{"id":"https://openalex.org/W2124225056","doi":"https://doi.org/10.1093/bioinformatics/bts009","title":"An effective statistical evaluation of ChIPseq dataset similarity","display_name":"An effective statistical evaluation of ChIPseq dataset similarity","publication_year":2012,"publication_date":"2012-01-19","ids":{"openalex":"https://openalex.org/W2124225056","doi":"https://doi.org/10.1093/bioinformatics/bts009","mag":"2124225056","pmid":"https://pubmed.ncbi.nlm.nih.gov/22262674"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bts009","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts009","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/5/607/48880273/bioinformatics_28_5_607.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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/28/5/607/48880273/bioinformatics_28_5_607.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034705320","display_name":"Maria Chikina","orcid":"https://orcid.org/0000-0003-2550-5403"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maria D. Chikina","raw_affiliation_strings":["1 Department of Neurology, Mount Sinai School of Medicine, New York, NY 10029 and 2Lewis-Sigler Institute for Integrative Genomics, Department of Computer Science and Molecular Biology, Princeton University, Princeton, NJ 08540, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Neurology, Mount Sinai School of Medicine, New York, NY 10029 and 2Lewis-Sigler Institute for Integrative Genomics, Department of Computer Science and Molecular Biology, Princeton University, Princeton, NJ 08540, USA","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I98704320"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025250742","display_name":"Olga G. Troyanskaya","orcid":"https://orcid.org/0000-0002-5676-5737"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Olga G. Troyanskaya","raw_affiliation_strings":["1 Department of Neurology, Mount Sinai School of Medicine, New York, NY 10029 and 2Lewis-Sigler Institute for Integrative Genomics, Department of Computer Science and Molecular Biology, Princeton University, Princeton, NJ 08540, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Neurology, Mount Sinai School of Medicine, New York, NY 10029 and 2Lewis-Sigler Institute for Integrative Genomics, Department of Computer Science and Molecular Biology, Princeton University, Princeton, NJ 08540, USA","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I98704320"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025250742"],"corresponding_institution_ids":["https://openalex.org/I20089843","https://openalex.org/I98704320"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.9646,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.86369784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"28","issue":"5","first_page":"607","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9398000240325928,"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":0.9398000240325928,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.014000000432133675,"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":0.011300000362098217,"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":0.6584550142288208},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5402900576591492},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4928007423877716},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4924229383468628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48594772815704346},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4621710181236267},{"id":"https://openalex.org/keywords/chromatin","display_name":"Chromatin","score":0.41198620200157166},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.2092229425907135},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.18079790472984314}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6584550142288208},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5402900576591492},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4928007423877716},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4924229383468628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48594772815704346},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4621710181236267},{"id":"https://openalex.org/C83640560","wikidata":"https://www.wikidata.org/wiki/Q180951","display_name":"Chromatin","level":3,"score":0.41198620200157166},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2092229425907135},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.18079790472984314},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D047369","descriptor_name":"Chromatin Immunoprecipitation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D047369","descriptor_name":"Chromatin Immunoprecipitation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D047369","descriptor_name":"Chromatin Immunoprecipitation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/bts009","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts009","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/5/607/48880273/bioinformatics_28_5_607.