{"id":"https://openalex.org/W2150389968","doi":"https://doi.org/10.1093/bioinformatics/btm633","title":"Beyond the \u2018best\u2019 match: machine learning annotation of protein sequences by integration of different sources of information","display_name":"Beyond the \u2018best\u2019 match: machine learning annotation of protein sequences by integration of different sources of information","publication_year":2008,"publication_date":"2008-01-03","ids":{"openalex":"https://openalex.org/W2150389968","doi":"https://doi.org/10.1093/bioinformatics/btm633","mag":"2150389968","pmid":"https://pubmed.ncbi.nlm.nih.gov/18174184"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btm633","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm633","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/5/621/49050534/bioinformatics_24_5_621.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/24/5/621/49050534/bioinformatics_24_5_621.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067679577","display_name":"Igor V. Tetko","orcid":"https://orcid.org/0000-0002-6855-0012"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Igor V. Tetko","raw_affiliation_strings":["1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany","institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210100097","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086939772","display_name":"Igor Rodchenkov","orcid":null},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Igor V. Rodchenkov","raw_affiliation_strings":["1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany","institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210100097","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081584590","display_name":"Mathias C. Walter","orcid":"https://orcid.org/0000-0003-3012-2626"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mathias C. Walter","raw_affiliation_strings":["1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany","institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210100097","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051653794","display_name":"Thomas Rattei","orcid":"https://orcid.org/0000-0002-0592-7791"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Rattei","raw_affiliation_strings":["1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany","institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210100097","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086890458","display_name":"Hans\u2010Werner Mewes","orcid":"https://orcid.org/0000-0002-9713-6398"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hans-Werner Mewes","raw_affiliation_strings":["1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Helmholtz Zentrum M\u00fcnchen - German Research Center for Environmental Health (GmbH), Institute of Bioinformatics and Systems Biology, Ingolst\u00e4dter Landstra\u00dfe 1, 85764, Neuherberg and 2Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universit\u00e4t M\u00fcnchen 85350 Freising, Germany","institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210100097","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067679577"],"corresponding_institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210100097","https://openalex.org/I62916508"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.6498,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.68823874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"24","issue":"5","first_page":"621","last_page":"628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.867900013923645,"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":0.867900013923645,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.025100000202655792,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.021700000390410423,"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":0.8092318177223206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.700392484664917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.502877414226532},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4393622875213623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.359595388174057}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8092318177223206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700392484664917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.502877414226532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4393622875213623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.359595388174057}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btm633","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm633","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/5/621/49050534/bioinformatics_24_5_621.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:18174184","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18174184","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/btm633","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm633","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/5/621/49050534/bioinformatics_24_5_621.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":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150389968.pdf","grobid_xml":"https://content.openalex.org/works/W2150389968.