMBL Cambridge Outstation","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041977335"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I170203145"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.7691,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.82978883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"6","issue":"1","first_page":"302","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.397599995136261,"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":0.397599995136261,"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":0.2556999921798706,"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":0.14270000159740448,"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/annotation","display_name":"Annotation","score":0.6185941100120544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5925187468528748},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5586971044540405},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5383485555648804},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48301586508750916},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4703172743320465},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.45617055892944336},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4549540877342224},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43003514409065247},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42562317848205566},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.42291608452796936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3800082206726074},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.2718147933483124},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2537040710449219},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15733122825622559}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6185941100120544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5925187468528748},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5586971044540405},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5383485555648804},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48301586508750916},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4703172743320465},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45617055892944336},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4549540877342224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43003514409065247},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42562317848205566},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.42291608452796936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3800082206726074},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.2718147933483124},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2537040710449219},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15733122825622559},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":"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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","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":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","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":"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":"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":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":8,"locations":[{"id":"doi:10.1186/1471-2105-6-302","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-302","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-302","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16354297","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16354297","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/a3eb9735-a45c-46a2-b910-bcfbd39a5789","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/a3eb9735-a45c-46a2-b910-bcfbd39a5789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Levy, E D, Ouzounis, C A, Gilks, W R & Audit, B 2005, 'Probabilistic annotation of protein sequences based on functional classifications', BMC Bioinformatics, vol. 6, 302.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:0709.4425","is_oa":true,"landing_page_url":"http://arxiv.org/abs/0709.4425","pdf_url":"https://arxiv.org/pdf/0709.4425","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:ensl-00175314v1","is_oa":true,"landing_page_url":"https://ens-lyon.hal.science/ensl-00175314","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, 2005, 6, pp.302. ⟨10.1186/1471-2105-6-302⟩","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:c024f14e88774bdb95714079379e5f0b","is_oa":true,"landing_page_url":"https://doaj.org/article/c024f14e88774bdb95714079379e5f0b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 6, Iss 1, p 302 (2005)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1361783","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1361783","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/238081","is_oa":true,"landing_page_url":"http://www.dspace.cam.ac.uk/handle/1810/238081","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-6-302","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-302","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-302","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1517588910.pdf","grobid_xml":"https://content.openalex.org/works/W1517588910.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1505791519","https://openalex.org/W1529541464","https://openalex.org/W1558365920","https://openalex.org/W1575035941","https://openalex.org/W1970346761","https://openalex.org/W1975796937","https://openalex.org/W1981095206","https://openalex.org/W1991022130","https://openalex.org/W1995047912","https://openalex.org/W2023790301","https://openalex.org/W2032838501","https://openalex.org/W2035478230","https://openalex.org/W2036792999","https://openalex.org/W2048241494","https://openalex.org/W2049558051","https://openalex.org/W2055043387","https://openalex.org/W2085277871","https://openalex.org/W2097263991","https://openalex.org/W2102122585","https://openalex.org/W2103017472","https://openalex.org/W2103150692","https://openalex.org/W2104412724","https://openalex.org/W2107251251","https://openalex.org/W2107427637","https://openalex.org/W2111973517","https://openalex.org/W2114098797","https://openalex.org/W2122536624","https://openalex.org/W2123858481","https://openalex.org/W2127648442","https://openalex.org/W2133790733","https://openalex.org/W2136522597","https://openalex.org/W2146638336","https://openalex.org/W2148853951","https://openalex.org/W2158714788","https://openalex.org/W2166575747","https://openalex.org/W2166745327","https://openalex.org/W2171963266","https://openalex.org/W2283504545","https://openalex.org/W4256395558"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W2251519152"],"abstract_inverted_index":{"BACKGROUND:":[0],"One":[1],"of":[2,7,12,26,36,59,61,67,86,93,101,117,130,137,154,173,187,197,208,224],"the":[3,10,34,40,57,65,84,91,111,127,135,149,168,185,231,237,240],"most":[4],"evident":[5],"achievements":[6],"bioinformatics":[8],"is":[9,30,114,227,246],"development":[11],"methods":[13],"that":[14,42],"transfer":[15],"biological":[16],"knowledge":[17],"from":[18,239],"characterised":[19],"proteins":[20,63,69,119,139],"to":[21,53,76,96,104,121,140,166,176,178,248],"uncharacterised":[22],"sequences.":[23],"This":[24,182],"mode":[25],"protein":[27],"function":[28,159,175],"assignment":[29],"mostly":[31],"based":[32],"on":[33,56],"detection":[35],"sequence":[37,106,131,157,172,189],"similarity":[38,132],"and":[39,64,126,158,160,192,217,245],"premise":[41],"functional":[43,78,98,123,142,180,253],"properties":[44],"are":[45,74],"conserved":[46],"during":[47],"evolution.":[48],"Most":[49],"automatic":[50],"approaches":[51,165],"developed":[52],"date":[54],"rely":[55],"identification":[58],"clusters":[60],"homologous":[62],"mapping":[66,92,102],"new":[68,138],"onto":[70],"these":[71,141],"clusters,":[72],"which":[73],"expected":[75,247],"share":[77],"characteristics.":[79],"RESULTS:":[80],"Here,":[81],"we":[82,147],"inverse":[83],"logic":[85],"this":[87,109,145,203,225],"process,":[88],"by":[89,211],"considering":[90],"sequences":[94],"directly":[95],"a":[97,105,115,122,171,179,194,206],"classification":[99,124],"instead":[100],"functions":[103],"clustering.":[107],"In":[108,144],"mode,":[110],"starting":[112],"point":[113],"database":[116,207],"labelled":[118,210],"according":[120],"scheme,":[125],"subsequent":[128],"use":[129],"allows":[133,184],"defining":[134],"membership":[136],"classes.":[143],"framework,":[146],"define":[148],"Correspondence":[150],"Indicators":[151],"as":[152],"measures":[153],"relationship":[155],"between":[156],"further":[161],"formulate":[162],"two":[163],"Bayesian":[164],"estimate":[167],"probability":[169],"for":[170],"unknown":[174],"belong":[177],"class.":[181],"approach":[183,204],"parametrisation":[186],"different":[188],"search":[190],"strategies":[191],"provides":[193],"direct":[195],"measure":[196],"annotation":[198,238,254],"error":[199],"rates.":[200],"We":[201],"validate":[202],"with":[205],"enzymes":[209],"their":[212],"corresponding":[213],"four-digit":[214],"EC":[215],"numbers":[216],"analyse":[218],"specific":[219],"cases.":[220],"CONCLUSION:":[221],"The":[222],"performance":[223],"method":[226],"significantly":[228],"higher":[229],"than":[230],"simple":[232],"strategy":[233],"consisting":[234],"in":[235,251],"transferring":[236],"highest":[241],"scoring":[242],"BLAST":[243],"match":[244],"find":[249],"applications":[250],"automated":[252],"pipelines.":[255]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}