{"id":"https://openalex.org/W3102524682","doi":"https://doi.org/10.1093/database/baaa067","title":"OCCAM: prediction of small ORFs in bacterial genomes by means of a target-decoy database approach and machine learning techniques","display_name":"OCCAM: prediction of small ORFs in bacterial genomes by means of a target-decoy database approach and machine learning techniques","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3102524682","doi":"https://doi.org/10.1093/database/baaa067","mag":"3102524682","pmid":"https://pubmed.ncbi.nlm.nih.gov/33206960"},"language":"en","primary_location":{"id":"doi:10.1093/database/baaa067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaa067","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa067/34385717/baaa067.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa067/34385717/baaa067.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029149702","display_name":"F\u00e1bio Ribeiro Cerqueira","orcid":"https://orcid.org/0000-0003-1325-2592"},"institutions":[{"id":"https://openalex.org/I146165071","display_name":"Universidade Federal de Vi\u00e7osa","ror":"https://ror.org/0409dgb37","country_code":"BR","type":"education","lineage":["https://openalex.org/I146165071"]},{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Fabio R. Cerqueira","raw_affiliation_strings":["Department of Production Engineering, Universidade Federal Fluminense, Rua Domingos Silv\u00e9rio s/n, Petr\u00f3polis, 25\u2009650-050, Rio de Janeiro, Brazil","Graduate Program in Computer Science, Universidade Federal de Vi\u00e7osa, 36570-900, Minas Gerais, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Production Engineering, Universidade Federal Fluminense, Rua Domingos Silv\u00e9rio s/n, Petr\u00f3polis, 25\u2009650-050, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I161127581"]},{"raw_affiliation_string":"Graduate Program in Computer Science, Universidade Federal de Vi\u00e7osa, 36570-900, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I146165071"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000425403","display_name":"Ana Tereza Ribeiro de Vasconcelos","orcid":"https://orcid.org/0000-0002-4632-2086"},"institutions":[{"id":"https://openalex.org/I4210142352","display_name":"Laborat\u00f3rio Nacional de Computa\u00e7\u00e3o Cient\u00edfica","ror":"https://ror.org/0498ekt05","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210142352"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Ana Tereza Ribeiro Vasconcelos","raw_affiliation_strings":["Laborat\u00f3rio Nacional de Computa\u00e7\u00e3o Cient\u00edfica, Rua Get\u00falio Vargas 333, Petrop\u00f3lis, 25\u2009651-071, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laborat\u00f3rio Nacional de Computa\u00e7\u00e3o Cient\u00edfica, Rua Get\u00falio Vargas 333, Petrop\u00f3lis, 25\u2009651-071, Brazil","institution_ids":["https://openalex.org/I4210142352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000425403","https://openalex.org/A5029149702"],"corresponding_institution_ids":["https://openalex.org/I146165071","https://openalex.org/I161127581","https://openalex.org/I4210142352"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.2242,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.5018566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2020","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9986000061035156,"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":0.9958000183105469,"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/orfs","display_name":"ORFS","score":0.9837343096733093},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6156156063079834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5882249474525452},{"id":"https://openalex.org/keywords/open-reading-frame","display_name":"Open reading frame","score":0.48260605335235596},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.43545275926589966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39303916692733765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32164329290390015},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2904397249221802},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.16158592700958252},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.0774475634098053}],"concepts":[{"id":"https://openalex.org/C2780530800","wikidata":"https://www.wikidata.org/wiki/Q7072921","display_name":"ORFS","level":5,"score":0.9837343096733093},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6156156063079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5882249474525452},{"id":"https://openalex.org/C47289529","wikidata":"https://www.wikidata.org/wiki/Q908550","display_name":"Open reading frame","level":4,"score":0.48260605335235596},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.43545275926589966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39303916692733765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32164329290390015},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2904397249221802},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16158592700958252},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0774475634098053},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":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":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/baaa067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaa067","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa067/34385717/baaa067.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:33206960","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33206960","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7673341","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7673341","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":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baaa067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaa067","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaa067/34385717/baaa067.