{"id":"https://openalex.org/W1971037820","doi":"https://doi.org/10.1109/tcbb.2014.2366146","title":"A Partial Least Squares Based Procedure for Upstream Sequence Classification in Prokaryotes","display_name":"A Partial Least Squares Based Procedure for Upstream Sequence Classification in Prokaryotes","publication_year":2014,"publication_date":"2014-11-10","ids":{"openalex":"https://openalex.org/W1971037820","doi":"https://doi.org/10.1109/tcbb.2014.2366146","mag":"1971037820","pmid":"https://pubmed.ncbi.nlm.nih.gov/26357267"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2014.2366146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2014.2366146","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5004305859","display_name":"Tahir Mehmood","orcid":"https://orcid.org/0000-0001-9775-8093"},"institutions":[{"id":"https://openalex.org/I54108979","display_name":"Norwegian University of Life Sciences","ror":"https://ror.org/04a1mvv97","country_code":"NO","type":"education","lineage":["https://openalex.org/I54108979"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Tahir Mehmood","raw_affiliation_strings":["Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway","[Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway","institution_ids":["https://openalex.org/I54108979"]},{"raw_affiliation_string":"[Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway.]","institution_ids":["https://openalex.org/I54108979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049001926","display_name":"Jon Bohlin","orcid":"https://orcid.org/0000-0002-0992-1311"},"institutions":[{"id":"https://openalex.org/I1333353642","display_name":"Norwegian Institute of Public Health","ror":"https://ror.org/046nvst19","country_code":"NO","type":"government","lineage":["https://openalex.org/I1333353642","https://openalex.org/I4210149801","https://openalex.org/I4210163359"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jon Bohlin","raw_affiliation_strings":["Norwegian Institute of Public Health, Division of Epidemiology, Marcus Thranes gate 6, 0403 Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian Institute of Public Health, Division of Epidemiology, Marcus Thranes gate 6, 0403 Oslo","institution_ids":["https://openalex.org/I1333353642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072350800","display_name":"Lars Snipen","orcid":"https://orcid.org/0000-0002-2883-861X"},"institutions":[{"id":"https://openalex.org/I54108979","display_name":"Norwegian University of Life Sciences","ror":"https://ror.org/04a1mvv97","country_code":"NO","type":"education","lineage":["https://openalex.org/I54108979"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Lars Snipen","raw_affiliation_strings":["Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway","[Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway","institution_ids":["https://openalex.org/I54108979"]},{"raw_affiliation_string":"[Department of Chemistry, Biotechnology and Food Sciences, Biostatistics Institute, Norwegian University of Life Sciences, Aas 1430, Akershous, Norway.]","institution_ids":["https://openalex.org/I54108979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.3932,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.59542285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"12","issue":"3","first_page":"560","last_page":"567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9983999729156494,"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/upstream","display_name":"Upstream (networking)","score":0.6551746129989624},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6376781463623047},{"id":"https://openalex.org/keywords/coding-region","display_name":"Coding region","score":0.5798451900482178},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5307742357254028},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5303179621696472},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5254209041595459},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5073608756065369},{"id":"https://openalex.org/keywords/upstream-activating-sequence","display_name":"Upstream activating sequence","score":0.4875342547893524},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4645540416240692},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.44831612706184387},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.44077861309051514},{"id":"https://openalex.org/keywords/upstream-and-downstream","display_name":"Upstream and downstream (DNA)","score":0.4268791377544403},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.42597225308418274},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3063134253025055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.29568374156951904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2724751830101013},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.13912266492843628},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.1338631808757782}],"concepts":[{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.6551746129989624},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6376781463623047},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.5798451900482178},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5307742357254028},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5303179621696472},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5254209041595459},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5073608756065369},{"id":"https://openalex.org/C192245184","wikidata":"https://www.wikidata.org/wiki/Q3552104","display_name":"Upstream