{"id":"https://openalex.org/W2094240435","doi":"https://doi.org/10.1089/10665270260518263","title":"Using Substitution Matrices to Estimate Probability Distributions for Biological Sequences","display_name":"Using Substitution Matrices to Estimate Probability Distributions for Biological Sequences","publication_year":2002,"publication_date":"2002-12-01","ids":{"openalex":"https://openalex.org/W2094240435","doi":"https://doi.org/10.1089/10665270260518263","mag":"2094240435","pmid":"https://pubmed.ncbi.nlm.nih.gov/12614546"},"language":"en","primary_location":{"id":"doi:10.1089/10665270260518263","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270260518263","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/A5009368988","display_name":"Eleazar Eskin","orcid":"https://orcid.org/0000-0003-1149-4758"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eleazar Eskin","raw_affiliation_strings":["Department of Computer Science, Columbia University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057375933","display_name":"William Stafford Noble","orcid":"https://orcid.org/0000-0001-7283-4715"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Stafford Noble","raw_affiliation_strings":["Department of Genome Sciences, University of Washington"],"affiliations":[{"raw_affiliation_string":"Department of Genome Sciences, University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113437318","display_name":"Yoram Singer","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yoram Singer","raw_affiliation_strings":["School of Computer Science and Engineering, Hebrew University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Hebrew University","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009368988"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12685275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"6","first_page":"775","last_page":"791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973999857902527,"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":0.9962999820709229,"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/substitution","display_name":"Substitution (logic)","score":0.7067967653274536},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.6996990442276001},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6090373992919922},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.6025570631027222},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5411180257797241},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5229440331459045},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5005812644958496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4598046839237213},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.448464959859848},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4315303862094879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4246862232685089},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.26065805554389954}],"concepts":[{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.7067967653274536},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.6996990442276001},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6090373992919922},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.6025570631027222},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5411180257797241},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5229440331459045},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5005812644958496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4598046839237213},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.448464959859848},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4315303862094879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4246862232685089},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26065805554389954},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008433","descriptor_name":"Mathematics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008433","descriptor_name":"Mathematics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008433","descriptor_name":"Mathematics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1089/10665270260518263","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270260518263","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:12614546","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12614546","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}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306799","display_name":"Pharmaceutical Research and Manufacturers of America Foundation","ror":"https://ror.org/01z88k350"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W580160208","https://openalex.org/W1422803820","https://openalex.org/W1483704041","https://openalex.org/W1531116739","https://openalex.org/W1574109141","https://openalex.org/W1970999032","https://openalex.org/W1974892965","https://openalex.org/W1982496832","https://openalex.org/W1988237769","https://openalex.org/W1990645294","https://openalex.org/W2000758249","https://openalex.org/W2006258746","https://openalex.org/W2013570924","https://openalex.org/W2049633694","https://openalex.org/W2066513603","https://openalex.org/W2096556032","https://openalex.org/W2099111195","https://openalex.org/W2102122585","https://openalex.org/W2117619142","https://openalex.org/W2122665495","https://openalex.org/W2129448726","https://openalex.org/W2129837421","https://openalex.org/W2140244239","https://openalex.org/W2156628505","https://openalex.org/W2163294786","https://openalex.org/W2283504545","https://openalex.org/W2601913882","https://openalex.org/W2611814747","https://openalex.org/W2797816625","https://openalex.org/W3150945973","https://openalex.org/W3214380909"],"related_works":["https://openalex.org/W2379444625","https://openalex.org/W2393147081","https://openalex.org/W2575869988","https://openalex.org/W4308647020","https://openalex.org/W2370088286","https://openalex.org/W2385568494","https://openalex.org/W2075768550","https://openalex.org/W3022218857","https://openalex.org/W2038132579","https://openalex.org/W2042068218"],"abstract_inverted_index":{"Accurately":[0],"estimating":[1,24],"probabilities":[2,90],"from":[3,30],"observations":[4,31],"is":[5,41,72,84,99,109],"important":[6],"for":[7,23,79],"probabilistic-based":[8],"approaches":[9],"to":[10,52,77,86,101,104,112],"problems":[11],"in":[12,95],"computational":[13],"biology.":[14],"In":[15,50],"this":[16],"paper":[17],"we":[18],"present":[19],"a":[20,33,59],"biologically-motivated":[21],"method":[22,40,57,83,108],"probability":[25,47,114],"distributions":[26,115],"over":[27,67,116],"discrete":[28],"alphabets":[29],"using":[32],"mixture":[34],"model":[35],"of":[36,44],"common":[37],"ancestors.":[38],"The":[39,82,107],"an":[42,96],"extension":[43],"substitution":[45],"matrix-based":[46],"estimation":[48],"methods.":[49,106],"contrast":[51],"previous":[53,105],"such":[54],"methods,":[55],"our":[56],"has":[58,64],"simple":[60,76],"Bayesian":[61],"interpretation":[62],"and":[63,75,98,119],"the":[65],"advantage":[66],"Dirichlet":[68],"mixtures":[69],"that":[70],"it":[71],"both":[73],"effective":[74],"compute":[78],"large":[80],"alphabets.":[81],"applied":[85,111],"estimate":[87,113],"amino":[88],"acid":[89],"based":[91],"on":[92],"observed":[93],"counts":[94],"alignment":[97],"shown":[100],"perform":[102],"comparably":[103],"also":[110],"protein":[117,121],"families":[118],"improves":[120],"classification":[122],"accuracy.":[123]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}