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W1492391409","https://openalex.org/W1504991194","https://openalex.org/W1517588910","https://openalex.org/W1521398555","https://openalex.org/W1533936090","https://openalex.org/W1536270671","https://openalex.org/W1541767983","https://openalex.org/W1554313068","https://openalex.org/W1647729745","https://openalex.org/W1975796937","https://openalex.org/W1992437878","https://openalex.org/W1993267991","https://openalex.org/W1997268601","https://openalex.org/W2002817195","https://openalex.org/W2005233786","https://openalex.org/W2006211612","https://openalex.org/W2006360003","https://openalex.org/W2011986160","https://openalex.org/W2026649417","https://openalex.org/W2050986127","https://openalex.org/W2051916497","https://openalex.org/W2055193239","https://openalex.org/W2065820441","https://openalex.org/W2070955875","https://openalex.org/W2071551353","https://openalex.org/W2077582053","https://openalex.org/W2087064593","https://openalex.org/W2097263991","https://openalex.org/W2097413543","https://openalex.org/W2100990314","https://openalex.org/W2103017472","https://openalex.org/W2106737886","https://openalex.org/W2110734043","https://openalex.org/W2114766824","https://openalex.org/W2116999639","https://openalex.org/W2117805756","https://openalex.org/W2119027485","https://openalex.org/W2119043225","https://openalex.org/W2119452210","https://openalex.org/W2124166542","https://openalex.org/W2126775187","https://openalex.org/W2128379497","https://openalex.org/W2128859735","https://openalex.org/W2129448726","https://openalex.org/W2130925474","https://openalex.org/W2133014144","https://openalex.org/W2134789671","https://openalex.org/W2135805255","https://openalex.org/W2136522597","https://openalex.org/W2137786672","https://openalex.org/W2137810087","https://openalex.org/W2137917513","https://openalex.org/W2144482798","https://openalex.org/W2152376949","https://openalex.org/W2152770371","https://openalex.org/W2153635508","https://openalex.org/W2154370832","https://openalex.org/W2155440340","https://openalex.org/W2158714788","https://openalex.org/W2160375677","https://openalex.org/W2161062388","https://openalex.org/W2161444669","https://openalex.org/W2161746138","https://openalex.org/W2166525781","https://openalex.org/W2167188257","https://openalex.org/W2171936986","https://openalex.org/W2172136887","https://openalex.org/W2950225692","https://openalex.org/W2951726307","https://openalex.org/W3120421331","https://openalex.org/W4246925013","https://openalex.org/W4248536238","https://openalex.org/W6636975626","https://openalex.org/W6677103964","https://openalex.org/W6677712588"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"MOTIVATION:":[0],"Accurate":[1],"automatic":[2,19],"assignment":[3],"of":[4,21,55,108,127,163],"protein":[5,80,104,176],"functions":[6],"remains":[7],"a":[8,26,48,53,93],"challenge":[9],"for":[10],"genome":[11],"annotation.":[12],"We":[13],"have":[14],"developed":[15,169],"and":[16,30,78,100,146],"compared":[17,123],"the":[18,89,96,102,109,125,136,143,150,154,175],"annotation":[20,121,159],"four":[22],"bacterial":[23,181],"genomes":[24,38],"employing":[25],"5-fold":[27],"cross-validation":[28],"procedure":[29],"several":[31],"machine":[32],"learning":[33],"methods.":[34],"RESULTS:":[35],"The":[36,64,112,131,139,157,168,184],"analyzed":[37],"were":[39,62,66],"manually":[40],"annotated":[41,101],"with":[42,95,105],"FunCat":[43],"categories":[44,107],"in":[45],"MIPS":[46],"providing":[47],"gold":[49],"standard.":[50],"Features":[51],"describing":[52],"pair":[54,94],"sequences":[56,177],"rather":[57],"than":[58],"each":[59],"sequence":[60,69,76,147],"alone":[61],"used.":[63],"descriptors":[65,129,140],"derived":[67,141],"from":[68,88,142,178],"alignment":[70],"scores,":[71],"InterPro":[72,144],"domains,":[73],"synteny":[74],"information,":[75],"length":[77],"calculated":[79],"properties.":[81],"Following":[82],"training":[83],"we":[84],"scored":[85],"all":[86],"pairs":[87],"validation":[90],"sets,":[91],"selected":[92],"highest":[97,151],"predicted":[98,158],"score":[99],"target":[103],"functional":[106],"prototype":[110],"protein.":[111],"data":[113],"integration":[114],"using":[115],"machine-learning":[116],"methods":[117],"provided":[118,149],"significantly":[119],"higher":[120],"accuracy":[122],"to":[124,153,173],"use":[126],"individual":[128],"alone.":[130],"neural":[132],"network":[133],"approach":[134,170],"showed":[135],"best":[137],"performance.":[138,156],"domains":[145],"similarity":[148],"contribution":[152],"method":[155],"scores":[160],"allow":[161],"differentiation":[162],"reliable":[164],"versus":[165],"non-reliable":[166],"annotations.":[167],"was":[171],"applied":[172],"annotate":[174],"180":[179],"complete":[180],"genomes.":[182],"AVAILABILITY:":[183],"FUNcat":[185],"Annotation":[186],"Tool":[187],"(FUNAT)":[188],"is":[189],"available":[190],"on-line":[191],"as":[192],"Web":[193],"Services":[194],"at":[195],"http://mips.gsf.de/proj/funat.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}