{"id":"https://openalex.org/W1990400148","doi":"https://doi.org/10.1089/cmb.2011.0040","title":"On the Inference of Dirichlet Mixture Priors for Protein Sequence Comparison","display_name":"On the Inference of Dirichlet Mixture Priors for Protein Sequence Comparison","publication_year":2011,"publication_date":"2011-06-24","ids":{"openalex":"https://openalex.org/W1990400148","doi":"https://doi.org/10.1089/cmb.2011.0040","mag":"1990400148","pmid":"https://pubmed.ncbi.nlm.nih.gov/21702690","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3145951"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2011.0040","doi":"https://doi.org/10.1089/cmb.2011.0040","is_oa":true,"landing_page_url":"https://doi.org/10.1089/cmb.2011.0040","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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1089/cmb.2011.0040","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038414601","display_name":"Xugang Ye","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xugang Ye","raw_affiliation_strings":["National Institutes of Health","National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health","institution_ids":["https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland 20894, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080970152","display_name":"Yi\u2010Kuo Yu","orcid":"https://orcid.org/0000-0002-6213-7665","observed_orcids":["https://orcid.org/0000-0002-6213-7665"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Kuo Yu","raw_affiliation_strings":["National Institutes of Health","National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health","institution_ids":["https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015061000","display_name":"Stephen F. Altschul","orcid":"https://orcid.org/0000-0003-2120-9631","observed_orcids":["https://orcid.org/0000-0003-2120-9631"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stephen F. Altschul","raw_affiliation_strings":["National Institutes of Health","National Center for Biotechnology Information National Library of Medicine National Institutes of Health Bethesda, MD 20894","National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health","institution_ids":["https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Center for Biotechnology Information National Library of Medicine National Institutes of Health Bethesda, MD 20894","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015061000"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":null,"apc_paid":null,"fwci":1.1757,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8201219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":"8","first_page":"941","last_page":"954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9897000193595886,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9897000193595886,"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":0.00800000037997961,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-multiple-sequence-alignment","display_name":"protein multiple sequence alignment","score":0.8650000095367432},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"minimum description length","score":0.7120000123977661},{"id":"https://openalex.org/keywords/model-complexity","display_name":"model complexity","score":0.7369999885559082},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.9800000190734863},{"id":"https://openalex.org/keywords/protein-sequence-comparison","display_name":"protein sequence comparison","score":0.6710000038146973}],"concepts":[{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.8044191598892212},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6620618104934692},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6007102131843567},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.5813344120979309},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.5706075429916382},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.568507730960846},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.56647789478302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5325732827186584},{"id":"https://openalex.org/C181262310","wikidata":"https://www.wikidata.org/wiki/Q5158330","display_name":"Concentration parameter","level":4,"score":0.49044033885002136},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.4618811309337616},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4345833957195282},{"id":"https://openalex.org/C52290693","wikidata":"https://www.wikidata.org/wiki/Q5532435","display_name":"Generalized Dirichlet distribution","level":5,"score":0.42694610357284546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.415367066860199},{"id":"https://openalex.org/C148158259","wikidata":"https://www.wikidata.org/wiki/Q975727","display_name":"Dirichlet's principle","level":4,"score":0.35654687881469727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3188663721084595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31402385234832764},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2951124906539917},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21506646275520325},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.12498900294303894},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1089/cmb.2011.0040","doi":"https://doi.org/10.1089/cmb.2011.0040","is_oa":true,"landing_page_url":"https://doi.org/10.1089/cmb.2011.0040","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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3145951","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3145951","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,"listed_in":[],"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":"J Comput Biol","raw_type":"Text"},{"id":"pmid:21702690","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21702690","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,"listed_in":[],"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":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.937.3160","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.937.3160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Stephen_Altschul/publication/51247417_On_the_inference_of_Dirichlet_mixture_priors_for_protein_sequence_comparison/links/00463526ec7d0e9e7c000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.939.5303","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.939.5303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.jhu.edu/%7Exye/papers_and_ppts/papers/DM_find.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1089/cmb.2011.0040","doi":"https://doi.org/10.1089/cmb.2011.0040","is_oa":true,"landing_page_url":"https://doi.org/10.1089/cmb.2011.0040","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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1574109141","https://openalex.org/W1974052996","https://openalex.org/W1994448597","https://openalex.org/W1998300401","https://openalex.org/W2020999234","https://openalex.org/W2024060531","https://openalex.org/W2035183366","https://openalex.org/W2056760934","https://openalex.org/W2066167693","https://openalex.org/W2101460669","https://openalex.org/W2107757325","https://openalex.org/W2122665495","https://openalex.org/W2797998707","https://openalex.org/W2802420499"],"related_works":["https://openalex.org/W1994448597","https://openalex.org/W1980557641","https://openalex.org/W2122665495","https://openalex.org/W7098938359","https://openalex.org/W1974052996","https://openalex.org/W7098634385","https://openalex.org/W7096686849","https://openalex.org/W2137857555","https://openalex.org/W2159021758","https://openalex.org/W2962631801"],"abstract_inverted_index":{"Dirichlet":[0,20,45,82,85,106,135],"mixtures":[1,86,136],"provide":[2],"an":[3,74],"elegant":[4],"formalism":[5],"for":[6,77],"constructing":[7],"and":[8,48,133],"evaluating":[9],"protein":[10],"multiple":[11],"sequence":[12],"alignments.":[13],"Their":[14],"use":[15],"requires":[16],"the":[17,63,69,78,97,118,139],"inference":[18],"of":[19,26,39,80],"mixture":[21,46,53,145],"priors":[22],"from":[23,56],"curated":[24],"sets":[25],"accurately":[27],"aligned":[28],"sequences.":[29],"This":[30],"article":[31],"addresses":[32],"two":[33],"questions":[34],"relevant":[35],"to":[36,68,84,96,115,130],"such":[37],"inference:":[38],"how":[40,49],"many":[41],"components":[42],"should":[43],"a":[44,51,57,81,92,105,144],"consist,":[47],"may":[50],"maximum-likelihood":[52],"be":[54],"derived":[55,146],"given":[58],"data":[59,102,140],"set.":[60],"To":[61],"apply":[62,91,125],"Minimum":[64],"Description":[65],"Length":[66],"principle":[67],"first":[70],"question,":[71],"we":[72,108],"extend":[73],"analytic":[75],"formula":[76],"complexity":[79],"model":[83],"by":[87,104],"informal":[88],"argument.":[89],"We":[90,124],"Gibbs-sampling":[93],"based":[94],"approach":[95],"second":[98],"question.":[99],"Using":[100],"artificial":[101],"generated":[103],"mixture,":[107],"demonstrate":[109],"that":[110,137],"our":[111,126],"methods":[112,127],"are":[113],"able":[114],"approximate":[116],"well":[117,129],"true":[119],"theory,":[120],"when":[121],"it":[122],"exists.":[123],"as":[128],"real":[131],"data,":[132],"infer":[134],"describe":[138],"better":[141],"than":[142],"does":[143],"using":[147],"previous":[148],"approaches.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}