{"id":"https://openalex.org/W2120710794","doi":"https://doi.org/10.1186/1471-2105-7-342","title":"EMD: an ensemble algorithm for discovering regulatory motifs in DNA sequences","display_name":"EMD: an ensemble algorithm for discovering regulatory motifs in DNA sequences","publication_year":2006,"publication_date":"2006-07-13","ids":{"openalex":"https://openalex.org/W2120710794","doi":"https://doi.org/10.1186/1471-2105-7-342","mag":"2120710794","pmid":"https://pubmed.ncbi.nlm.nih.gov/16839417"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-342","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-342","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-342","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/10.1186/1471-2105-7-342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080081719","display_name":"Jianjun Hu","orcid":"https://orcid.org/0000-0002-5177-399X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianjun Hu","raw_affiliation_strings":["Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA. hu5@purdue.edu","Department of Computer Science, Purdue University, West Lafayette, IN, 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA. hu5@purdue.edu","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102323616","display_name":"Yi\u2010Feng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifeng D Yang","raw_affiliation_strings":["Department of Biological Sciences, Purdue University, West Lafayette, IN, 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062293219","display_name":"Daisuke Kihara","orcid":"https://orcid.org/0000-0003-4091-6614"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daisuke Kihara","raw_affiliation_strings":["Department of Biological Sciences, Purdue University, West Lafayette, IN, 47907, USA","Department of Computer Science, Purdue University, West Lafayette, IN, 47907, USA","Markey Center for Structural Biology, Purdue University, West Lafayette, IN, 47907, USA","The Bindley Bioscience Center, Discovery Park, Purdue University, West Lafayette, IN, 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Markey Center for Structural Biology, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"The Bindley Bioscience Center, Discovery Park, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062293219"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":2.4162,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.88529067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"1","first_page":"342","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9757000207901001,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9757000207901001,"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":0.013500000350177288,"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/T10885","display_name":"Gene expression and cancer classification","score":0.00139999995008111,"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/algorithm","display_name":"Algorithm","score":0.7033494710922241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6529797315597534},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.57753586769104},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5260244011878967},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5053730607032776},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5021662712097168},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4776281714439392},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38046419620513916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36664819717407227},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10660660266876221},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10650357604026794}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.7033494710922241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6529797315597534},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.57753586769104},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5260244011878967},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5053730607032776},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5021662712097168},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4776281714439392},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38046419620513916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36664819717407227},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10660660266876221},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10650357604026794},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1186/1471-2105-7-342","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-342","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-342","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:16839417","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16839417","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:docs.lib.purdue.edu:bioscipubs-1024","is_oa":true,"landing_page_url":"https://docs.lib.purdue.edu/bioscipubs/25","pdf_url":"https://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1024&context=bioscipubs","source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Biological Sciences Faculty Publications","raw_type":"text"},{"id":"pmh:oai:docs.lib.purdue.edu:bioscipubs-1076","is_oa":true,"landing_page_url":"https://docs.lib.purdue.edu/bioscipubs/76","pdf_url":"https://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1076&context=bioscipubs","source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"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":"Department of Biological Sciences Faculty Publications","raw_type":"text"},{"id":"pmh:oai:scholarcommons.sc.edu:csce_facpub-1113","is_oa":true,"landing_page_url":"https://scholarcommons.sc.edu/csce_facpub/116","pdf_url":"https://scholarcommons.sc.edu/csce_facpub/116","source":{"id":"https://openalex.org/S4377196354","display_name":"Scholar Commons (University of South