{"id":"https://openalex.org/W2123708619","doi":"https://doi.org/10.1186/1687-4153-2012-12","title":"Identification of CpG islands in DNA sequences using statistically optimal null filters","display_name":"Identification of CpG islands in DNA sequences using statistically optimal null filters","publication_year":2012,"publication_date":"2012-08-29","ids":{"openalex":"https://openalex.org/W2123708619","doi":"https://doi.org/10.1186/1687-4153-2012-12","mag":"2123708619","pmid":"https://pubmed.ncbi.nlm.nih.gov/22931396"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4153-2012-12","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4153-2012-12","pdf_url":"https://bsb-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4153-2012-12","source":{"id":"https://openalex.org/S22696228","display_name":"EURASIP Journal on Bioinformatics and Systems Biology","issn_l":"1687-4145","issn":["1687-4145","1687-4153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Bioinformatics and Systems Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://bsb-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4153-2012-12","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040990763","display_name":"Rajasekhar Kakumani","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Rajasekhar Kakumani","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd, West Montreal, QC H3G1M8, Canada. r_kakuma@encs.concordia.ca","Department of Electrical and Computer Engineering, Concordia University, West Montr\u00e9al, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd, West Montreal, QC H3G1M8, Canada. r_kakuma@encs.concordia.ca","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, West Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050675413","display_name":"Omair Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Omair Ahmad","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd., West Montreal, QC, H3G1M8, Canada","Department of Electrical and Computer Engineering, Concordia University, West Montr\u00e9al, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, 1455 de Maisonneuve Blvd., West Montreal, QC, H3G1M8, Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, West Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111712571","display_name":"Vijay Devabhaktuni","orcid":null},"institutions":[{"id":"https://openalex.org/I90871651","display_name":"University of Toledo","ror":"https://ror.org/01pbdzh19","country_code":"US","type":"education","lineage":["https://openalex.org/I90871651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Devabhaktuni","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Toledo, MS 308, 2801 W. Bancroft St., Toledo, OH, 43606, USA","Department of Electrical Engineering and Computer Sci., University of Toledo, Toledo, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Toledo, MS 308, 2801 W. Bancroft St., Toledo, OH, 43606, USA","institution_ids":["https://openalex.org/I90871651"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sci., University of Toledo, Toledo, USA","institution_ids":["https://openalex.org/I90871651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040990763"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":0.5297,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.65862862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2012","issue":"1","first_page":"12","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9995999932289124,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/cpg-site","display_name":"CpG site","score":0.7005136013031006},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5439127087593079},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5253490805625916},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4556456506252289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45259666442871094},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4447345733642578},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4426061511039734},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.4251609444618225},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.399235337972641},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36854174733161926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3507142961025238},{"id":"https://openalex.org/keywords/dna-methylation","display_name":"DNA methylation","score":0.22391074895858765},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.13619673252105713}],"concepts":[{"id":"https://openalex.org/C140173407","wikidata":"https://www.wikidata.org/wiki/Q1138358","display_name":"CpG site","level":5,"score":0.7005136013031006},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5439127087593079},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5253490805625916},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4556456506252289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45259666442871094},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4447345733642578},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4426061511039734},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.4251609444618225},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.399235337972641},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36854174733161926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3507142961025238},{"id":"https://openalex.org/C190727270","wikidata":"https://www.wikidata.org/wiki/Q874745","display_name":"DNA methylation","level":4,"score":0.22391074895858765},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.13619673252105713},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1687-4153-2012-12","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4153-2012-12","pdf_url":"https://bsb-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4153-2012-12","source":{"id":"https://openalex.org/S22696228","display_name":"EURASIP Journal on Bioinformatics and Systems