{"id":"https://openalex.org/W2093163894","doi":"https://doi.org/10.1093/nar/gki492","title":"WordSpy: identifying transcription factor binding motifs by building a dictionary and learning a grammar","display_name":"WordSpy: identifying transcription factor binding motifs by building a dictionary and learning a grammar","publication_year":2005,"publication_date":"2005-06-26","ids":{"openalex":"https://openalex.org/W2093163894","doi":"https://doi.org/10.1093/nar/gki492","mag":"2093163894","pmid":"https://pubmed.ncbi.nlm.nih.gov/15980501"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gki492","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gki492","pdf_url":"https://academic.oup.com/nar/article-pdf/33/suppl_2/W412/7623714/gki492.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","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/nar/article-pdf/33/suppl_2/W412/7623714/gki492.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067856421","display_name":"G. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"G. Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Washington University in Saint Louis, Saint Louis, MO 63130, USA","Department of Computer Science and Engineering, Washington University in Saint Louis, Saint Louis, MO 63130, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University in Saint Louis, Saint Louis, MO 63130, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University in Saint Louis, Saint Louis, MO 63130, USA#TAB#","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597138","display_name":"Tao Yu","orcid":"https://orcid.org/0009-0009-8381-6104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Yu","raw_affiliation_strings":["Department of Computer Science and Engineering and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068659777","display_name":"Weixiong Zhang","orcid":"https://orcid.org/0000-0002-4998-9791"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering and","Department of Genetics, Washington University in Saint Louis, Saint Louis, MO 63130, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and","institution_ids":[]},{"raw_affiliation_string":"Department of Genetics, Washington University in Saint Louis, Saint Louis, MO 63130, USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5067856421"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":{"value":3630,"currency":"USD","value_usd":3630},"fwci":2.0094,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.85783984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"Web Server","first_page":"W412","last_page":"W416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9979000091552734,"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":0.9853000044822693,"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/biology","display_name":"Biology","score":0.7231273651123047},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.6372133493423462},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6022484302520752},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5664870142936707},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.5558451414108276},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.555467963218689},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.5511309504508972},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.523115336894989},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5226504802703857},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4821281433105469},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4742364287376404},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.4535369575023651},{"id":"https://openalex.org/keywords/regulatory-sequence","display_name":"Regulatory sequence","score":0.447563111782074},{"id":"https://openalex.org/keywords/cis-regulatory-module","display_name":"Cis-regulatory module","score":0.43560490012168884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2839624881744385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26426321268081665},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.2135864496231079},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1416269838809967}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7231273651123047},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.6372133493423462},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6022484302520752},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5664870142936707},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.5558451414108276},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.555467963218689},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.5511309504508972},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.523115336894989},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5226504802703857},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4821281433105469},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4742364287376404},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.4535369575023651},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.447563111782074},{"id":"https://openalex.org/C190796033","wikidata":"https://www.wikidata.org/wiki/Q1093165","display_name":"Cis-regulatory module","level":5,"score":0.43560490012168884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2839624881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26426321268081665},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.2135864496231079},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1416269838809967},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","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":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"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},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/nar/gki492","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gki492","pdf_url":"https://academic.oup.com/nar/article-pdf/33/suppl_2/W412/7623714/gki492.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:15980501","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15980501","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":"Nucleic acids research","raw_type":null},{"id":"pmh:oai:europepmc.org:155253","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1160252","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/nar/gki492","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gki492","pdf_url":"https://academic.oup.com/nar/article-pdf/33/suppl_2/W412/7623714/gki492.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6211169549","display_name":"State-Space Reduction for Flexible and Approximate          Computation","funder_award_id":"0196057","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8568373648","display_name":"ITR/AP (CISE) Collaborative Research: Best-First Search Algorithms for Sequence Alignment Problems in Computational Biology","funder_award_id":"0113618","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2093163894.pdf","grobid_xml":"https://content.openalex.org/works/W2093163894.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W187269661","https://openalex.org/W1956090332","https://openalex.org/W1998300401","https://openalex.org/W2003967338","https://openalex.org/W2005244073","https://openalex.org/W2032231928","https://openalex.org/W2103453943","https://openalex.org/W2126602684","https://openalex.org/W2168157737","https://openalex.org/W2566466544","https://openalex.org/W4242314241","https://openalex.org/W4253987737","https://openalex.org/W4298215144"],"related_works":["https://openalex.org/W2073661767","https://openalex.org/W2143211236","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2103777723","https://openalex.org/W2117549173","https://openalex.org/W1502510273","https://openalex.org/W4390649590","https://openalex.org/W4387501506","https://openalex.org/W2134680153"],"abstract_inverted_index":{"Transcription":[0],"factor":[1],"(TF)":[2],"binding":[3,172],"sites":[4,173],"or":[5],"motifs":[6,75,97,163],"(TFBMs)":[7],"are":[8],"functional":[9],"cis-regulatory":[10],"DNA":[11],"sequences":[12,128,169],"that":[13],"play":[14],"an":[15,158],"essential":[16],"role":[17],"in":[18,104],"gene":[19,114],"transcriptional":[20],"regulation.":[21],"Although":[22],"many":[23],"experimental":[24],"and":[25,39,65,76,124,164],"computational":[26],"methods":[27],"have":[28],"been":[29],"developed,":[30],"finding":[31,46],"TFBMs":[32,120],"remains":[33],"a":[34,41,61,66,72,77,99,105,165],"challenging":[35],"problem.":[36],"We":[37,108],"propose":[38],"develop":[40],"novel":[42],"dictionary":[43,73],"based":[44],"motif":[45,88,171],"algorithm,":[47],"which":[48,69],"we":[49,135],"call":[50],"WordSpy.":[51],"One":[52],"significant":[53],"feature":[54],"of":[55,60,71,74,93,96,102,148,157,161,167,178],"WordSpy":[56,111,155,179],"is":[57,84,91,180],"the":[58,142,146,149],"combination":[59],"word":[62],"counting":[63],"method":[64],"statistical":[67],"model":[68],"consists":[70,156],"grammar":[78],"specifying":[79],"their":[80],"usage.":[81],"The":[82,152,175],"algorithm":[83],"suitable":[85],"for":[86],"genome-wide":[87],"finding;":[89],"it":[90],"capable":[92],"discovering":[94],"hundreds":[95],"from":[98,121,141,154],"large":[100],"set":[101,166],"promoters":[103,140],"single":[106],"run.":[107],"further":[109],"enhance":[110],"by":[112,125],"applying":[113],"expression":[115],"information":[116],"to":[117,129,144],"separate":[118],"true":[119],"spurious":[122],"ones,":[123],"incorporating":[126],"negative":[127],"identify":[130],"discriminative":[131],"motifs.":[132,151],"In":[133],"addition,":[134],"also":[136],"use":[137],"randomly":[138],"selected":[139],"genome":[143],"evaluate":[145],"significance":[147],"discovered":[150],"output":[153],"ordered":[159],"list":[160],"putative":[162],"regulatory":[168],"with":[170],"highlighted.":[174],"web":[176],"server":[177],"available":[181],"at":[182],"http://cic.cs.wustl.edu/wordspy.":[183]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}