activating sequence","level":5,"score":0.4875342547893524},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4645540416240692},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.44831612706184387},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.44077861309051514},{"id":"https://openalex.org/C158980903","wikidata":"https://www.wikidata.org/wiki/Q7899329","display_name":"Upstream and downstream (DNA)","level":3,"score":0.4268791377544403},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.42597225308418274},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3063134253025055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29568374156951904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2724751830101013},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.13912266492843628},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.1338631808757782},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"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":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","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":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2014.2366146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2014.2366146","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26357267","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26357267","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W242257288","https://openalex.org/W1480376652","https://openalex.org/W1484347389","https://openalex.org/W1981194976","https://openalex.org/W1988650678","https://openalex.org/W1997010323","https://openalex.org/W1998157707","https://openalex.org/W1999064315","https://openalex.org/W2007808016","https://openalex.org/W2018567038","https://openalex.org/W2030798529","https://openalex.org/W2031200646","https://openalex.org/W2047081748","https://openalex.org/W2055615325","https://openalex.org/W2093926580","https://openalex.org/W2095649738","https://openalex.org/W2097694646","https://openalex.org/W2107514803","https://openalex.org/W2108619906","https://openalex.org/W2109696618","https://openalex.org/W2110949266","https://openalex.org/W2119821739","https://openalex.org/W2127641304","https://openalex.org/W2143481518","https://openalex.org/W2143485490","https://openalex.org/W2148470786","https://openalex.org/W2150550043","https://openalex.org/W2159934528","https://openalex.org/W2160716554","https://openalex.org/W2162711333","https://openalex.org/W2171252918","https://openalex.org/W2911964244","https://openalex.org/W4239510810","https://openalex.org/W6685199251"],"related_works":["https://openalex.org/W3124485524","https://openalex.org/W4322775356","https://openalex.org/W2542074884","https://openalex.org/W2348356937","https://openalex.org/W4385833122","https://openalex.org/W3187420948","https://openalex.org/W3113528484","https://openalex.org/W2241146542","https://openalex.org/W2373560751","https://openalex.org/W3125376000"],"abstract_inverted_index":{"The":[0,63,133],"upstream":[1,56,61,64,103,134,149,178],"region":[2,150],"of":[3,54,66,102,116,176],"coding":[4,38,68,78],"genes":[5,69,79],"is":[6,126],"important":[7],"for":[8,11,51,86,130],"several":[9],"reasons,":[10],"instance":[12],"locating":[13],"transcription":[14],"factor,":[15],"binding":[16],"sites,":[17],"and":[18,120,144,158],"start":[19],"site":[20],"initiation":[21],"in":[22,74],"genomic":[23],"DNA.":[24],"Motivated":[25],"by":[26,82,107,140],"a":[27,44],"recently":[28],"conducted":[29],"study,":[30],"where":[31,76],"multivariate":[32],"approach":[33,146],"was":[34,138],"successfully":[35],"applied":[36],"to":[37,98,153],"sequence":[39,58,131,135],"modeling,":[40],"we":[41],"have":[42],"introduced":[43],"partial":[45],"least":[46],"squares":[47],"(PLS)":[48],"based":[49,109],"procedure":[50],"the":[52,100,164,177],"classification":[53,136],"true":[55],"prokaryotic":[57,89,148],"from":[59],"background":[60],"sequence.":[62],"sequences":[65],"conserved":[67,77],"over":[70],"genomes":[71],"were":[72,80,111],"considered":[73,88],"analysis,":[75],"found":[81],"using":[83,141],"pan-genomics":[84],"concept":[85],"each":[87],"species.":[90],"PLS":[91,108],"uses":[92],"position":[93],"specific":[94],"scoring":[95],"matrix":[96],"(PSSM)":[97],"study":[99],"characteristics":[101,175],"region.":[104,179],"Results":[105],"obtained":[106],"method":[110,129,166],"compared":[112],"with":[113,172],"Gini":[114],"importance":[115],"random":[117],"forest":[118],"(RF)":[119],"support":[121],"vector":[122],"machine":[123],"(SVM),":[124],"which":[125],"much":[127],"used":[128],"classification.":[132],"performance":[137],"evaluated":[139],"cross":[142],"validation,":[143],"suggested":[145],"identifies":[147],"significantly":[151],"better":[152],"RF":[154],"(p-value":[155,160],"<":[156,161],"0.01)":[157],"SVM":[159],"0.01).":[162],"Further,":[163],"proposed":[165],"also":[167],"produced":[168],"results":[169],"that":[170],"concurred":[171],"known":[173],"biological":[174]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}
