{"id":"https://openalex.org/W2153524490","doi":"https://doi.org/10.1093/bioinformatics/bth153","title":"Multiple-sequence functional annotation and the generalized hidden Markov phylogeny","display_name":"Multiple-sequence functional annotation and the generalized hidden Markov phylogeny","publication_year":2004,"publication_date":"2004-02-26","ids":{"openalex":"https://openalex.org/W2153524490","doi":"https://doi.org/10.1093/bioinformatics/bth153","mag":"2153524490"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth153","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth153","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/12/1850/48905858/bioinformatics_20_12_1850.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/20/12/1850/48905858/bioinformatics_20_12_1850.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010768151","display_name":"Jon McAuliffe","orcid":"https://orcid.org/0000-0003-2626-7320"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jon D. McAuliffe","raw_affiliation_strings":["Department of Statistics, University of California, 367 Evans Hall, Berkeley, CA 94720, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, 367 Evans Hall, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020008219","display_name":"Lior Pachter","orcid":"https://orcid.org/0000-0002-9164-6231"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lior Pachter","raw_affiliation_strings":["Department of Mathematics, University of California, 970 Evans Hall, Berkeley, CA 94720, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of California, 970 Evans Hall, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049812527","display_name":"Michael I. Jordan","orcid":"https://orcid.org/0000-0001-8935-817X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I. Jordan","raw_affiliation_strings":["Department of Statistics, University of California, 367 Evans Hall, Berkeley, CA 94720, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, 367 Evans Hall, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010768151"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.9514,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.94471612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":"12","first_page":"1850","last_page":"1860"},"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/T10012","display_name":"Genetic diversity and population structure","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.9943000078201294,"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/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.7343477010726929},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6443420648574829},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.565514087677002},{"id":"https://openalex.org/keywords/phylogenetics","display_name":"Phylogenetics","score":0.5598298907279968},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5333637595176697},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5324802398681641},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"Comparative genomics","score":0.49893760681152344},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4770309627056122},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.46553292870521545},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.46343404054641724},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4534265995025635},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4438683092594147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4360347390174866},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4312414824962616},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.34426000714302063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31310755014419556},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2906759977340698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2757195234298706},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.2674108147621155},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.25024640560150146},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.10502853989601135}],"concepts":[{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.7343477010726929},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6443420648574829},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.565514087677002},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.5598298907279968},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5333637595176697},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5324802398681641},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.49893760681152344},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4770309627056122},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46553292870521545},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.46343404054641724},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4534265995025635},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4438683092594147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4360347390174866},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4312414824962616},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.34426000714302063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31310755014419556},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2906759977340698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2757195234298706},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2674108147621155},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25024640560150146},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.10502853989601135}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/bth153","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth153","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/12/1850/48905858/bioinformatics_20_12_1850.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:authors.library.caltech.edu:74917","is_oa":false,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20170308-135943475","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"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:berkeley.edu:28722-bk0000n2p7r","is_oa":false,"landing_page_url":"http://stat-reports.lib.berkeley.edu/accessPages/647.html","pdf_url":null,"source":{"id":"https://openalex.org/S7407050879","display_name":"UC Berkeley","issn_l":null,"issn":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"technical reports"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.318.6484","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.318.6484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2004/02/26/bioinformatics.bth153.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bth153","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth153","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/12/1850/48905858/bioinformatics_20_12_1850.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.49000000953674316,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2153524490.pdf","grobid_xml":"https://content.openalex.org/works/W2153524490.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1511730061","https://openalex.org/W1513861746","https://openalex.org/W1746680969","https://openalex.org/W1957469265","https://openalex.org/W1969620339","https://openalex.org/W1994017531","https://openalex.org/W2015609160","https://openalex.org/W2062345582","https://openalex.org/W2087892194","https://openalex.org/W2102424972","https://openalex.org/W2105926960","https://openalex.org/W2107246857","https://openalex.org/W2121114391","https://openalex.org/W2128607924","https://openalex.org/W2142418779","https://openalex.org/W2149467186","https://openalex.org/W2154131901","https://openalex.org/W2156521045","https://openalex.org/W2166187656","https://openalex.org/W2166444569","https://openalex.org/W2170496993"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2378969149","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2149492307","https://openalex.org/W1985408726"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"Phylogenetic":[2],"shadowing":[3,33],"is":[4,150],"a":[5,26,42,50,90,109],"comparative":[6,105],"genomics":[7],"principle":[8],"that":[9,95,128],"allows":[10],"for":[11,30],"the":[12],"discovery":[13],"of":[14,52,88,112,123],"conserved":[15],"regions":[16,56],"in":[17,78,143],"sequences":[18],"from":[19,61],"multiple":[20,79],"closely":[21],"related":[22],"organisms.":[23],"We":[24,65,82,93],"develop":[25],"formal":[27],"probabilistic":[28],"framework":[29],"combining":[31],"phylogenetic":[32],"with":[34],"feature-based":[35],"functional":[36,55],"annotation":[37],"methods.":[38],"The":[39],"resulting":[40],"model,":[41],"generalized":[43],"hidden":[44],"Markov":[45],"phylogeny":[46],"(GHMP),":[47],"applies":[48],"to":[49,58,72,137],"variety":[51],"situations":[53],"where":[54],"are":[57],"be":[59,70],"inferred":[60],"evolutionary":[62],"constraints.":[63],"Results:":[64],"show":[66],"how":[67],"GHMPs":[68],"can":[69],"used":[71],"predict":[73],"complete":[74],"shared":[75],"gene":[76,102],"structures":[77],"primate":[80],"sequences.":[81],"also":[83],"describe":[84],"shadower,":[85],"our":[86],"implementation":[87],"such":[89],"prediction":[91],"system.":[92],"find":[94],"shadower":[96],"outperforms":[97],"previously":[98],"reported":[99],"ab":[100],"initio":[101],"finders,":[103],"including":[104],"human\u2013mouse":[106],"approaches,":[107],"on":[108,119],"small":[110],"sample":[111],"diverse":[113],"exonic":[114],"regions.":[115],"Finally,":[116],"we":[117],"report":[118],"an":[120],"empirical":[121],"analysis":[122],"shadower's":[124],"performance":[125],"which":[126],"reveals":[127],"as":[129,131],"few":[130],"five":[132],"well-chosen":[133],"species":[134],"may":[135],"suffice":[136],"attain":[138],"maximal":[139],"sensitivity":[140],"and":[141],"specificity":[142],"exon":[144],"demarcation.":[145],"Availability:":[146],"A":[147],"Web":[148],"server":[149],"available":[151],"at":[152],"http://bonaire.lbl.gov/shadower":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
