{"id":"https://openalex.org/W1910334622","doi":"https://doi.org/10.1186/1471-2105-6-219","title":"Generalizations of Markov model to characterize biological sequences","display_name":"Generalizations of Markov model to characterize biological sequences","publication_year":2005,"publication_date":"2005-09-06","ids":{"openalex":"https://openalex.org/W1910334622","doi":"https://doi.org/10.1186/1471-2105-6-219","mag":"1910334622","pmid":"https://pubmed.ncbi.nlm.nih.gov/16144548"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-6-219","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-219","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-219","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100704433","display_name":"Junwen Wang","orcid":"https://orcid.org/0000-0002-4432-4707"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junwen Wang","raw_affiliation_strings":["Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania, Philadelphia, PA 19104-6021, USA. junwen@pcbi.upenn.edu","Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania, Philadelphia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania, Philadelphia, PA 19104-6021, USA. junwen@pcbi.upenn.edu","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011962029","display_name":"Sridhar Hannenhalli","orcid":"https://orcid.org/0000-0001-9603-7569"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sridhar Hannenhalli","raw_affiliation_strings":["Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania Philadelphia, PA, 19104-6021, USA","Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania, Philadelphia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania Philadelphia, PA, 19104-6021, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Penn Center for Bioinformatics, Department of Genetics, University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011962029"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.8305,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.68619497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":"1","first_page":"219","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4124000072479248,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4124000072479248,"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":0.34470000863075256,"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":0.17630000412464142,"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/computational-biology","display_name":"Computational biology","score":0.6321655511856079},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5469650030136108},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.49669843912124634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4758203327655792},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4274104833602905},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.42316678166389465},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.33192986249923706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19894284009933472},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11565157771110535},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.08011171221733093}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6321655511856079},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5469650030136108},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.49669843912124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4758203327655792},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4274104833602905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.42316678166389465},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.33192986249923706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19894284009933472},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11565157771110535},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.08011171221733093}],"mesh":[{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","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":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005091","descriptor_name":"Exons","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005091","descriptor_name":"Exons","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005091","descriptor_name":"Exons","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"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":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009707","descriptor_name":"Nucleosomes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009707","descriptor_name":"Nucleosomes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009707","descriptor_name":"Nucleosomes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-6-219","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-219","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-219","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16144548","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16144548","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:d84cdae6d2d24538b6948e24fcafd787","is_oa":true,"landing_page_url":"https://doaj.org/article/d84cdae6d2d24538b6948e24fcafd787","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 6, Iss 1, p 219 (2005)","raw_type":"article"},{"id":"pmh:oai:hub.hku.hk:10722/147523","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/147523","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1236913","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1236913","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-6-219","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-219","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-219","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1910334622.pdf","grobid_xml":"https://content.openalex.org/works/W1910334622.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W201521870","https://openalex.org/W1554728849","https://openalex.org/W1606770439","https://openalex.org/W1964007348","https://openalex.org/W1972875048","https://openalex.org/W1999004357","https://openalex.org/W1999510229","https://openalex.org/W2011485152","https://openalex.org/W2014681911","https://openalex.org/W2022916085","https://openalex.org/W2029358314","https://openalex.org/W2032870665","https://openalex.org/W2040258702","https://openalex.org/W2049815058","https://openalex.org/W2056422388","https://openalex.org/W2062838869","https://openalex.org/W2074231493","https://openalex.org/W2084748297","https://openalex.org/W2089566942","https://openalex.org/W2114769465","https://openalex.org/W2122893035","https://openalex.org/W2129319388","https://openalex.org/W2130919037","https://openalex.org/W2136785696","https://openalex.org/W2143706916","https://openalex.org/W2146393977","https://openalex.org/W2166187656","https://openalex.org/W2166429927","https://openalex.org/W2337490104","https://openalex.org/W3214380909","https://openalex.org/W4245668478"],"related_works":["https://openalex.org/W2084326697","https://openalex.org/W2027903142","https://openalex.org/W2354322608","https://openalex.org/W2804608325","https://openalex.org/W2077211377","https://openalex.org/W2186675474","https://openalex.org/W2387462590","https://openalex.org/W2056274461","https://openalex.org/W2368739446","https://openalex.org/W2010321967"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,83,166,209],"currently":[2],"used":[3],"kth":[4],"order":[5],"Markov":[6,63,180,196,214],"models":[7],"estimate":[8],"the":[9,18,32,43,61,68,106,111,117,123,141,147,162,194,206,213,220],"probability":[10],"of":[11,35,60,80,90,125,137,143,151,186,212,223],"generating":[12],"a":[13,54,134,149],"single":[14,119],"nucleotide":[15,120],"conditional":[16],"upon":[17],"immediately":[19],"preceding":[20],"(gap":[21],"=":[22],"0)":[23],"k":[24],"units.":[25],"However,":[26],"this":[27],"neither":[28],"takes":[29],"into":[30],"account":[31],"joint":[33,200],"dependency":[34,46],"multiple":[36],"neighboring":[37],"nucleotides,":[38],"nor":[39],"does":[40],"it":[41],"consider":[42],"long":[44,202],"range":[45,203],"with":[47],"gap":[48,135],">":[49],"0.":[50],"RESULT:":[51],"We":[52,65,191],"describe":[53],"configurable":[55],"tool":[56,167],"to":[57,116,198,218],"explore":[58],"generalizations":[59,211],"standard":[62,118,195],"model.":[64,121],"evaluated":[66],"whether":[67],"sequence":[69,112,188,207,224],"classification":[70,113,144],"accuracy":[71,114,130,145,222],"can":[72],"be":[73],"improved":[74,110],"by":[75],"using":[76],"an":[77,183],"alternative":[78],"set":[79],"model":[81,107,197,215],"parameters.":[82],"evaluation":[84],"was":[85,131,154],"done":[86],"on":[87],"four":[88],"classes":[89],"biological":[91],"sequences--CpG-poor":[92],"promoters,":[93,95],"all":[94],"exons":[96],"and":[97,103,172,201],"nucleosome":[98,126,163],"positioning":[99,127,164],"sequences.":[100],"Using":[101],"di-":[102],"tri-nucleotide":[104],"as":[105],"unit":[108],"significantly":[109],"relative":[115],"In":[122],"case":[124],"sequences,":[128],"optimal":[129],"achieved":[132],"at":[133,177],"length":[136],"4.":[138],"Furthermore":[139],"in":[140,161,170],"plot":[142],"versus":[146],"gap,":[148],"periodicity":[150],"10-11":[152],"bps":[153],"observed":[155],"which":[156],"might":[157],"indicate":[158],"structural":[159],"preferences":[160],"sequence.":[165],"is":[168,173,182],"implemented":[169],"Java":[171],"available":[174],"for":[175],"download":[176],"ftp://ftp.pcbi.upenn.edu/GMM/.":[178],"CONCLUSION:":[179],"modeling":[181],"important":[184],"component":[185],"many":[187],"analysis":[189,225],"tools.":[190,226],"have":[192],"extended":[193],"incorporate":[199],"dependencies":[204],"between":[205],"elements.":[208],"proposed":[210],"are":[216],"likely":[217],"improve":[219],"overall":[221]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