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22262674","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22262674","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":null},{"id":"pmh:oai:europepmc.org:2583202","is_oa":false,"landing_page_url":"http://europepmc.org/articles/PMC3339511","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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3339511","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3339511","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bts009","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts009","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/5/607/48880273/bioinformatics_28_5_607.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G105050592","display_name":null,"funder_award_id":"P50 GM-071508","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G1716682633","display_name":null,"funder_award_id":"R01 GM-071966","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3218012782","display_name":null,"funder_award_id":"T32HG003284","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G991359604","display_name":null,"funder_award_id":"R01 HG005998","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1968475238","https://openalex.org/W1971324809","https://openalex.org/W1974891525","https://openalex.org/W1988294855","https://openalex.org/W1989373989","https://openalex.org/W1994115491","https://openalex.org/W1999746344","https://openalex.org/W2010031978","https://openalex.org/W2015396326","https://openalex.org/W2017840637","https://openalex.org/W2024409799","https://openalex.org/W2038697069","https://openalex.org/W2052444795","https://openalex.org/W2058414986","https://openalex.org/W2066349225","https://openalex.org/W2083080708","https://openalex.org/W2105924780","https://openalex.org/W2117623697","https://openalex.org/W2119805681","https://openalex.org/W2124586487","https://openalex.org/W2127851640","https://openalex.org/W2128612482","https://openalex.org/W2129795133","https://openalex.org/W2134128560","https://openalex.org/W2135478764","https://openalex.org/W2140236326","https://openalex.org/W2171111703"],"related_works":["https://openalex.org/W2152861454","https://openalex.org/W3004891660","https://openalex.org/W4286930115","https://openalex.org/W1842891956","https://openalex.org/W4206381471","https://openalex.org/W2414971881","https://openalex.org/W1598419885","https://openalex.org/W1886874180","https://openalex.org/W4225831698","https://openalex.org/W1607718650"],"abstract_inverted_index":{"MOTIVATION:":[0],"ChIPseq":[1,53,67,108,182],"is":[2,42,102,121,210],"rapidly":[3],"becoming":[4],"a":[5,18,47,144],"common":[6],"technique":[7],"for":[8,117,212],"investigating":[9],"protein-DNA":[10],"interactions.":[11],"However,":[12],"results":[13],"from":[14],"individual":[15],"experiments":[16],"provide":[17],"limited":[19],"understanding":[20],"of":[21,66,73,114,147,164],"chromatin":[22,26],"structure,":[23],"as":[24,129,151,199],"various":[25],"factors":[27,202],"cooperate":[28],"in":[29,103,126,184],"complex":[30],"ways":[31],"to":[32,37,45,52,61,91,106,123,160,191],"orchestrate":[33],"transcription.":[34],"In":[35],"order":[36],"quantify":[38],"chromtain":[39],"interactions,":[40],"it":[41,101],"thus":[43],"necessary":[44],"devise":[46],"robust":[48],"similarity":[49,141],"metric":[50],"applicable":[51],"data.":[54],"Unfortunately,":[55],"moving":[56],"past":[57],"simple":[58],"overlap":[59],"calculations":[60],"give":[62],"statistically":[63],"rigorous":[64],"comparisons":[65],"datasets":[68,109,127],"often":[69],"involves":[70],"arbitrary":[71],"choices":[72],"distance":[74],"metrics,":[75],"with":[76,176],"significance":[77],"being":[78],"estimated":[79],"by":[80,139],"computationally":[81],"intensive":[82],"permutation":[83],"tests":[84],"whose":[85],"statistical":[86],"power":[87],"may":[88],"be":[89],"sensitive":[90],"non-biological":[92,124],"experimental":[93],"and":[94,132,201],"post-processing":[95],"variation.":[96],"RESULTS:":[97],"We":[98],"show":[99],"that":[100,203],"fact":[104],"possible":[105],"compare":[107],"through":[110],"the":[111,161],"efficient":[112],"computation":[113],"exact":[115],"P-values":[116],"proximity.":[118],"Our":[119],"method":[120,159],"insensitive":[122],"variation":[125],"such":[128,198],"peak":[130,136],"width,":[131],"can":[133],"rigorously":[134],"model":[135],"location":[137],"biases":[138],"evaluating":[140],"conditioned":[142],"on":[143],"restricted":[145],"set":[146],"genomic":[148],"regions":[149],"(such":[150],"mappable":[152],"genome":[153],"or":[154],"promoter":[155],"regions).":[156],"Applying":[157],"our":[158,177],"well-studied":[162],"dataset":[163],"Chen":[165],"et":[166],"al.":[167],"(2008),":[168],"we":[169,188],"elucidate":[170],"novel":[171],"interactions":[172],"which":[173],"conform":[174],"well":[175],"biological":[178],"understanding.":[179],"By":[180],"comparing":[181],"data":[183,219],"an":[185],"asymmetric":[186],"way,":[187],"are":[189,220],"able":[190],"observe":[192],"clear":[193],"interaction":[194],"differences":[195],"between":[196],"cofactors":[197],"p300":[200],"bind":[204],"DNA":[205],"directly.":[206],"AVAILABILITY:":[207],"Source":[208],"code":[209],"available":[211,221],"download":[213],"at":[214,222],"http://sonorus.princeton.edu/IntervalStats/IntervalStats.tar.gz.":[215],"SUPPLEMENTARY":[216],"INFORMATION:":[217],"Supplementary":[218],"Bioinformatics":[223],"online.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2016-06-24T00:00:00"}