{"id":"https://openalex.org/W4229460206","doi":"https://doi.org/10.1186/s12859-022-04714-x","title":"Machine learning and statistics shape a novel path in archaeal promoter annotation","display_name":"Machine learning and statistics shape a novel path in archaeal promoter annotation","publication_year":2022,"publication_date":"2022-05-10","ids":{"openalex":"https://openalex.org/W4229460206","doi":"https://doi.org/10.1186/s12859-022-04714-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/35538405"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-022-04714-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04714-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04714-x","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":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04714-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079773743","display_name":"Gustavo Sganzerla Martinez","orcid":"https://orcid.org/0000-0002-7656-0579"},"institutions":[{"id":"https://openalex.org/I30338065","display_name":"Universidade de Caxias do Sul","ror":"https://ror.org/05rpzs058","country_code":"BR","type":"education","lineage":["https://openalex.org/I30338065"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Gustavo Sganzerla Martinez","raw_affiliation_strings":["Programa de P\u00f3s-Gradua\u00e7\u00e3o em Biotecnologia, Universidade de Caxias do Sul, Av. Francisco Get\u00falio Vargas, 1130, Caxias do Sul, RS, CEP 95070-560, Brazil"],"affiliations":[{"raw_affiliation_string":"Programa de P\u00f3s-Gradua\u00e7\u00e3o em Biotecnologia, Universidade de Caxias do Sul, Av. Francisco Get\u00falio Vargas, 1130, Caxias do Sul, RS, CEP 95070-560, Brazil","institution_ids":["https://openalex.org/I30338065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005750232","display_name":"Ernesto P\u00e9rez\u2010Rueda","orcid":"https://orcid.org/0000-0002-6879-0673"},"institutions":[{"id":"https://openalex.org/I8961855","display_name":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/01tmp8f25","country_code":"MX","type":"education","lineage":["https://openalex.org/I8961855"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ernesto P\u00e9rez-Rueda","raw_affiliation_strings":["Instituto de Investigaciones en Matem\u00e1ticas Aplicadas y en Sistemas, Universidad Nacional Aut\u00f3noma de M\u00e9xico, Unidad Acad\u00e9mica de Yucat\u00e1n, Yucat\u00e1n, M\u00e9rida, Mexico"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaciones en Matem\u00e1ticas Aplicadas y en Sistemas, Universidad Nacional Aut\u00f3noma de M\u00e9xico, Unidad Acad\u00e9mica de Yucat\u00e1n, Yucat\u00e1n, M\u00e9rida, Mexico","institution_ids":["https://openalex.org/I8961855"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035033999","display_name":"Sharmilee Sarkar","orcid":"https://orcid.org/0000-0001-5655-6874"},"institutions":[{"id":"https://openalex.org/I126601174","display_name":"Tezpur University","ror":"https://ror.org/005x56091","country_code":"IN","type":"education","lineage":["https://openalex.org/I126601174"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sharmilee Sarkar","raw_affiliation_strings":["Department of Molecular Biology and Biotechnology, Tezpur University, Tezpur, Assam, 784028, India"],"affiliations":[{"raw_affiliation_string":"Department of Molecular Biology and Biotechnology, Tezpur University, Tezpur, Assam, 784028, India","institution_ids":["https://openalex.org/I126601174"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031391323","display_name":"Aditya Kumar","orcid":"https://orcid.org/0000-0002-6474-8830"},"institutions":[{"id":"https://openalex.org/I126601174","display_name":"Tezpur University","ror":"https://ror.org/005x56091","country_code":"IN","type":"education","lineage":["https://openalex.org/I126601174"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Kumar","raw_affiliation_strings":["Department of Molecular Biology and Biotechnology, Tezpur University, Tezpur, Assam, 784028, India"],"affiliations":[{"raw_affiliation_string":"Department of Molecular Biology and Biotechnology, Tezpur University, Tezpur, Assam, 784028, India","institution_ids":["https://openalex.org/I126601174"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058894197","display_name":"Scheila de \u00c1vila e Silva","orcid":"https://orcid.org/0000-0002-3472-3907"},"institutions":[{"id":"https://openalex.org/I30338065","display_name":"Universidade de Caxias do Sul","ror":"https://ror.org/05rpzs058","country_code":"BR","type":"education","lineage":["https://openalex.org/I30338065"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Scheila de \u00c1vila e Silva","raw_affiliation_strings":["Programa de P\u00f3s-Gradua\u00e7\u00e3o em Biotecnologia, Universidade de Caxias do Sul, Av. Francisco Get\u00falio Vargas, 1130, Caxias do Sul, RS, CEP 95070-560, Brazil. sasilva6@ucs.br","Programa de P\u00f3s-Gradua\u00e7\u00e3o em Biotecnologia, Universidade de Caxias do Sul, Av. Francisco Get\u00falio Vargas, 1130, Caxias do Sul, RS, CEP 95070-560, Brazil"],"affiliations":[{"raw_affiliation_string":"Programa de P\u00f3s-Gradua\u00e7\u00e3o em Biotecnologia, Universidade de Caxias do Sul, Av. Francisco Get\u00falio Vargas, 1130, Caxias do Sul, RS, CEP 95070-560, Brazil. sasilva6@ucs.br","institution_ids":[]},{"raw_affiliation_string":"Programa de P\u00f3s-Gradua\u00e7\u00e3o em Biotecnologia, Universidade de Caxias do Sul, Av. Francisco Get\u00falio Vargas, 1130, Caxias do Sul, RS, CEP 95070-560, Brazil","institution_ids":["https://openalex.org/I30338065"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079773743"],"corresponding_institution_ids":["https://openalex.org/I30338065"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.1284,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.76236349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"23","issue":"1","first_page":"171","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.9966999888420105,"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/sulfolobus-solfataricus","display_name":"Sulfolobus