{"id":"https://openalex.org/W2091869971","doi":"https://doi.org/10.1142/s0219720009003935","title":"COUNTING OF OLIGOMERS IN SEQUENCES GENERATED BY MARKOV CHAINS FOR DNA MOTIF DISCOVERY","display_name":"COUNTING OF OLIGOMERS IN SEQUENCES GENERATED BY MARKOV CHAINS FOR DNA MOTIF DISCOVERY","publication_year":2009,"publication_date":"2009-02-01","ids":{"openalex":"https://openalex.org/W2091869971","doi":"https://doi.org/10.1142/s0219720009003935","mag":"2091869971","pmid":"https://pubmed.ncbi.nlm.nih.gov/19226659"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720009003935","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720009003935","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113651192","display_name":"Gao Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"GAO SHAN","raw_affiliation_strings":["Beijing Genomics Institute, Shenzhen (BGI-SZ), Shenzhen 518083, China","Zhejiang University, Hangzhou 310008, China"],"affiliations":[{"raw_affiliation_string":"Beijing Genomics Institute, Shenzhen (BGI-SZ), Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou 310008, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021041719","display_name":"Wei\u2010Mou Zheng","orcid":"https://orcid.org/0000-0001-6546-2917"},"institutions":[{"id":"https://openalex.org/I4210125404","display_name":"Institute of Theoretical Physics","ror":"https://ror.org/02xtbq882","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210125404"]},{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WEI-MOU ZHENG","raw_affiliation_strings":["Beijing Genomics Institute, Shenzhen (BGI-SZ), Shenzhen 518083, China","Institute of Theoretical Physics, Academia Sinica, Beijing 100190, China"],"affiliations":[{"raw_affiliation_string":"Beijing Genomics Institute, Shenzhen (BGI-SZ), Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]},{"raw_affiliation_string":"Institute of Theoretical Physics, Academia Sinica, Beijing 100190, China","institution_ids":["https://openalex.org/I4210125404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113651192"],"corresponding_institution_ids":["https://openalex.org/I100135526","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.3086,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84259458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"07","issue":"01","first_page":"39","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9979000091552734,"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":0.9973000288009644,"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/markov-chain","display_name":"Markov chain","score":0.8350932598114014},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.5314326286315918},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49152621626853943},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4699098467826843},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46535760164260864},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45779070258140564},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.44380900263786316},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42540639638900757},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42195698618888855},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4168926179409027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38441261649131775},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.36057811975479126},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3427410125732422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23454496264457703},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22891482710838318},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.198928564786911},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1304919421672821},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1257060468196869}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.8350932598114014},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5314326286315918},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49152621626853943},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4699098467826843},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46535760164260864},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45779070258140564},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.44380900263786316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42540639638900757},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42195698618888855},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4168926179409027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38441261649131775},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.36057811975479126},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3427410125732422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23454496264457703},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22891482710838318},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.198928564786911},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1304919421672821},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1257060468196869},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":"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":"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":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D016384","descriptor_name":"Consensus Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016384","descriptor_name":"Consensus Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016384","descriptor_name":"Consensus Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","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":2,"locations":[{"id":"doi:10.1142/s0219720009003935","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720009003935","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:19226659","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19226659","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":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1917767512","https://openalex.org/W1975924111","https://openalex.org/W1998300401","https://openalex.org/W2018983027","https://openalex.org/W2032231928","https://openalex.org/W2039286232","https://openalex.org/W2045894772","https://openalex.org/W2053392780","https://openalex.org/W2120344408","https://openalex.org/W2148315211","https://openalex.org/W2911361414"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":{"By":[0],"means":[1],"of":[2,5,21,68,79,85,91,96],"the":[3,6,25,50,59,66,73,76],"technique":[4],"imbedded":[7,51],"Markov":[8,41,52],"chain,":[9],"an":[10],"efficient":[11],"algorithm":[12],"is":[13,46,106],"proposed":[14],"to":[15,30,54],"exactly":[16],"calculate":[17],"first,":[18],"second":[19],"moments":[20],"word":[22,29,80],"counts":[23],"and":[24,72],"probability":[26],"for":[27,58,89],"a":[28,40,83,94],"occur":[31],"at":[32,108],"least":[33],"once":[34],"in":[35,82],"random":[36],"texts":[37],"generated":[38],"by":[39],"chain.":[42],"A":[43],"generating":[44],"function":[45],"introduced":[47],"directly":[48],"from":[49,100],"chain":[53],"derive":[55],"asymptotic":[56],"approximations":[57],"problem.":[60],"Two":[61],"Z-scores,":[62],"one":[63],"based":[64],"on":[65,75,93],"number":[67,78],"sequences":[69,98],"with":[70],"hits":[71,81],"other":[74],"total":[77],"set":[84,95],"sequences,":[86],"are":[87],"examined":[88],"discovery":[90],"motifs":[92],"promoter":[97],"extracted":[99],"A.":[101],"thaliana":[102],"genome.":[103],"Source":[104],"code":[105],"available":[107],"http://www.itp.ac.cn/zheng/oligo.c.":[109]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}