{"id":"https://openalex.org/W2166515972","doi":"https://doi.org/10.1109/csb.2003.1227331","title":"Haplotype motifs: an algorithmic approach to locating evolutionarily conserved patterns in haploid sequences","display_name":"Haplotype motifs: an algorithmic approach to locating evolutionarily conserved patterns in haploid sequences","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2166515972","doi":"https://doi.org/10.1109/csb.2003.1227331","mag":"2166515972","pmid":"https://pubmed.ncbi.nlm.nih.gov/16452806"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-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/A5051953313","display_name":"Russell Schwartz","orcid":"https://orcid.org/0000-0002-4970-2252"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R. Schwartz","raw_affiliation_strings":["Department of Biological Sciences, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051953313"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.5426,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7090203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"291","issue":null,"first_page":"306","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9993000030517578,"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.9993000030517578,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9980000257492065,"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/haplotype","display_name":"Haplotype","score":0.8509782552719116},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5907983183860779},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5271517634391785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4892830550670624},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4263591468334198},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41748878359794617},{"id":"https://openalex.org/keywords/haplotype-estimation","display_name":"Haplotype estimation","score":0.4109748899936676},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3857802152633667},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3693530559539795},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3644134998321533},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.3358275890350342},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3111204206943512},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2996106743812561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2982953190803528},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10080605745315552},{"id":"https://openalex.org/keywords/allele","display_name":"Allele","score":0.09833541512489319}],"concepts":[{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.8509782552719116},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5907983183860779},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5271517634391785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4892830550670624},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4263591468334198},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41748878359794617},{"id":"https://openalex.org/C44432683","wikidata":"https://www.wikidata.org/wiki/Q17145705","display_name":"Haplotype estimation","level":5,"score":0.4109748899936676},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3857802152633667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3693530559539795},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3644134998321533},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3358275890350342},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3111204206943512},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2996106743812561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2982953190803528},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10080605745315552},{"id":"https://openalex.org/C180754005","wikidata":"https://www.wikidata.org/wiki/Q80726","display_name":"Allele","level":3,"score":0.09833541512489319},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D006238","descriptor_name":"Haploidy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006238","descriptor_name":"Haploidy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006238","descriptor_name":"Haploidy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","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":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":"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":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":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","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},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/csb.2003.1227331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},{"id":"pmid:16452806","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16452806","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":"Proceedings. IEEE Computer Society Bioinformatics Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1508985588","https://openalex.org/W1583476286","https://openalex.org/W1711580613","https://openalex.org/W1967980922","https://openalex.org/W2007781696","https://openalex.org/W2047222949","https://openalex.org/W2049414355","https://openalex.org/W2086699924","https://openalex.org/W2089718377","https://openalex.org/W2126384007","https://openalex.org/W2127230663","https://openalex.org/W2133571829","https://openalex.org/W2146820632","https://openalex.org/W2152664025","https://openalex.org/W2156341632","https://openalex.org/W2162445884","https://openalex.org/W2165671666","https://openalex.org/W2165792170","https://openalex.org/W2168909179","https://openalex.org/W2169484904","https://openalex.org/W2297165308"],"related_works":["https://openalex.org/W2468405568","https://openalex.org/W2170167789","https://openalex.org/W2105845028","https://openalex.org/W1522648572","https://openalex.org/W49128561","https://openalex.org/W2066735477","https://openalex.org/W2545986793","https://openalex.org/W2067047548","https://openalex.org/W1750162611","https://openalex.org/W2169145207"],"abstract_inverted_index":{"The":[0],"promise":[1],"of":[2,47,52,62,82],"plentiful":[3],"data":[4],"on":[5,42,152,162],"common":[6,23],"human":[7,95],"genetic":[8,20,49,104],"variations":[9],"has":[10,40],"given":[11],"hope":[12],"that":[13,25],"we":[14,76],"will":[15,77],"be":[16],"able":[17],"to":[18,29,58,69,157,171],"uncover":[19],"factors":[21],"behind":[22],"diseases":[24],"have":[26],"proven":[27],"difficult":[28],"locate":[30],"by":[31],"prior":[32],"methods.":[33],"Much":[34],"recent":[35],"interest":[36],"in":[37,56,93,102,118,125,155,169],"this":[38],"problem":[39],"focused":[41],"using":[43,121],"haplotypes":[44],"(contiguous":[45],"regions":[46,105],"correlated":[48],"variations),":[50],"instead":[51],"the":[53,60,63,87,94,98,131,138,159,167],"isolated":[54],"variations,":[55],"order":[57,68,156,170],"reduce":[59],"size":[61],"statistical":[64],"analysis":[65],"problem.":[66],"In":[67],"most":[70],"effectively":[71],"use":[72],"such":[73],"variation":[74],"data,":[75,154],"need":[78],"a":[79,111,119,146],"better":[80],"understanding":[81],"haplotype":[83,91,116,143],"structure,":[84],"including":[85],"both":[86],"general":[88],"principles":[89],"underlying":[90],"structure":[92,117,144],"population":[96,120],"and":[97,133,142,161],"specific":[99],"structures":[100],"found":[101,124],"particular":[103],"or":[106],"sub-populations.":[107,128],"This":[108],"paper":[109],"presents":[110,150],"probabilistic":[112],"model":[113,132],"for":[114,136,145],"analyzing":[115],"conserved":[122],"motifs":[123],"statistically":[126],"significant":[127],"It":[129,148],"describes":[130],"computational":[134],"methods":[135],"deriving":[137],"predicted":[139],"motif":[140],"set":[141],"population.":[147],"further":[149],"results":[151],"simulated":[153],"validate":[158],"method,":[160],"two":[163],"real":[164],"datasets":[165],"from":[166],"literature,":[168],"illustrate":[172],"its":[173],"practical":[174],"application.":[175]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
