{"id":"https://openalex.org/W2089783852","doi":"https://doi.org/10.1093/nar/gkg618","title":"YMF: a program for discovery of novel transcription factor binding sites by statistical overrepresentation","display_name":"YMF: a program for discovery of novel transcription factor binding sites by statistical overrepresentation","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2089783852","doi":"https://doi.org/10.1093/nar/gkg618","mag":"2089783852","pmid":"https://pubmed.ncbi.nlm.nih.gov/12824371"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gkg618","is_oa":false,"landing_page_url":"https://doi.org/10.1093/nar/gkg618","pdf_url":null,"source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"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":null,"license_id":null,"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":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027026155","display_name":"Satrajit Sinha","orcid":"https://orcid.org/0000-0002-9574-4576"},"institutions":[{"id":"https://openalex.org/I83399316","display_name":"Rockefeller University","ror":"https://ror.org/0420db125","country_code":"US","type":"education","lineage":["https://openalex.org/I83399316"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Sinha","raw_affiliation_strings":["Center for Studies in Physics and Biology, Box 25, The Rockefeller University, 1230 York Avenue, New York, NY 10021, USA"],"affiliations":[{"raw_affiliation_string":"Center for Studies in Physics and Biology, Box 25, The Rockefeller University, 1230 York Avenue, New York, NY 10021, USA","institution_ids":["https://openalex.org/I83399316"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027026155"],"corresponding_institution_ids":["https://openalex.org/I83399316"],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":null,"fwci":4.5756,"has_fulltext":false,"cited_by_count":259,"citation_normalized_percentile":{"value":0.9562976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"31","issue":"13","first_page":"3586","last_page":"3588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9940999746322632,"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":0.9940999746322632,"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":0.9650999903678894,"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":0.9643999934196472,"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":0.8624222278594971},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.6559278964996338},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5877150297164917},{"id":"https://openalex.org/keywords/binding-site","display_name":"Binding site","score":0.5820556282997131},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.576041042804718},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5682756900787354},{"id":"https://openalex.org/keywords/dna-binding-protein","display_name":"DNA-binding protein","score":0.4139154851436615},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.40295088291168213},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.33688920736312866},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.16768360137939453},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.10554200410842896}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.8624222278594971},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.6559278964996338},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5877150297164917},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.5820556282997131},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.576041042804718},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5682756900787354},{"id":"https://openalex.org/C94966510","wikidata":"https://www.wikidata.org/wiki/Q2252764","display_name":"DNA-binding protein","level":4,"score":0.4139154851436615},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.40295088291168213},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.33688920736312866},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.16768360137939453},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.10554200410842896}],"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":"D000465","descriptor_name":"Algorithms","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":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009169","descriptor_name":"Mycobacterium tuberculosis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009169","descriptor_name":"Mycobacterium tuberculosis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009169","descriptor_name":"Mycobacterium tuberculosis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009169","descriptor_name":"Mycobacterium tuberculosis","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"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":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"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":"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","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}],"locations_count":4,"locations":[{"id":"doi:10.1093/nar/gkg618","is_oa":false,"landing_page_url":"https://doi.org/10.1093/nar/gkg618","pdf_url":null,"source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:12824371","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12824371","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:pubmedcentral.nih.gov:169024","is_oa":true,"landing_page_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:169024","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/169024","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nucleic Acids Res","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:169024","is_oa":true,"landing_page_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1836573911","display_name":"ITR: Discovering Regulatory Elements in Biological Sequences","funder_award_id":"0218798","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1956090332","https://openalex.org/W1998300401","https://openalex.org/W2003967338","https://openalex.org/W2039286232","https://openalex.org/W2056002855","https://openalex.org/W2084908610","https://openalex.org/W2102787800","https://openalex.org/W2120842435","https://openalex.org/W2151234222"],"related_works":["https://openalex.org/W2036927633","https://openalex.org/W2152664145","https://openalex.org/W2153561273","https://openalex.org/W2079197459","https://openalex.org/W2379997263","https://openalex.org/W2165899269","https://openalex.org/W2236968607","https://openalex.org/W2131580913","https://openalex.org/W2009673058","https://openalex.org/W2039285586"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"challenge":[2],"facing":[3],"biologists":[4],"is":[5,51],"to":[6,21,53],"identify":[7],"DNA":[8],"binding":[9,32],"sites":[10,33],"for":[11,30,36],"unknown":[12],"regulatory":[13],"factors,":[14],"given":[15],"a":[16],"collection":[17],"of":[18],"genes":[19],"believed":[20],"be":[22],"coregulated.":[23],"The":[24],"program":[25],"YMF":[26,42,64],"identifies":[27],"good":[28],"candidates":[29],"such":[31],"by":[34],"searching":[35],"statistically":[37],"overrepresented":[38],"motifs.":[39],"More":[40],"specifically,":[41],"enumerates":[43],"all":[44],"motifs":[45,56],"in":[46],"the":[47,63],"search":[48],"space":[49],"and":[50],"guaranteed":[52],"produce":[54],"those":[55],"with":[57],"greatest":[58],"z-scores.":[59],"This":[60],"note":[61],"describes":[62],"web":[65],"software,":[66],"available":[67],"at":[68],"http://bio.cs.washington.edu/software.html.":[69]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
