{"id":"https://openalex.org/W4382490834","doi":"https://doi.org/10.48550/arxiv.2306.15032","title":"DMseg: a Python algorithm for de novo detection of differentially or variably methylated regions","display_name":"DMseg: a Python algorithm for de novo detection of differentially or variably methylated regions","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382490834","doi":"https://doi.org/10.48550/arxiv.2306.15032"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.15032","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.15032","pdf_url":"https://arxiv.org/pdf/2306.15032","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.15032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100357599","display_name":"Xiaoyu Wang","orcid":"https://orcid.org/0000-0002-4504-7799","observed_orcids":["https://orcid.org/0000-0002-4504-7799"]},"institutions":[{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Xiaoyu","raw_affiliation_strings":["Fred Hutchinson Cancer Center , Public Health Sciences Division , Seattle , 98109 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fred Hutchinson Cancer Center , Public Health Sciences Division , Seattle , 98109 , USA","institution_ids":["https://openalex.org/I4210089486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031067040","display_name":"Ming Yu","orcid":"https://orcid.org/0000-0001-8692-6135","observed_orcids":["https://orcid.org/0000-0001-8692-6135"]},"institutions":[{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu, Ming","raw_affiliation_strings":["Fred Hutchinson Cancer Center , Clinical Research Division , Seattle , 98109 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fred Hutchinson Cancer Center , Clinical Research Division , Seattle , 98109 , USA","institution_ids":["https://openalex.org/I4210089486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068477057","display_name":"William M. Grady","orcid":"https://orcid.org/0000-0002-0129-7809","observed_orcids":["https://orcid.org/0000-0002-0129-7809"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grady, William","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058030955","display_name":"Ziding Feng","orcid":"https://orcid.org/0000-0003-3051-8882","observed_orcids":["https://orcid.org/0000-0003-3051-8882"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng, Ziding","raw_affiliation_strings":["Fred Hutchinson Cancer Center , Public Health Sciences Division , Seattle , 98109 , USA","University of Washington , Department of Biostatistics , School of Public Health , Seattle , 98195 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fred Hutchinson Cancer Center , Public Health Sciences Division , Seattle , 98109 , USA","institution_ids":["https://openalex.org/I4210089486"]},{"raw_affiliation_string":"University of Washington , Department of Biostatistics , School of Public Health , Seattle , 98195 , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086153438","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0002-6350-1107","observed_orcids":["https://orcid.org/0000-0002-6350-1107"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032281064","display_name":"James Y. Dai","orcid":"https://orcid.org/0000-0001-6479-9286","observed_orcids":["https://orcid.org/0000-0001-6479-9286"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dai, James Y","raw_affiliation_strings":["Fred Hutchinson Cancer Center , Public Health Sciences Division , Seattle , 98109 , USA","University of Washington , Department of Biostatistics , School of Public Health , Seattle , 98195 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fred Hutchinson Cancer Center , Public Health Sciences Division , Seattle , 98109 , USA","institution_ids":["https://openalex.org/I4210089486"]},{"raw_affiliation_string":"University of Washington , Department of Biostatistics , School of Public Health , Seattle , 98195 , USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9901999831199646,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9901999831199646,"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":0.003100000089034438,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.0005000000237487257,"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/differentially-methylated-regions","display_name":"differentially methylated regions","score":0.9869999885559082},{"id":"https://openalex.org/keywords/dna-methylation","display_name":"DNA methylation","score":0.9639999866485596},{"id":"https://openalex.org/keywords/type-i-error-control","display_name":"type I error control","score":0.7110000252723694},{"id":"https://openalex.org/keywords/levene-test","display_name":"Levene test","score":0.8410000205039978},{"id":"https://openalex.org/keywords/likelihood-ratio-test","display_name":"likelihood ratio test","score":0.8709999918937683},{"id":"https://openalex.org/keywords/barrett-s-esophagus","display_name":"Barrett's esophagus","score":0.9940000176429749},{"id":"https://openalex.org/keywords/esophageal-adenocarcinoma","display_name":"esophageal