{"id":"https://openalex.org/W2095910078","doi":"https://doi.org/10.1093/bioinformatics/bti261","title":"Inference of missing SNPs and information quantity measurements for haplotype blocks","display_name":"Inference of missing SNPs and information quantity measurements for haplotype blocks","publication_year":2005,"publication_date":"2005-02-04","ids":{"openalex":"https://openalex.org/W2095910078","doi":"https://doi.org/10.1093/bioinformatics/bti261","mag":"2095910078","pmid":"https://pubmed.ncbi.nlm.nih.gov/15699029"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti261","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti261","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/2001/48972769/bioinformatics_21_9_2001.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/2001/48972769/bioinformatics_21_9_2001.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058572348","display_name":"S.-C. Su","orcid":"https://orcid.org/0009-0006-0167-2484"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S.-C. Su","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, 90089, USA","Dept, of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, 90089, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept, of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001082656","display_name":"C.\u2010C. Jay Kuo","orcid":"https://orcid.org/0000-0001-9474-5035"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-C. J. Kuo","raw_affiliation_strings":["Dept, of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept, of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443189","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0002-3228-9166"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. Chen","raw_affiliation_strings":["Department of Biological Sciences, University of Southern California Los Angeles CA 90089 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, University of Southern California Los Angeles CA 90089 USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058572348"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":2.4126,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88497528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"9","first_page":"2001","last_page":"2007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9160000085830688,"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":0.9160000085830688,"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/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.016300000250339508,"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":0.009700000286102295,"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":0.7977825999259949},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7649385929107666},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.661848783493042},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.6451306343078613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5143741369247437},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3664201498031616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3492732644081116},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.320284366607666},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3186267614364624},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2552158236503601},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23758232593536377},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19512727856636047},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.17686989903450012},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15165162086486816}],"concepts":[{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.7977825999259949},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7649385929107666},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.661848783493042},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6451306343078613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5143741369247437},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3664201498031616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3492732644081116},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.320284366607666},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3186267614364624},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2552158236503601},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23758232593536377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19512727856636047},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.17686989903450012},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15165162086486816}],"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":"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":"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":"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":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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":"D015810","descriptor_name":"Linkage Disequilibrium","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015810","descriptor_name":"Linkage Disequilibrium","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015810","descriptor_name":"Linkage Disequilibrium","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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:10.1093/bioinformatics/bti261","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti261","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/2001/48972769/bioinformatics_21_9_2001.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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:15699029","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15699029","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti261","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti261","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/9/2001/48972769/bioinformatics_21_9_2001.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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":[],"awards":[{"id":"https://openalex.org/G171726519","display_name":null,"funder_award_id":"P50 HG002790","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1508985588","https://openalex.org/W1826574233","https://openalex.org/W1891283710","https://openalex.org/W1964901903","https://openalex.org/W2012003805","https://openalex.org/W2021123182","https://openalex.org/W2037454239","https://openalex.org/W2042413629","https://openalex.org/W2083878136","https://openalex.org/W2109347434","https://openalex.org/W2110755408","https://openalex.org/W2135732313","https://openalex.org/W2156341632","https://openalex.org/W2159267146","https://openalex.org/W3146051953","https://openalex.org/W4205911826"],"related_works":["https://openalex.org/W3146762847","https://openalex.org/W2398263405","https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W2056886854","https://openalex.org/W2025446304","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W1499399347"],"abstract_inverted_index":{"MOTIVATION:":[0],"Missing":[1],"data":[2,30,187],"in":[3,156,184],"genotyping":[4,13],"single":[5],"nucleotide":[6],"polymorphism":[7],"(SNP)":[8],"spots":[9],"are":[10,57],"common.":[11],"High-throughput":[12],"methods":[14],"usually":[15],"have":[16],"a":[17,64,79,92,112],"high":[18],"rate":[19],"of":[20,81,120,200],"missing":[21,38,41,121,154],"data.":[22],"For":[23],"example,":[24],"the":[25,44,53,87,107,118,124,129,139,149,164,174,193,198,201],"published":[26],"human":[27],"chromosome":[28],"21":[29],"by":[31],"Patil":[32],"et":[33],"al.":[34],"contains":[35],"about":[36],"20%":[37],"SNPs.":[39,122],"Inferring":[40],"SNPs":[42,155],"using":[43],"haplotype":[45,54,82,98,158],"block":[46,55,99,159,165,176],"structure":[47],"is":[48,178],"promising":[49],"but":[50],"difficult":[51],"because":[52],"boundaries":[56],"not":[58],"well":[59],"defined.":[60],"Here":[61],"we":[62,73,110,127,142],"propose":[63,74,111],"global":[65,194],"algorithm":[66,95,116,132,151,168,183],"to":[67,75,133,148,152,162],"overcome":[68],"this":[69],"difficulty.":[70],"RESULTS:":[71],"First,":[72],"use":[76,143],"entropy":[77,88,108,177],"as":[78,161],"measure":[80,89],"diversity.":[83],"We":[84,180],"show":[85,191],"that":[86,192],"combined":[90],"with":[91],"dynamic":[93,130],"programming":[94,131],"produces":[96],"better":[97],"partitions":[100],"than":[101],"other":[102],"measures.":[103],"Second,":[104],"based":[105],"on":[106],"measure,":[109],"two-step":[113],"iterative":[114,145],"partition-inference":[115],"for":[117],"inference":[119],"At":[123,138],"first":[125],"step,":[126,141],"apply":[128],"partition":[134],"haplotypes":[135],"into":[136],"blocks.":[137],"second":[140],"an":[144],"process":[146],"similar":[147],"expectation-maximization":[150],"infer":[153],"each":[157],"so":[160],"minimize":[163],"entropy.":[166],"The":[167,189],"iterates":[169],"these":[170],"two":[171],"steps":[172],"until":[173],"total":[175],"minimized.":[179],"test":[181],"our":[182],"several":[185],"experimental":[186],"sets.":[188],"results":[190],"approach":[195],"significantly":[196],"improves":[197],"accuracy":[199],"inference.":[202],"AVAILABILITY:":[203],"Upon":[204],"request.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
