{"id":"https://openalex.org/W2092714248","doi":"https://doi.org/10.1109/ijcnn.2014.6889557","title":"Issues on sampling negative examples for predicting prokaryotic promoters","display_name":"Issues on sampling negative examples for predicting prokaryotic promoters","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2092714248","doi":"https://doi.org/10.1109/ijcnn.2014.6889557","mag":"2092714248"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2014.6889557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5030617406","display_name":"Eduardo Gade Gusmao","orcid":"https://orcid.org/0000-0001-7461-1443"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eduardo G. Gusmao","raw_affiliation_strings":["IZKF Aachen Computational Biology Research Group, Institute for Biomedical Engineering, Aachen, Germany","Med. Sch., Inst. for Biomed. Eng., RWTH Aachen Univ., Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IZKF Aachen Computational Biology Research Group, Institute for Biomedical Engineering, Aachen, Germany","institution_ids":[]},{"raw_affiliation_string":"Med. Sch., Inst. for Biomed. Eng., RWTH Aachen Univ., Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064710760","display_name":"Marc\u00edlio C. P. de Souto","orcid":"https://orcid.org/0000-0002-7033-8328"},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]},{"id":"https://openalex.org/I4210129154","display_name":"Services d\u00e9concentr\u00e9s d'appui \u00e0 la recherche Val de Loire","ror":"https://ror.org/03ntmtb29","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210129154"]},{"id":"https://openalex.org/I4210143826","display_name":"Institut National des Sciences Appliqu\u00e9es Centre Val de Loire","ror":"https://ror.org/03y0qc033","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210143826"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marcilio C. P. de Souto","raw_affiliation_strings":["Univ. Orl\u00e9ans, INSA Centre Val de Loire, Orl\u00e9ans, France","LIFO, Univ. Orleans INSA Centre Val de Loire, Orleans, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Orl\u00e9ans, INSA Centre Val de Loire, Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238","https://openalex.org/I4210129154","https://openalex.org/I4210143826"]},{"raw_affiliation_string":"LIFO, Univ. Orleans INSA Centre Val de Loire, Orleans, France","institution_ids":["https://openalex.org/I12449238","https://openalex.org/I4210143826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2026,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88361079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"494","last_page":"501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9984999895095825,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.998199999332428,"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/promoter","display_name":"Promoter","score":0.7137824296951294},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6701450347900391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5573851466178894},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4580179750919342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350113272666931},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40214812755584717},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.39923739433288574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33136141300201416},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3270893692970276},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3249080181121826},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.29476165771484375},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1976534128189087},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.07458212971687317}],"concepts":[{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.7137824296951294},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6701450347900391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5573851466178894},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4580179750919342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350113272666931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40214812755584717},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39923739433288574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33136141300201416},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3270893692970276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3249080181121826},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.29476165771484375},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1976534128189087},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.07458212971687317},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2014.6889557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00955531v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00955531","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE IJCNN 2014, Jul 2014, Beijing, China. pp.494-501, ⟨10.1109/IJCNN.2014.6889557⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1508395088","https://openalex.org/W1548736848","https://openalex.org/W1985986400","https://openalex.org/W1986403075","https://openalex.org/W1998525134","https://openalex.org/W2004711925","https://openalex.org/W2010588769","https://openalex.org/W2036092121","https://openalex.org/W2054331129","https://openalex.org/W2063555458","https://openalex.org/W2097651291","https://openalex.org/W2101029276","https://openalex.org/W2101492309","https://openalex.org/W2108740562","https://openalex.org/W2121400095","https://openalex.org/W2125970547","https://openalex.org/W2134497014","https://openalex.org/W2153937392","https://openalex.org/W2157009395","https://openalex.org/W2167821759","https://openalex.org/W4231536396","https://openalex.org/W4239403073","https://openalex.org/W4244296837","https://openalex.org/W6682682869"],"related_works":["https://openalex.org/W1969771092","https://openalex.org/W2795723184","https://openalex.org/W2025529750","https://openalex.org/W2891858816","https://openalex.org/W184057646","https://openalex.org/W2042874675","https://openalex.org/W129398428","https://openalex.org/W3212414177","https://openalex.org/W2007418658","https://openalex.org/W1967718992"],"abstract_inverted_index":{"Supervised":[0],"learning":[1],"methods":[2],"have":[3],"been":[4],"successfully":[5],"used":[6,41],"to":[7,66,92,130,179],"build":[8,131],"classifiers":[9],"for":[10,42,101,166,189],"the":[11,39,97,102,132,140,143,151,159,190],"identification":[12],"of":[13,27,38,104,112,125,142,150,158,161,164,187,192],"promoter":[14,28,47,60,167,194],"regions.":[15,33],"The":[16],"classifier":[17,144],"is":[18,50,83,107,182],"often":[19],"built":[20],"from":[21],"a":[22,35,46,51,77,81,109,114,119,135,147,185],"dataset":[23],"that":[24],"has":[25],"examples":[26],"(positive)":[29],"and":[30,44],"non-promoter":[31,82,126],"(negative)":[32],"Thus,":[34],"careful":[36],"selection":[37],"data":[40],"constructing":[43],"evaluating":[45],"finding":[48],"algorithm":[49],"very":[52],"important":[53],"issue.":[54],"In":[55,71],"this":[56,162],"context,":[57],"experimentally":[58],"known":[59],"regions":[61],"can":[62],"be":[63,67,93],"safely":[64],"assumed":[65,129],"positive":[68],"training":[69],"instances.":[70],"contrast,":[72],"since":[73],"definite":[74],"knowledge":[75],"whether":[76],"given":[78],"region":[79,127],"represents":[80],"not":[84,90,108],"generally":[85],"available,":[86],"negative":[87,115],"instances":[88],"are":[89,176],"straightforward":[91],"obtained.":[94],"To":[95],"make":[96],"problem":[98,165],"more":[99],"complex,":[100],"case":[103],"promoter,":[105],"there":[106,181],"unique":[110],"definition":[111,124],"what":[113],"instance":[116],"is.":[117],"As":[118,172],"consequence,":[120],"depending":[121],"on":[122],"which":[123],"one":[128],"data,":[133],"such":[134,184],"choice":[136],"could":[137],"affect":[138],"significantly":[139],"performance":[141],"and/or":[145],"yield":[146],"biased":[148],"estimate":[149],"performance.":[152],"We":[153],"present":[154],"an":[155],"empirical":[156],"study":[157,188],"effect":[160],"kind":[163,186],"prediction":[168],"in":[169],"E.":[170],"coli.":[171],"far":[173],"as":[174],"we":[175],"concerned,":[177],"up":[178],"now,":[180],"no":[183],"context":[191],"prokaryotic":[193],"prediction.":[195]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}