Biology","issn_l":"1687-4145","issn":["1687-4145","1687-4153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Bioinformatics and Systems Biology","raw_type":"journal-article"},{"id":"pmid:22931396","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22931396","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":"EURASIP journal on bioinformatics & systems biology","raw_type":null},{"id":"pmh:oai:europepmc.org:2572691","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3570435","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":"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"}],"best_oa_location":{"id":"doi:10.1186/1687-4153-2012-12","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4153-2012-12","pdf_url":"https://bsb-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4153-2012-12","source":{"id":"https://openalex.org/S22696228","display_name":"EURASIP Journal on Bioinformatics and Systems Biology","issn_l":"1687-4145","issn":["1687-4145","1687-4153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Bioinformatics and Systems Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life below water","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123708619.pdf","grobid_xml":"https://content.openalex.org/works/W2123708619.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W258794974","https://openalex.org/W659226229","https://openalex.org/W1479007048","https://openalex.org/W1491459594","https://openalex.org/W1531710418","https://openalex.org/W1579447084","https://openalex.org/W1603934303","https://openalex.org/W1966833356","https://openalex.org/W1984222728","https://openalex.org/W1984680322","https://openalex.org/W1996423252","https://openalex.org/W1999510229","https://openalex.org/W2002497918","https://openalex.org/W2011480164","https://openalex.org/W2018442053","https://openalex.org/W2024213282","https://openalex.org/W2037330912","https://openalex.org/W2040149948","https://openalex.org/W2040257851","https://openalex.org/W2042029290","https://openalex.org/W2050249780","https://openalex.org/W2066955844","https://openalex.org/W2073996456","https://openalex.org/W2075432652","https://openalex.org/W2076620045","https://openalex.org/W2084748297","https://openalex.org/W2087440101","https://openalex.org/W2101159760","https://openalex.org/W2115992869","https://openalex.org/W2121417064","https://openalex.org/W2125838338","https://openalex.org/W2128077864","https://openalex.org/W2133366642","https://openalex.org/W2133643592","https://openalex.org/W2136707328","https://openalex.org/W2137505881","https://openalex.org/W2141207260","https://openalex.org/W2141474097","https://openalex.org/W2143766664","https://openalex.org/W2145541031","https://openalex.org/W2153432157","https://openalex.org/W2161399316","https://openalex.org/W2543210503","https://openalex.org/W3045278540","https://openalex.org/W3142340468","https://openalex.org/W3146116728","https://openalex.org/W3214380909","https://openalex.org/W4245668478"],"related_works":["https://openalex.org/W2951287487","https://openalex.org/W1570309050","https://openalex.org/W1531710418","https://openalex.org/W1994829526","https://openalex.org/W2219563043","https://openalex.org/W2189061370","https://openalex.org/W1972740636","https://openalex.org/W2212197444","https://openalex.org/W2097100439","https://openalex.org/W2389183782"],"abstract_inverted_index":{":":[0],"CpG":[1,8,54],"dinucleotide":[2,55],"clusters":[3],"also":[4],"referred":[5],"to":[6,63,87,109,138,167,196,226],"as":[7,37,43,59,85,230,232],"islands":[9],"(CGIs)":[10],"are":[11,40],"usually":[12],"located":[13],"in":[14,20,31,57,80,103,133,173,202,234],"the":[15,52,65,72,95,101,122,134,198,203,236],"promoter":[16],"regions":[17],"of":[18,67,74,94,128,153,181,214],"genes":[19],"a":[21,28,60,81,88,112,115,146,162,174,212],"deoxyribonucleic":[22],"acid":[23],"(DNA)":[24],"sequence.":[25,205],"CGIs":[26,154,172],"play":[27],"crucial":[29],"role":[30],"gene":[32,44],"expression":[33],"and":[34,126,148,169,191,222,224],"cell":[35],"differentiation,":[36],"such,":[38],"they":[39],"normally":[41],"used":[42,51],"markers.":[45],"The":[46,69,206],"earlier":[47],"CGI":[48,82,113,164,199],"identification":[49,152,165,200],"methods":[50,99],"rich":[53],"content":[56],"CGIs,":[58],"characteristic":[61,166,201],"measure":[62],"identify":[64,171],"locations":[66],"CGIs.":[68,237],"fact,":[70],"that":[71],"probability":[73],"nucleotide":[75,78],"G":[76],"following":[77],"C":[79],"is":[83,90,179,209],"greater":[84],"compared":[86],"non-CGI,":[89],"employed":[91],"by":[92],"some":[93],"recent":[96],"methods.":[97],"These":[98,117],"use":[100],"difference":[102],"transition":[104,118],"probabilities":[105,119],"between":[106,111],"subsequent":[107],"nucleotides":[108],"distinguish":[110],"from":[114,218],"non-CGI.":[116],"vary":[120],"with":[121],"data":[123],"being":[124],"analyzed":[125],"several":[127],"them":[129],"have":[130],"been":[131],"reported":[132],"literature":[135],"sometimes":[136],"leading":[137],"contradictory":[139],"results.":[140],"In":[141],"this":[142],"article,":[143],"we":[144],"propose":[145],"new":[147,163],"efficient":[149,233],"scheme":[150,186,208],"for":[151],"using":[155],"statistically":[156],"optimal":[157],"null":[158],"filters.":[159],"We":[160],"formulate":[161],"reliably":[168],"efficiently":[170],"given":[175],"DNA":[176,204,215],"sequence":[177],"which":[178],"devoid":[180],"any":[182],"ambiguities.":[183],"Our":[184],"proposed":[185,207],"combines":[187],"maximum":[188],"signal-to-noise":[189],"ratio":[190],"least":[192],"squares":[193],"optimization":[194],"criteria":[195],"estimate":[197],"tested":[210],"on":[211],"number":[213],"sequences":[216],"taken":[217],"human":[219],"chromosomes":[220],"21":[221],"22,":[223],"proved":[225],"be":[227],"highly":[228],"reliable":[229],"well":[231],"identifying":[235]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}