{"id":"https://openalex.org/W2123223165","doi":"https://doi.org/10.1093/bioinformatics/btm610","title":"Natural similarity measures between position frequency matrices with an application to clustering","display_name":"Natural similarity measures between position frequency matrices with an application to clustering","publication_year":2008,"publication_date":"2008-01-02","ids":{"openalex":"https://openalex.org/W2123223165","doi":"https://doi.org/10.1093/bioinformatics/btm610","mag":"2123223165","pmid":"https://pubmed.ncbi.nlm.nih.gov/18174183"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btm610","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm610","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/3/350/50567983/bioinformatics_24_3_350.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/3/350/50567983/bioinformatics_24_3_350.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084657632","display_name":"Utz Johann Pape","orcid":"https://orcid.org/0000-0002-1802-6810"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Utz J. Pape","raw_affiliation_strings":["1 Computational Biology, Max Planck Institute f. Molecular Genetics, Ihnestr. 73, 14195 Berlin, 2Mathematics and Computer Science, Free University of Berlin, Takustr. 9, 14195 Berlin, 3COMET group, Genome Informatics, Universit\u00e4t Bielefeld, 33594 Bielefeld and 4Bioinformatics for High-Throughput Technologies, Computer Science 11, Dortmund University, 44221 Dortmund, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Computational Biology, Max Planck Institute f. Molecular Genetics, Ihnestr. 73, 14195 Berlin, 2Mathematics and Computer Science, Free University of Berlin, Takustr. 9, 14195 Berlin, 3COMET group, Genome Informatics, Universit\u00e4t Bielefeld, 33594 Bielefeld and 4Bioinformatics for High-Throughput Technologies, Computer Science 11, Dortmund University, 44221 Dortmund, Germany","institution_ids":["https://openalex.org/I20121455","https://openalex.org/I75951250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059606670","display_name":"Sven Rahmann","orcid":"https://orcid.org/0000-0002-8536-6065"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Rahmann","raw_affiliation_strings":["1 Computational Biology, Max Planck Institute f. Molecular Genetics, Ihnestr. 73, 14195 Berlin, 2Mathematics and Computer Science, Free University of Berlin, Takustr. 9, 14195 Berlin, 3COMET group, Genome Informatics, Universit\u00e4t Bielefeld, 33594 Bielefeld and 4Bioinformatics for High-Throughput Technologies, Computer Science 11, Dortmund University, 44221 Dortmund, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Computational Biology, Max Planck Institute f. Molecular Genetics, Ihnestr. 73, 14195 Berlin, 2Mathematics and Computer Science, Free University of Berlin, Takustr. 9, 14195 Berlin, 3COMET group, Genome Informatics, Universit\u00e4t Bielefeld, 33594 Bielefeld and 4Bioinformatics for High-Throughput Technologies, Computer Science 11, Dortmund University, 44221 Dortmund, Germany","institution_ids":["https://openalex.org/I20121455","https://openalex.org/I75951250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009628707","display_name":"Martin Vingron","orcid":"https://orcid.org/0000-0002-1765-4241"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Vingron","raw_affiliation_strings":["1 Computational Biology, Max Planck Institute f. Molecular Genetics, Ihnestr. 73, 14195 Berlin, 2Mathematics and Computer Science, Free University of Berlin, Takustr. 9, 14195 Berlin, 3COMET group, Genome Informatics, Universit\u00e4t Bielefeld, 33594 Bielefeld and 4Bioinformatics for High-Throughput Technologies, Computer Science 11, Dortmund University, 44221 Dortmund, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Computational Biology, Max Planck Institute f. Molecular Genetics, Ihnestr. 73, 14195 Berlin, 2Mathematics and Computer Science, Free University of Berlin, Takustr. 9, 14195 Berlin, 3COMET group, Genome Informatics, Universit\u00e4t Bielefeld, 33594 Bielefeld and 4Bioinformatics for High-Throughput Technologies, Computer Science 11, Dortmund University, 44221 Dortmund, Germany","institution_ids":["https://openalex.org/I20121455","https://openalex.org/I75951250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084657632"],"corresponding_institution_ids":["https://openalex.org/I20121455","https://openalex.org/I75951250"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":2.3894,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.88869631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"24","issue":"3","first_page":"350","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.8932999968528748,"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":0.8932999968528748,"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":0.03720000013709068,"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":0.019999999552965164,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7626067399978638},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6621023416519165},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5980818271636963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5373455882072449},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.45368871092796326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4105425477027893},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40980055928230286},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3889049291610718},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1485421359539032},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06665852665901184}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7626067399978638},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6621023416519165},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5980818271636963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5373455882072449},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.45368871092796326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4105425477027893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40980055928230286},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3889049291610718},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1485421359539032},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06665852665901184},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","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":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btm610","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm610","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/3/350/50567983/bioinformatics_24_3_350.