Carolina)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I155781252","host_organization_name":"University of South Carolina","host_organization_lineage":["https://openalex.org/I155781252"],"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":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:e43149765b74482781e31f50b50b3d59","is_oa":false,"landing_page_url":"https://doaj.org/article/e43149765b74482781e31f50b50b3d59","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 7, Iss 1, p 342 (2006)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1539026","is_oa":true,"landing_page_url":"http://doi.org/10.1186/1471-2105-7-342","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-7-342","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-342","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-342","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":[],"awards":[{"id":"https://openalex.org/G1255322771","display_name":null,"funder_award_id":"U24 GM077905","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G129686525","display_name":null,"funder_award_id":"R01 GM075004","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2167240763","display_name":"Bayesian models and Monte Carlo strategies in identifying protein or DNA sequence motifs","funder_award_id":"0604776","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3611247453","display_name":null,"funder_award_id":"R01GM","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G491830786","display_name":null,"funder_award_id":"U24GM077905","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2120710794.pdf","grobid_xml":"https://content.openalex.org/works/W2120710794.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1491590499","https://openalex.org/W1969051510","https://openalex.org/W1987122345","https://openalex.org/W1996342555","https://openalex.org/W1998300401","https://openalex.org/W2002584605","https://openalex.org/W2028904582","https://openalex.org/W2034206030","https://openalex.org/W2041726559","https://openalex.org/W2056002855","https://openalex.org/W2062123114","https://openalex.org/W2073850887","https://openalex.org/W2079659879","https://openalex.org/W2080855949","https://openalex.org/W2084908610","https://openalex.org/W2092904290","https://openalex.org/W2094051420","https://openalex.org/W2096139934","https://openalex.org/W2097556481","https://openalex.org/W2098487344","https://openalex.org/W2100558818","https://openalex.org/W2101843343","https://openalex.org/W2113410382","https://openalex.org/W2115772919","https://openalex.org/W2115979107","https://openalex.org/W2121356022","https://openalex.org/W2123485441","https://openalex.org/W2130280638","https://openalex.org/W2134591904","https://openalex.org/W2135221645","https://openalex.org/W2141408320","https://openalex.org/W2141783940","https://openalex.org/W2142237411","https://openalex.org/W2152824658","https://openalex.org/W2155333853","https://openalex.org/W2170778160","https://openalex.org/W2429595474","https://openalex.org/W2610493035","https://openalex.org/W4239029175"],"related_works":["https://openalex.org/W4376643315","https://openalex.org/W4324137541","https://openalex.org/W2900445707","https://openalex.org/W4285741730","https://openalex.org/W1191482210","https://openalex.org/W4285046548","https://openalex.org/W4210302090","https://openalex.org/W3092276832","https://openalex.org/W3111529524","https://openalex.org/W4375951447"],"abstract_inverted_index":{"BACKGROUND:":[0],"Understanding":[1],"gene":[2],"regulatory":[3,25],"networks":[4],"has":[5,126],"become":[6],"one":[7,90],"of":[8,36,64,89,132,146,172,195,198,202,226,231],"the":[9,28,33,55,60,102,107,133,139,147,168,173,188,196,210,224,227,232,239,251],"central":[10],"research":[11],"problems":[12],"in":[13,51,130,238],"bioinformatics.":[14],"More":[15],"than":[16],"thirty":[17,30],"algorithms":[18,38,44,176],"have":[19,45,207],"been":[20],"proposed":[21,69,183],"to":[22,101,250],"identify":[23],"DNA":[24],"sites":[26],"during":[27],"past":[29],"years.":[31],"However,":[32],"prediction":[34,56,62,136],"accuracy":[35,57,137,225],"these":[37],"is":[39,99,112,150,213,235],"still":[40],"quite":[41],"low.":[42],"Ensemble":[43],"emerged":[46],"as":[47],"an":[48,184,214],"effective":[49,215],"strategy":[50,216],"bioinformatics":[52],"for":[53,77,106,153,178,187,217],"improving":[54,218],"by":[58,82,192],"exploiting":[59],"synergetic":[61],"capability":[63],"multiple":[65,84,87],"algorithms.":[66,95],"RESULTS:":[67],"We":[68,182,206],"a":[70,115,199,242],"novel":[71],"clustering-based":[72],"ensemble":[73,97,185,211],"algorithm":[74,111,125,149,234,245],"named":[75],"EMD":[76,124,148,233],"de":[78],"novo":[79],"motif":[80,103,189,203],"discovery":[81,104,190,204],"combining":[83],"predictions":[85],"from":[86,119],"runs":[88],"or":[91,163],"more":[92,151],"base":[93],"component":[94,142,175],"The":[96,110,123,144,229],"approach":[98,186,212],"applied":[100],"problem":[105,191],"first":[108],"time.":[109],"tested":[113],"on":[114],"benchmark":[116],"dataset":[117],"generated":[118],"E.":[120],"coli":[121],"RegulonDB.":[122],"achieved":[127],"22.4%":[128],"improvement":[129],"terms":[131],"nucleotide":[134],"level":[135,171],"over":[138],"best":[140],"stand-alone":[141,174],"algorithm.":[143],"advantage":[145,194,230],"significant":[152],"shorter":[154],"input":[155],"sequences,":[156],"but":[157],"most":[158],"importantly,":[159],"it":[160],"always":[161],"outperforms":[162],"at":[164,167],"least":[165],"stays":[166],"same":[169],"performance":[170],"even":[177],"longer":[179],"sequences.":[180],"CONCLUSION:":[181],"taking":[193],"availability":[197],"large":[200],"number":[201],"programs.":[205],"shown":[208],"that":[209,241],"both":[219],"sensitivity":[220],"and":[221],"specificity,":[222],"thus":[223],"prediction.":[228],"its":[236],"flexibility":[237],"sense":[240],"new":[243],"powerful":[244],"can":[246],"be":[247],"easily":[248],"added":[249],"system.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}