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1189127572","display_name":null,"funder_award_id":"E -26/202.826/2018","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G1840770272","display_name":null,"funder_award_id":"E-26/","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G228631196","display_name":null,"funder_award_id":"E-26/202","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"},{"id":"https://openalex.org/G6352592334","display_name":null,"funder_award_id":"26/202.826/2018","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G8522711164","display_name":null,"funder_award_id":"26/202","funder_id":"https://openalex.org/F4320322749","funder_display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322749","display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro","ror":"https://ror.org/03kk0s825"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3102524682.pdf","grobid_xml":"https://content.openalex.org/works/W3102524682.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1418224","https://openalex.org/W1565377632","https://openalex.org/W1570448133","https://openalex.org/W1585056964","https://openalex.org/W1596013564","https://openalex.org/W1873623553","https://openalex.org/W1910105722","https://openalex.org/W1963945004","https://openalex.org/W1966072767","https://openalex.org/W1974042541","https://openalex.org/W1974274010","https://openalex.org/W1978164115","https://openalex.org/W1988667155","https://openalex.org/W1991585120","https://openalex.org/W1993521195","https://openalex.org/W2001491464","https://openalex.org/W2006325103","https://openalex.org/W2017716401","https://openalex.org/W2026465178","https://openalex.org/W2029318328","https://openalex.org/W2032883256","https://openalex.org/W2044109668","https://openalex.org/W2044750677","https://openalex.org/W2046374424","https://openalex.org/W2049789492","https://openalex.org/W2056000843","https://openalex.org/W2056666869","https://openalex.org/W2067183112","https://openalex.org/W2069516894","https://openalex.org/W2078266900","https://openalex.org/W2078460085","https://openalex.org/W2090327616","https://openalex.org/W2094894695","https://openalex.org/W2096049571","https://openalex.org/W2105199251","https://openalex.org/W2107158165","https://openalex.org/W2107903949","https://openalex.org/W2115036455","https://openalex.org/W2116041602","https://openalex.org/W2117725451","https://openalex.org/W2118993019","https://openalex.org/W2128580612","https://openalex.org/W2130168792","https://openalex.org/W2130308509","https://openalex.org/W2131892542","https://openalex.org/W2133990480","https://openalex.org/W2139658526","https://openalex.org/W2142699726","https://openalex.org/W2145292712","https://openalex.org/W2154350719","https://openalex.org/W2158714788","https://openalex.org/W2160017921","https://openalex.org/W2162417400","https://openalex.org/W2370363004","https://openalex.org/W2482589566","https://openalex.org/W2582077910","https://openalex.org/W2772727999","https://openalex.org/W2893439770","https://openalex.org/W2914192686","https://openalex.org/W2971297443","https://openalex.org/W2984180404","https://openalex.org/W2989594905","https://openalex.org/W2990951173","https://openalex.org/W2993472898","https://openalex.org/W3021822345","https://openalex.org/W3022137185","https://openalex.org/W4249445149","https://openalex.org/W6639230807","https://openalex.org/W6650734014","https://openalex.org/W6651910485","https://openalex.org/W6662236866"],"related_works":["https://openalex.org/W2017477982","https://openalex.org/W1978801575","https://openalex.org/W2029252138","https://openalex.org/W4306784270","https://openalex.org/W2101899141","https://openalex.org/W3031046715","https://openalex.org/W2017335389","https://openalex.org/W2358544099","https://openalex.org/W1976390578","https://openalex.org/W2072439611"],"abstract_inverted_index":{"Small":[0],"open":[1],"reading":[2],"frames":[3],"(ORFs)":[4],"have":[5],"been":[6],"systematically":[7],"disregarded":[8],"by":[9,32],"automatic":[10],"genome":[11],"annotation.":[12],"The":[13],"difficulty":[14],"in":[15,18,37,48,58,91,120,137,162,201],"finding":[16],"patterns":[17],"tiny":[19],"sequences":[20,102],"is":[21,53,78,134,184],"the":[22,59,67,126,138,157,188,196],"main":[23],"reason":[24],"that":[25,41,111,156],"makes":[26],"small":[27,42,71,89,141,199],"ORFs":[28,90,142,200],"to":[29,55,64,87,103,165],"be":[30,117],"overlooked":[31],"computational":[33,62,193],"procedures.":[34],"However,":[35],"advances":[36],"experimental":[38],"methods":[39],"show":[40,110,155],"proteins":[43],"can":[44,116,169],"play":[45],"vital":[46],"roles":[47],"cellular":[49],"activities.":[50],"Hence,":[51],"it":[52],"urgent":[54],"make":[56],"progress":[57],"development":[60],"of":[61,69,122,140,175,190,198],"approaches":[63],"speed":[65],"up":[66],"identification":[68,197],"potential":[70],"ORFs.":[72],"In":[73],"this":[74],"work,":[75],"our":[76,163],"focus":[77],"on":[79],"bacterial":[80],"genomes.":[81],"We":[82,109],"improve":[83],"a":[84],"previous":[85],"approach":[86],"identify":[88],"bacteria.":[92,202],"Our":[93],"method":[94,164],"uses":[95],"machine":[96,158],"learning":[97,159],"techniques":[98],"and":[99,128,173,177],"decoy":[100],"subject":[101],"filter":[104],"out":[105],"spurious":[106],"ORF":[107],"alignments.":[108],"an":[112,181],"advanced":[113],"multivariate":[114],"analysis":[115],"more":[118,191],"effective":[119],"terms":[121],"sensitivity":[123,172],"than":[124,149],"applying":[125],"simplistic":[127],"widely":[129],"used":[130,161],"e-value":[131],"cutoff.":[132],"This":[133],"particularly":[135],"important":[136,182],"case":[139],"for":[143,195],"which":[144],"alignments":[145,168],"present":[146],"higher":[147],"e-values":[148],"usual.":[150],"Experiments":[151],"with":[152],"control":[153],"datasets":[154],"algorithms":[160],"curate":[166],"significant":[167],"achieve":[170],"average":[171],"specificity":[174],"97.06%":[176],"99.61%,":[178],"respectively.":[179],"Therefore,":[180],"step":[183],"provided":[185],"here":[186],"toward":[187],"construction":[189],"accurate":[192],"tools":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2020-11-23T00:00:00"}