adenocarcinoma","score":1.0}],"concepts":[{"id":"https://openalex.org/C140173407","wikidata":"https://www.wikidata.org/wiki/Q1138358","display_name":"CpG site","level":5,"score":0.5616368055343628},{"id":"https://openalex.org/C190727270","wikidata":"https://www.wikidata.org/wiki/Q874745","display_name":"DNA methylation","level":4,"score":0.5504792332649231},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5171841382980347},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5141956806182861},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.5127216577529907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49949193000793457},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.494643896818161},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.4303879141807556},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.41250079870224},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3620620667934418},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2753742039203644},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.25168561935424805},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2386467158794403},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1128683090209961},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.15032","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.15032","pdf_url":"https://arxiv.org/pdf/2306.15032","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.15032","doi":"https://doi.org/10.48550/arxiv.2306.15032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.15032","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.15032","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.15032","pdf_url":"https://arxiv.org/pdf/2306.15032","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382490834.pdf","grobid_xml":"https://content.openalex.org/works/W4382490834.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161942452","https://openalex.org/W2186978757","https://openalex.org/W7167345015","https://openalex.org/W2891923099","https://openalex.org/W2093642692","https://openalex.org/W3134842602","https://openalex.org/W2134266353","https://openalex.org/W7126296084","https://openalex.org/W2768241952","https://openalex.org/W2949570635"],"abstract_inverted_index":{"Detecting":[0],"and":[1,59,95,102,130,181,223,231],"assessing":[2,144],"statistical":[3,49],"significance":[4,50,96],"of":[5,51,147,173,185,192,198,220,229,233],"differentially":[6],"methylated":[7,45],"regions":[8,36,46],"(DMRs)":[9],"is":[10,55,154],"a":[11,56,88,108,137,159,165,177,227],"fundamental":[12],"task":[13],"in":[14,23,34,136,164],"methylome":[15,100,218],"association":[16],"studies.":[17],"While":[18],"the":[19,29,171,199],"average":[20],"differential":[21,41,53,145],"methylation":[22,32,54],"different":[24],"phenotype":[25],"groups":[26],"has":[27,78],"been":[28,79],"inferential":[30],"focus,":[31],"changes":[33],"chromosomal":[35],"may":[37],"also":[38],"present":[39],"as":[40],"variability,":[42],"i.e.,":[43],"variably":[44],"(VMRs).":[47],"Testing":[48],"regional":[52,174],"challenging":[57],"problem,":[58],"existing":[60,110],"algorithms":[61],"do":[62],"not":[63],"provide":[64],"accurate":[65,196],"type":[66,200],"I":[67,201],"error":[68,202],"control":[69,197],"for":[70,82,98,115,143,158],"genome-wide":[71],"DMR":[72,166],"or":[73,117,167],"VMR":[74,168],"analysis.":[75],"No":[76],"algorithm":[77,90],"publicly":[80],"available":[81],"detecting":[83],"VMRs.":[84],"We":[85],"propose":[86],"DMseg,":[87],"Python":[89],"with":[91,189],"efficient":[92],"DMR/VMR":[93],"detection":[94],"assessment":[97],"array-based":[99],"data,":[101],"compare":[103],"its":[104],"performance":[105],"to":[106,156,169,213,217],"Bumphunter,":[107],"popular":[109],"algorithm.":[111],"Operationally,":[112],"DMseg":[113,194,207],"searches":[114],"DMRs":[116,230],"VMRs":[118,232],"within":[119,162],"CpG":[120,134],"clusters":[121,188],"that":[122],"are":[123],"adaptively":[124],"determined":[125],"by":[126],"both":[127],"gap":[128],"distance":[129],"correlation":[131],"between":[132],"contiguous":[133],"sites":[135],"microarray.":[138],"Levene":[139],"test":[140,157],"was":[141],"implemented":[142],"variability":[146],"individual":[148],"CpGs.":[149],"A":[150],"likelihood":[151],"ratio":[152],"statistic":[153],"proposed":[155],"constant":[160],"difference":[161],"CpGs":[163],"summarize":[170],"evidence":[172],"difference.":[175],"Using":[176],"stratified":[178],"permutation":[179],"scheme":[180],"pooling":[182],"null":[183],"distributions":[184],"LRTs":[186],"from":[187],"similar":[190],"numbers":[191],"CpGs,":[193],"provides":[195],"rate.":[203],"In":[204],"simulation":[205],"experiments,":[206],"shows":[208],"superior":[209],"power":[210],"than":[211],"Bumphunter":[212],"detect":[214],"DMRs.":[215],"Application":[216],"data":[219],"Barrett's":[221],"esophagus":[222],"esophageal":[224],"adenocarcinoma":[225],"reveals":[226],"number":[228],"biological":[234],"interest.":[235]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2023-06-29T00:00:00"}