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18174183","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18174183","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"},{"id":"pmh:oai:pure.mpg.de:item_1584650","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-80A3-C","pdf_url":"https://hdl.handle.net/11858/00-001M-0000-0010-80A2-E","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:edoc.mpg.de:404466","is_oa":true,"landing_page_url":"http://edoc.mpg.de/404466","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, v.24, 350-357 (2008)","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btm610","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm610","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/3/350/50567983/bioinformatics_24_3_350.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123223165.pdf","grobid_xml":"https://content.openalex.org/works/W2123223165.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1498410508","https://openalex.org/W1531954825","https://openalex.org/W1548872348","https://openalex.org/W1590648220","https://openalex.org/W1600463518","https://openalex.org/W1853093403","https://openalex.org/W1975924111","https://openalex.org/W1986841498","https://openalex.org/W1987122345","https://openalex.org/W1999755087","https://openalex.org/W2027662098","https://openalex.org/W2035564383","https://openalex.org/W2053392780","https://openalex.org/W2057000344","https://openalex.org/W2065635150","https://openalex.org/W2071037669","https://openalex.org/W2074703985","https://openalex.org/W2077013196","https://openalex.org/W2081891527","https://openalex.org/W2103325210","https://openalex.org/W2103777723","https://openalex.org/W2109383935","https://openalex.org/W2110455321","https://openalex.org/W2111473801","https://openalex.org/W2116405705","https://openalex.org/W2116672274","https://openalex.org/W2120900302","https://openalex.org/W2123838014","https://openalex.org/W2135221645","https://openalex.org/W2137428312","https://openalex.org/W2141408320","https://openalex.org/W2148315211","https://openalex.org/W2149769193","https://openalex.org/W2150290224","https://openalex.org/W2158266834","https://openalex.org/W2162829784","https://openalex.org/W2166898290","https://openalex.org/W2167826943","https://openalex.org/W2169016544","https://openalex.org/W2317912355","https://openalex.org/W2797506774","https://openalex.org/W2954108003","https://openalex.org/W4248160505","https://openalex.org/W4249255000","https://openalex.org/W6632990887","https://openalex.org/W6669828346","https://openalex.org/W6676479977","https://openalex.org/W6680709261","https://openalex.org/W6684528287","https://openalex.org/W6684577476"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W2090259340","https://openalex.org/W4310225030","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W1534720161","https://openalex.org/W1926736923","https://openalex.org/W2804957450"],"abstract_inverted_index":{"MOTIVATION:":[0],"Transcription":[1],"factors":[2],"(TFs)":[3],"play":[4],"a":[5,23,26,30,45,77,96,117,127,145,181],"key":[6],"role":[7],"in":[8,33],"gene":[9],"regulation":[10],"by":[11,44,144],"binding":[12,21,27,37],"to":[13,25,58,61,87,125,191,206,211],"target":[14],"sequences.":[15],"In":[16,64,189],"silico":[17],"prediction":[18],"of":[19,22,52,90,108,129,149,174,176],"potential":[20],"TF":[24,41],"site":[28],"is":[29,184],"well-studied":[31],"problem":[32],"computational":[34],"biology.":[35],"The":[36,50,153,168],"sites":[38],"for":[39,186],"one":[40],"are":[42,68,220],"represented":[43],"position":[46],"frequency":[47],"matrix":[48],"(PFM).":[49],"discovery":[51],"new":[53],"PFMs":[54,60,67,196],"requires":[55],"the":[56,91,102,106,122,130,137,150,177,208,214],"comparison":[57],"known":[59],"avoid":[62],"redundancies.":[63],"general,":[65],"two":[66,146],"similar":[69],"if":[70],"they":[71],"occur":[72],"at":[73,222],"overlapping":[74],"positions":[75],"under":[76],"null":[78],"model.":[79],"Still,":[80],"most":[81,192],"existing":[82],"methods":[83],"compute":[84,207],"similarity":[85,98,199,209],"according":[86],"probabilistic":[88],"distances":[89],"PFMs.":[92,132],"Here":[93],"we":[94,115],"propose":[95],"natural":[97],"measure":[99,119],"based":[100,120],"on":[101,121],"asymptotic":[103,138,154],"covariance":[104,139,155],"between":[105],"number":[107],"PFM":[109,183],"hits":[110],"incorporating":[111],"both":[112],"strands.":[113],"Furthermore,":[114,180],"introduce":[116],"second":[118],"same":[123,178],"idea":[124],"cluster":[126],"set":[128],"Jaspar":[131,169],"RESULTS:":[133],"We":[134],"show":[135],"that":[136],"can":[140],"be":[141],"efficiently":[142],"computed":[143],"dimensional":[147],"convolution":[148],"score":[151],"distributions.":[152],"approach":[156],"shows":[157],"strong":[158],"correlation":[159],"with":[160,197],"simulated":[161],"data.":[162],"It":[163],"outperforms":[164],"three":[165],"alternative":[166],"methods.":[167],"clustering":[170,194],"yields":[171],"distinct":[172],"groups":[173],"TFs":[175],"class.":[179,188],"representative":[182],"given":[185],"each":[187],"contrast":[190],"other":[193],"methods,":[195],"low":[198],"automatically":[200],"remain":[201],"singletons.":[202],"AVAILABILITY:":[203],"A":[204],"website":[205],"and":[210,217],"perform":[212],"clustering,":[213],"source":[215],"code":[216],"Supplementary":[218],"Material":[219],"available":[221],"http://mosta.molgen.mpg.de.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-08-30T07:30:35.949966","created_date":"2025-10-10T00:00:00"}
