{"id":"https://openalex.org/W2166444569","doi":"https://doi.org/10.1089/1066527041410472","title":"Combining Phylogenetic and Hidden Markov Models in Biosequence Analysis","display_name":"Combining Phylogenetic and Hidden Markov Models in Biosequence Analysis","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2166444569","doi":"https://doi.org/10.1089/1066527041410472","mag":"2166444569","pmid":"https://pubmed.ncbi.nlm.nih.gov/15285899"},"language":"en","primary_location":{"id":"doi:10.1089/1066527041410472","is_oa":false,"landing_page_url":"https://doi.org/10.1089/1066527041410472","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of 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/A5061240989","display_name":"Adam Siepel","orcid":"https://orcid.org/0000-0002-3557-7219"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adam Siepel","raw_affiliation_strings":["Center for Biomolecular Science and Engineering, University of California, Santa Cruz, CA 95064"],"affiliations":[{"raw_affiliation_string":"Center for Biomolecular Science and Engineering, University of California, Santa Cruz, CA 95064","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090849321","display_name":"David Haussler","orcid":"https://orcid.org/0000-0003-1533-4575"},"institutions":[{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Haussler","raw_affiliation_strings":["Howard Hughes Medical Institute, University of California, Santa Cruz, CA 95064"],"affiliations":[{"raw_affiliation_string":"Howard Hughes Medical Institute, University of California, Santa Cruz, CA 95064","institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061240989"],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":11.3437,"has_fulltext":false,"cited_by_count":253,"citation_normalized_percentile":{"value":0.99227127,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"11","issue":"2-3","first_page":"413","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9904999732971191,"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":0.9902999997138977,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7672686576843262},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.7434988021850586},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5607103109359741},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5592905282974243},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.5582709908485413},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5453606843948364},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49358880519866943},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.4459875822067261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43595123291015625},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.43573668599128723},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3437536358833313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.314558207988739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28192004561424255},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25679031014442444},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19195407629013062},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1723213791847229},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09255984425544739},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.0680016279220581}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7672686576843262},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.7434988021850586},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5607103109359741},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5592905282974243},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.5582709908485413},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5453606843948364},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49358880519866943},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4459875822067261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43595123291015625},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.43573668599128723},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3437536358833313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.314558207988739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28192004561424255},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25679031014442444},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19195407629013062},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1723213791847229},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09255984425544739},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0680016279220581},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"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":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016013","descriptor_name":"Likelihood Functions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016013","descriptor_name":"Likelihood Functions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016013","descriptor_name":"Likelihood Functions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","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":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1089/1066527041410472","is_oa":false,"landing_page_url":"https://doi.org/10.1089/1066527041410472","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:15285899","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15285899","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 computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:repository.cshl.edu:31102","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402288","display_name":"Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1546563018","https://openalex.org/W1844951369","https://openalex.org/W1881807356","https://openalex.org/W1920973730","https://openalex.org/W1941675760","https://openalex.org/W1957469265","https://openalex.org/W1967131476","https://openalex.org/W1969620339","https://openalex.org/W1984195830","https://openalex.org/W1988171432","https://openalex.org/W1992425974","https://openalex.org/W2009596137","https://openalex.org/W2026551295","https://openalex.org/W2038287860","https://openalex.org/W2047354232","https://openalex.org/W2052576140","https://openalex.org/W2063235239","https://openalex.org/W2068117230","https://openalex.org/W2072885673","https://openalex.org/W2075651743","https://openalex.org/W2091851394","https://openalex.org/W2101021009","https://openalex.org/W2101671848","https://openalex.org/W2102122585","https://openalex.org/W2102424972","https://openalex.org/W2107010419","https://openalex.org/W2114122189","https://openalex.org/W2118676074","https://openalex.org/W2119885694","https://openalex.org/W2124608480","https://openalex.org/W2125393869","https://openalex.org/W2128607924","https://openalex.org/W2137188869","https://openalex.org/W2139585463","https://openalex.org/W2140244239","https://openalex.org/W2143249496","https://openalex.org/W2151464048","https://openalex.org/W2151831732","https://openalex.org/W2155836971","https://openalex.org/W2156521045","https://openalex.org/W2163941254","https://openalex.org/W2166187656","https://openalex.org/W4231338500","https://openalex.org/W4234467048"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2084326697","https://openalex.org/W2194396582","https://openalex.org/W2027903142","https://openalex.org/W2082284720","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2354322608","https://openalex.org/W2379938888"],"abstract_inverted_index":{"A":[0],"few":[1],"models":[2,39,42,102,130,134],"have":[3],"appeared":[4],"in":[5,123,166],"recent":[6],"years":[7],"that":[8,135,152],"consider":[9,136],"not":[10],"only":[11],"the":[12,27,29,36,65,124,137,143,167,178],"way":[13,28],"substitutions":[14],"occur":[15],"through":[16],"evolutionary":[17],"history":[18],"at":[19],"each":[20],"site":[21,34,60],"of":[22,43,67,87,131,139,145,169,180],"a":[23,114,170],"genome,":[24],"but":[25],"also":[26],"process":[30],"changes":[31,58],"from":[32,59],"one":[33],"to":[35,48,61,107,163],"next.":[37],"These":[38],"combine":[40],"phylogenetic":[41,69,98,172],"molecular":[44],"evolution,":[45],"which":[46,55,126],"apply":[47],"individual":[49],"sites,":[50],"and":[51,79,99,103,116,157,173],"hidden":[52,100,174],"Markov":[53,101,175],"models,":[54,70],"allow":[56],"for":[57,77,82,119,128],"site.":[62],"Besides":[63],"improving":[64],"realism":[66],"ordinary":[68],"they":[71],"are":[72],"potentially":[73],"very":[74],"powerful":[75],"tools":[76],"inference":[78],"prediction--for":[80],"example,":[81],"gene":[83],"finding":[84],"or":[85],"prediction":[86],"secondary":[88],"structure.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"review":[94],"progress":[95],"on":[96,142],"combined":[97,171],"present":[104,148],"some":[105],"extensions":[106],"previous":[108],"work.":[109],"Our":[110],"main":[111],"result":[112],"is":[113],"simple":[115],"efficient":[117],"method":[118],"accommodating":[120],"higher-order":[121,153,181],"states":[122,182],"HMM,":[125],"allows":[127],"context-dependent":[129],"substitution--that":[132],"is,":[133],"effects":[138],"neighboring":[140],"bases":[141],"pattern":[144],"substitution.":[146],"We":[147],"experimental":[149],"results":[150],"indicating":[151],"states,":[154],"autocorrelated":[155],"rates,":[156],"multiple":[158],"functional":[159],"categories":[160],"all":[161],"lead":[162],"significant":[164],"improvements":[165],"fit":[168],"model,":[176],"with":[177],"effect":[179],"being":[183],"particularly":[184],"pronounced.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":12}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}