solfataricus","score":0.8631969690322876},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.6644314527511597},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6383479833602905},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6356179118156433},{"id":"https://openalex.org/keywords/haloferax-volcanii","display_name":"Haloferax volcanii","score":0.5717275738716125},{"id":"https://openalex.org/keywords/archaea","display_name":"Archaea","score":0.5670438408851624},{"id":"https://openalex.org/keywords/sulfolobus","display_name":"Sulfolobus","score":0.5454944968223572},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.504193902015686},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.46387919783592224},{"id":"https://openalex.org/keywords/hyperthermophile","display_name":"Hyperthermophile","score":0.42811596393585205},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.39165836572647095},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.08803889155387878}],"concepts":[{"id":"https://openalex.org/C2780631447","wikidata":"https://www.wikidata.org/wiki/Q3503466","display_name":"Sulfolobus solfataricus","level":4,"score":0.8631969690322876},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.6644314527511597},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6383479833602905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6356179118156433},{"id":"https://openalex.org/C2776179084","wikidata":"https://www.wikidata.org/wiki/Q16982678","display_name":"Haloferax volcanii","level":4,"score":0.5717275738716125},{"id":"https://openalex.org/C550995028","wikidata":"https://www.wikidata.org/wiki/Q10872","display_name":"Archaea","level":3,"score":0.5670438408851624},{"id":"https://openalex.org/C2778644216","wikidata":"https://www.wikidata.org/wiki/Q1209791","display_name":"Sulfolobus","level":4,"score":0.5454944968223572},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.504193902015686},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.46387919783592224},{"id":"https://openalex.org/C55428944","wikidata":"https://www.wikidata.org/wiki/Q1784119","display_name":"Hyperthermophile","level":4,"score":0.42811596393585205},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.39165836572647095},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.08803889155387878}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-022-04714-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04714-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04714-x","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:35538405","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35538405","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:doaj.org/article:9a55fc5174c7482cb711da615ddf31f9","is_oa":true,"landing_page_url":"https://doaj.org/article/9a55fc5174c7482cb711da615ddf31f9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 23, Iss 1, Pp 1-14 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9087966","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9087966","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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"}],"best_oa_location":{"id":"doi:10.1186/s12859-022-04714-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04714-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04714-x","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":[{"display_name":"Life in Land","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G5139334624","display_name":null,"funder_award_id":"Coordena\u00e7\u00e3o","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/G692611148","display_name":null,"funder_award_id":"Brazil","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/G963174003","display_name":null,"funder_award_id":"de Aperfei\u00e7","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"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/F4320323401","display_name":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/01tmp8f25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4229460206.pdf","grobid_xml":"https://content.openalex.org/works/W4229460206.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1493378561","https://openalex.org/W1780156870","https://openalex.org/W1972593478","https://openalex.org/W1973488942","https://openalex.org/W2003188984","https://openalex.org/W2064397639","https://openalex.org/W2076118331","https://openalex.org/W2083122216","https://openalex.org/W2084246818","https://openalex.org/W2110612352","https://openalex.org/W2112081648","https://openalex.org/W2112333437","https://openalex.org/W2114120960","https://openalex.org/W2126939295","https://openalex.org/W2134977238","https://openalex.org/W2151605074","https://openalex.org/W2154379317","https://openalex.org/W2513021116","https://openalex.org/W2613885973","https://openalex.org/W2766430438","https://openalex.org/W2767716592","https://openalex.org/W2787629429","https://openalex.org/W2807110181","https://openalex.org/W2810754857","https://openalex.org/W2885307904","https://openalex.org/W2900659973","https://openalex.org/W2932524182","https://openalex.org/W2955031793","https://openalex.org/W3022704487","https://openalex.org/W3047183845","https://openalex.org/W3124199946","https://openalex.org/W3209160030"],"related_works":["https://openalex.org/W2291533887","https://openalex.org/W2136227817","https://openalex.org/W2760207402","https://openalex.org/W2149125844","https://openalex.org/W2614047336","https://openalex.org/W2979278439","https://openalex.org/W4249320990","https://openalex.org/W1999509531","https://openalex.org/W3024210989","https://openalex.org/W4386457921"],"abstract_inverted_index":{"The":[0],"classification":[1],"models":[2],"were":[3],"employed":[4],"to":[5],"perform":[6],"genomic":[7],"annotation":[8],"into":[9,26],"the":[10],"archaea":[11],"Aciduliprofundum":[12],"boonei":[13],"and":[14,24],"Thermofilum":[15],"pendens,":[16],"from":[17],"which":[18],"potential":[19],"promoters":[20],"have":[21],"been":[22],"identified":[23],"uploaded":[25],"public":[27],"repositories.":[28]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
