{"id":"https://openalex.org/W2112380236","doi":"https://doi.org/10.1093/bioinformatics/btp265","title":"Augmented training of hidden Markov models to recognize remote homologs via simulated evolution","display_name":"Augmented training of hidden Markov models to recognize remote homologs via simulated evolution","publication_year":2009,"publication_date":"2009-04-23","ids":{"openalex":"https://openalex.org/W2112380236","doi":"https://doi.org/10.1093/bioinformatics/btp265","mag":"2112380236","pmid":"https://pubmed.ncbi.nlm.nih.gov/19389731"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btp265","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp265","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/25/13/1602/48996791/bioinformatics_25_13_1602.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/25/13/1602/48996791/bioinformatics_25_13_1602.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101478918","display_name":"Anoop Kumar","orcid":"https://orcid.org/0009-0004-7029-4697"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anoop Kumar","raw_affiliation_strings":["Department of Computer Science, Tufts University, Medford, MA, USA","Department of Computer Science, Tufts University, Medford, MA, USA.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Computer Science, Tufts University, Medford, MA, USA.;","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026411021","display_name":"Lenore Cowen","orcid":"https://orcid.org/0000-0001-6698-6413"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lenore Cowen","raw_affiliation_strings":["Department of Computer Science, Tufts University, Medford, MA, USA","Department of Computer Science, Tufts University, Medford, MA, USA.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Computer Science, Tufts University, Medford, MA, USA.;","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5026411021","https://openalex.org/A5101478918"],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.3501,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.80186006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"13","first_page":"1602","last_page":"1608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998000264167786,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998000264167786,"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":0.9997000098228455,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9987999796867371,"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":0.8696059584617615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6909066438674927},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5722508430480957},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5553631782531738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.524001955986023},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.5029672980308533},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4772339165210724},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4410867989063263},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43687495589256287},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.42232757806777954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41732946038246155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3979523777961731},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20839011669158936},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20210880041122437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1422581970691681},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10806727409362793}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8696059584617615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6909066438674927},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5722508430480957},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5553631782531738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524001955986023},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.5029672980308533},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4772339165210724},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4410867989063263},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43687495589256287},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.42232757806777954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41732946038246155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3979523777961731},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20839011669158936},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20210880041122437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1422581970691681},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10806727409362793},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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":"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btp265","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp265","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/25/13/1602/48996791/bioinformatics_25_13_1602.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19389731","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19389731","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:2732314","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2732314","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btp265","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp265","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/25/13/1602/48996791/bioinformatics_25_13_1602.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1590325200","display_name":null,"funder_award_id":"R01 GM080330","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G5265660885","display_name":null,"funder_award_id":"1R01 GM 080330-01A1","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6174545591","display_name":null,"funder_award_id":"1R01GM080330","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2112380236.pdf","grobid_xml":"https://content.openalex.org/works/W2112380236.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W11981056","https://openalex.org/W642629379","https://openalex.org/W1558365920","https://openalex.org/W1966628412","https://openalex.org/W1971913854","https://openalex.org/W1982481323","https://openalex.org/W1991022130","https://openalex.org/W2035100851","https://openalex.org/W2036866029","https://openalex.org/W2049349724","https://openalex.org/W2055043387","https://openalex.org/W2085277871","https://openalex.org/W2086173258","https://openalex.org/W2097555181","https://openalex.org/W2107427637","https://openalex.org/W2131889225","https://openalex.org/W2132926880","https://openalex.org/W2133657429","https://openalex.org/W2136280642","https://openalex.org/W2140244239","https://openalex.org/W2144363281","https://openalex.org/W2151831732","https://openalex.org/W2164698543","https://openalex.org/W2213326431","https://openalex.org/W2283504545","https://openalex.org/W6600461906","https://openalex.org/W6674463856","https://openalex.org/W6684274822"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2082284720","https://openalex.org/W2084326697","https://openalex.org/W2194396582","https://openalex.org/W2027903142","https://openalex.org/W2116722627","https://openalex.org/W2354322608","https://openalex.org/W2379938888","https://openalex.org/W2804608325"],"abstract_inverted_index":{"MOTIVATION:":[0],"While":[1],"profile":[2],"hidden":[3],"Markov":[4],"models":[5],"(HMMs)":[6],"are":[7],"successful":[8],"and":[9,93,106],"powerful":[10],"methods":[11],"to":[12,26,53],"recognize":[13],"homologous":[14],"proteins,":[15],"they":[16],"can":[17,36],"break":[18],"down":[19],"when":[20],"homology":[21],"becomes":[22],"too":[23],"distant":[24],"due":[25],"lack":[27],"of":[28,40,51],"sufficient":[29],"training":[30,57,72],"data.":[31,84],"We":[32,60,85],"show":[33],"that":[34,69,87],"we":[35],"improve":[37],"the":[38],"performance":[39],"HMMs":[41,70,79],"in":[42,62,103],"this":[43],"domain":[44],"by":[45],"using":[46],"a":[47,88],"simple":[48],"simulated":[49,76],"model":[50],"evolution":[52,77],"create":[54],"an":[55],"augmented":[56,74],"set.":[58],"RESULTS:":[59],"show,":[61],"two":[63],"different":[64,104,113],"remote":[65],"protein":[66],"homolog":[67],"tasks,":[68],"whose":[71],"is":[73],"with":[75],"outperform":[78],"trained":[80],"only":[81],"on":[82],"real":[83],"find":[86],"mutation":[89],"rate":[90],"between":[91],"15":[92],"20%":[94],"performs":[95],"best":[96],"for":[97,107],"recognizing":[98,108],"G-protein":[99],"coupled":[100],"receptor":[101],"proteins":[102,111],"classes,":[105],"SCOP":[109],"super-family":[110],"from":[112],"families.":[114]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
