{"id":"https://openalex.org/W2106341787","doi":"https://doi.org/10.1093/bioinformatics/bth454","title":"Training HMM structure with genetic algorithm for biological sequence analysis","display_name":"Training HMM structure with genetic algorithm for biological sequence analysis","publication_year":2004,"publication_date":"2004-08-05","ids":{"openalex":"https://openalex.org/W2106341787","doi":"https://doi.org/10.1093/bioinformatics/bth454","mag":"2106341787","pmid":"https://pubmed.ncbi.nlm.nih.gov/15297297"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth454","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth454","pdf_url":null,"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","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/A5060918471","display_name":"Kyoung\u2010Jae Won","orcid":"https://orcid.org/0000-0002-2924-9630"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kyoung-Jae Won","raw_affiliation_strings":["ISIS Group, ECS, University of Southampton, SO17 1BJ, UK. j.won@ecs.soton.ac.uk <j.won@ecs.soton.ac.uk>","ISIS Group, ECS, University of Southampton, SO17 1BJ, UK"],"affiliations":[{"raw_affiliation_string":"ISIS Group, ECS, University of Southampton, SO17 1BJ, UK. j.won@ecs.soton.ac.uk <j.won@ecs.soton.ac.uk>","institution_ids":["https://openalex.org/I43439940"]},{"raw_affiliation_string":"ISIS Group, ECS, University of Southampton, SO17 1BJ, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046941095","display_name":"Adam Pr\u00fcgel\u2010Bennett","orcid":"https://orcid.org/0000-0002-1329-5077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Pr\u00fcgel-Bennett","raw_affiliation_strings":["ISIS Group, ECS, University of Southampton, SO17 1BJ, UK"],"affiliations":[{"raw_affiliation_string":"ISIS Group, ECS, University of Southampton, SO17 1BJ, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083542637","display_name":"Anders Krogh","orcid":"https://orcid.org/0000-0002-5147-6282"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anders Krogh","raw_affiliation_strings":["Bioinformatics Centre, University of Copenhagen, DK-2100 Copenhagen, Denmark#TAB#"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Centre, University of Copenhagen, DK-2100 Copenhagen, Denmark#TAB#","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060918471"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.5676,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.81641357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"18","first_page":"3613","last_page":"3619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10141","display_name":"Probiotics and Fermented Foods","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9900000095367432,"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":0.9505905508995056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6575145721435547},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5915875434875488},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5507010221481323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5414180755615234},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5145794749259949},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4369089603424072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40871021151542664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3460380733013153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16845500469207764},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14165562391281128},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07017478346824646}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9505905508995056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575145721435547},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5915875434875488},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5507010221481323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5414180755615234},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5145794749259949},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4369089603424072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40871021151542664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3460380733013153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16845500469207764},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14165562391281128},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07017478346824646},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016123","descriptor_name":"Campylobacter jejuni","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016123","descriptor_name":"Campylobacter jejuni","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016123","descriptor_name":"Campylobacter jejuni","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/bth454","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth454","pdf_url":null,"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":"pmid:15297297","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15297297","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:eprints.soton.ac.uk:259393","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/d6294d30-74c2-11db-bee9-02004c4f4f50","is_oa":false,"landing_page_url":"https://curis.ku.dk/portal/da/publications/training-hmm-structure-with-genetic-algorithm-for-biological-sequence-analysis(d6294d30-74c2-11db-bee9-02004c4f4f50).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Won , K J & Krogh , A S 2004 , ' Training HMM structure with genetic algorithm for biological sequence analysis ' , Bioinformatics , no. Vol. 20 (18) , pp. 3613-9 . https://doi.org/10.1093/bioinformatics/bth454","raw_type":"article"},{"id":"pmh:oai:pure.atira.dk:publications/d6294d30-74c2-11db-bee9-02004c4f4f50","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/d6294d30-74c2-11db-bee9-02004c4f4f50","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Won , K J & Krogh , A S 2004 , ' Training HMM structure with genetic algorithm for biological sequence analysis ' , Bioinformatics , no. Vol. 20 (18) , pp. 3613-9 . https://doi.org/10.1093/bioinformatics/bth454","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1551413707","https://openalex.org/W1607768087","https://openalex.org/W1639032689","https://openalex.org/W2093989924","https://openalex.org/W2124290836","https://openalex.org/W2125838338","https://openalex.org/W2152150600","https://openalex.org/W2170700562","https://openalex.org/W2346127172","https://openalex.org/W2526073727","https://openalex.org/W2904250082","https://openalex.org/W3214380909"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2961085424","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W4306674287","https://openalex.org/W1521297879","https://openalex.org/W197415996","https://openalex.org/W2131226854","https://openalex.org/W1979120075","https://openalex.org/W2539985974"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1,157],"models":[2,158],"(HMMs)":[3],"are":[4,89],"widely":[5],"used":[6,176,186],"for":[7,83,141,155,177,187,205],"biological":[8,17],"sequence":[9],"analysis":[10],"because":[11],"of":[12,25,29,57,77,95,112,147,165,181,195],"their":[13,20,103],"ability":[14],"to":[15,53,92,117,167,184,200],"incorporate":[16],"information":[18],"in":[19],"structure.":[21,87],"An":[22],"automatic":[23],"means":[24],"optimizing":[26,84],"the":[27,42,55,58,75,85,110,142,148,179,182,188,206],"structure":[28,111],"HMMs":[30,44,113,161,183],"would":[31],"be":[32,46,115],"highly":[33],"desirable.":[34],"However,":[35],"this":[36,71,124],"raises":[37],"two":[38],"important":[39],"issues;":[40],"first,":[41],"new":[43],"should":[45],"biologically":[47],"interpretable,":[48],"and":[49,120,133,144],"second,":[50],"we":[51,73],"need":[52],"control":[54],"complexity":[56],"HMM":[59,86,139,198,203],"so":[60],"that":[61,108,185],"it":[62,134],"has":[63,210],"good":[64],"generalization":[65],"performance":[66,180],"on":[67,137],"unseen":[68],"sequences.":[69],"In":[70,123],"paper,":[72,125],"explore":[74],"possibility":[76],"using":[78,129],"a":[79,126,172,201],"genetic":[80],"algorithm":[81],"(GA)":[82],"GAs":[88,130],"sufficiently":[90],"flexible":[91],"allow":[93],"incorporation":[94],"other":[96],"techniques":[97],"such":[98],"as":[99],"Baum-Welch":[100,189],"training":[101,127],"within":[102],"evolutionary":[104],"cycle.":[105],"Furthermore,":[106],"operators":[107],"alter":[109],"can":[114],"designed":[116,204],"favour":[118],"interpretable":[119],"simple":[121],"structures.":[122],"strategy":[128],"is":[131,135,175],"proposed,":[132],"tested":[136],"finding":[138,196],"structures":[140],"promoter":[143],"coding":[145],"region":[146],"bacterium":[149],"Campylobacter":[150],"jejuni.":[151],"The":[152,191],"proposed":[153],"GA":[154],"hidden":[156],"(GA-HMM)":[159],"allows,":[160],"with":[162],"different":[163],"numbers":[164],"states":[166],"evolve.":[168],"To":[169],"prevent":[170],"over-fitting,":[171],"separate":[173],"dataset":[174],"comparing":[178],"training.":[190],"GA-HMM":[192],"was":[193],"capable":[194],"an":[197],"comparable":[199],"hand-coded":[202],"same":[207],"task,":[208],"which":[209],"been":[211],"published":[212],"previously.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}