{"id":"https://openalex.org/W4309997573","doi":"https://doi.org/10.1109/ictc55196.2022.9952611","title":"Genotype Imputation Using K-Nearest Neighbors and Levenshtein Distance Metric","display_name":"Genotype Imputation Using K-Nearest Neighbors and Levenshtein Distance Metric","publication_year":2022,"publication_date":"2022-10-19","ids":{"openalex":"https://openalex.org/W4309997573","doi":"https://doi.org/10.1109/ictc55196.2022.9952611"},"language":"en","primary_location":{"id":"doi:10.1109/ictc55196.2022.9952611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc55196.2022.9952611","pdf_url":null,"source":{"id":"https://openalex.org/S4363607740","display_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5028527445","display_name":"Nishkal Hundia","orcid":null},"institutions":[{"id":"https://openalex.org/I52527943","display_name":"Ahmedabad University","ror":"https://ror.org/02swff503","country_code":"IN","type":"education","lineage":["https://openalex.org/I52527943"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nishkal Hundia","raw_affiliation_strings":["Puna International School,Ahmedabad,India","Puna International School, Ahmedabad, India"],"affiliations":[{"raw_affiliation_string":"Puna International School,Ahmedabad,India","institution_ids":["https://openalex.org/I52527943"]},{"raw_affiliation_string":"Puna International School, Ahmedabad, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013383512","display_name":"Naveed Kabir","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naveed Kabir","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,United States","Georgia Institute of Technology, Atlanta, United States"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,United States","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031733330","display_name":"Sweksha Mehta","orcid":null},"institutions":[{"id":"https://openalex.org/I196272386","display_name":"Providence College","ror":"https://ror.org/00rxpqe74","country_code":"US","type":"education","lineage":["https://openalex.org/I196272386"]},{"id":"https://openalex.org/I67641582","display_name":"Union County College","ror":"https://ror.org/00wjxpj07","country_code":"US","type":"education","lineage":["https://openalex.org/I67641582"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sweksha Mehta","raw_affiliation_strings":["Union County Vo-tech High School,New Providence,United States","Union County Vo-tech High School, New Providence, United States"],"affiliations":[{"raw_affiliation_string":"Union County Vo-tech High School,New Providence,United States","institution_ids":["https://openalex.org/I67641582"]},{"raw_affiliation_string":"Union County Vo-tech High School, New Providence, United States","institution_ids":["https://openalex.org/I67641582","https://openalex.org/I196272386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028106905","display_name":"Abhay Pokhriyal","orcid":null},"institutions":[{"id":"https://openalex.org/I872719","display_name":"Bellarmine University","ror":"https://ror.org/04p81nz21","country_code":"US","type":"education","lineage":["https://openalex.org/I872719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhay Pokhriyal","raw_affiliation_strings":["Bellarmine College Preparatory,San Jose,United States","Bellarmine College Preparatory, San Jose, United States"],"affiliations":[{"raw_affiliation_string":"Bellarmine College Preparatory,San Jose,United States","institution_ids":["https://openalex.org/I872719"]},{"raw_affiliation_string":"Bellarmine College Preparatory, San Jose, United States","institution_ids":["https://openalex.org/I872719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080145268","display_name":"Zhuo En Chua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155519","display_name":"St Luke's Hospital","ror":"https://ror.org/053x7k331","country_code":"SG","type":"healthcare","lineage":["https://openalex.org/I4210155519"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhuo En Chua","raw_affiliation_strings":["SJII Singapore,Singapore","SJII Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"SJII Singapore,Singapore","institution_ids":["https://openalex.org/I4210155519"]},{"raw_affiliation_string":"SJII Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043114491","display_name":"Arjun Rajaram","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjun Rajaram","raw_affiliation_strings":["University of Maryland, College Park,San Jose,United States","University of Maryland, College Park, San Jose, United States"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park,San Jose,United States","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, San Jose, United States","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051876024","display_name":"Michael Lutz","orcid":null},"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"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Lutz","raw_affiliation_strings":["UC Berkeley,Berkeley,United States","UC Berkeley, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"UC Berkeley,Berkeley,United States","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003035291","display_name":"Amisha Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amisha Kumar","raw_affiliation_strings":["Case Western Reserve University,Pomona,United States","Case Western Reserve University, Pomona, United States"],"affiliations":[{"raw_affiliation_string":"Case Western Reserve University,Pomona,United States","institution_ids":["https://openalex.org/I58956616"]},{"raw_affiliation_string":"Case Western Reserve University, Pomona, United States","institution_ids":["https://openalex.org/I58956616"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5028527445"],"corresponding_institution_ids":["https://openalex.org/I52527943"],"apc_list":null,"apc_paid":null,"fwci":0.4409,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60047468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"272","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.995199978351593,"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/imputation","display_name":"Imputation (statistics)","score":0.8348170518875122},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.6850342750549316},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.6044819355010986},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5948914289474487},{"id":"https://openalex.org/keywords/genetic-distance","display_name":"Genetic distance","score":0.4603893458843231},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.43359240889549255},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4320961534976959},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4294770359992981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39061838388442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3757908344268799},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3324521780014038},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.33019715547561646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3290126323699951},{"id":"https://openalex.org/keywords/genetic-variation","display_name":"Genetic variation","score":0.2593359053134918},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2093978226184845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20604297518730164}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.8348170518875122},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.6850342750549316},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.6044819355010986},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5948914289474487},{"id":"https://openalex.org/C138592617","wikidata":"https://www.wikidata.org/wiki/Q748695","display_name":"Genetic distance","level":4,"score":0.4603893458843231},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.43359240889549255},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4320961534976959},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4294770359992981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39061838388442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3757908344268799},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3324521780014038},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33019715547561646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3290126323699951},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.2593359053134918},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2093978226184845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20604297518730164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc55196.2022.9952611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc55196.2022.9952611","pdf_url":null,"source":{"id":"https://openalex.org/S4363607740","display_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1533198000","https://openalex.org/W1707927426","https://openalex.org/W2023161567","https://openalex.org/W2067914026","https://openalex.org/W2096555119","https://openalex.org/W2096863518","https://openalex.org/W2100908666","https://openalex.org/W2133403068","https://openalex.org/W2153464644","https://openalex.org/W2520945469","https://openalex.org/W2559028527","https://openalex.org/W2948115951","https://openalex.org/W3156655518","https://openalex.org/W3174467356","https://openalex.org/W3197003309","https://openalex.org/W6637591177"],"related_works":["https://openalex.org/W2181530120","https://openalex.org/W4211215373","https://openalex.org/W2024529227","https://openalex.org/W2055961818","https://openalex.org/W1574575415","https://openalex.org/W3144172081","https://openalex.org/W3179858851","https://openalex.org/W3028371478","https://openalex.org/W2081476516","https://openalex.org/W2581984549"],"abstract_inverted_index":{"With":[0],"several":[1],"new":[2],"genome":[3],"sequencing":[4],"methods":[5],"such":[6],"as":[7,36],"Next":[8],"Generation":[9],"Sequencing":[10],"(NGS)":[11],"and":[12,27,99,140,158,181],"nanopore":[13],"technologies,":[14],"there":[15],"exists":[16],"a":[17,152,160],"wide":[18],"range":[19],"of":[20,126,155,163,177,216,238],"techniques":[21],"to":[22,43,56,72,77,88,173,205,222],"explore":[23],"different":[24],"genetic":[25],"variants":[26],"their":[28],"impacts.":[29],"However,":[30],"these":[31,49],"sequences":[32,215],"can":[33],"become":[34],"degraded":[35],"some":[37,73],"genotypes":[38],"are":[39],"not":[40],"detected,":[41],"leading":[42],"missing":[44,81,146,164,210],"base":[45],"pair":[46],"values.":[47],"Imputing":[48],"gaps":[50],"in":[51,83,115,120,133,167,186,212],"the":[52,58,80,95,104,127,134,145,168,174,187,191,213,234],"data":[53,59,125],"is":[54],"essential":[55],"analyze":[57],"properly.":[60],"Some":[61],"past":[62],"studies":[63],"have":[64],"shown":[65],"that":[66,197],"certain":[67],"machine":[68],"learning":[69],"models":[70],"have,":[71],"extent,":[74],"been":[75],"able":[76,204],"accurately":[78],"impute":[79],"values":[82],"genotypes.":[84],"This":[85,107],"paper":[86],"aims":[87],"outline":[89],"an":[90,227],"imputation":[91],"approach":[92,108],"created":[93],"using":[94,124,190,198],"K-Nearest":[96],"Neighbors":[97],"algorithm":[98],"Levenshtein":[100,192],"Distance":[101],"parameters":[102],"on":[103],"Mus":[105,121,138,141,171,217],"genus.":[106],"involved":[109],"imputing":[110],"randomly":[111],"masked":[112],"nucleotide":[113,165],"bases":[114,156,166,178,211],"any":[116],"given":[117,161],"gene":[118,214],"sequence":[119,162],"musculus":[122,218],"by":[123,150],"same":[128,175],"genes":[129],"from":[130],"similar":[131,188],"species":[132,189],"Phylogenetic":[135],"tree,":[136],"namely":[137],"pahari":[139],"caroli.":[142],"Predictions":[143],"for":[144],"spaces":[147,236],"were":[148,203,242],"generated":[149],"comparing":[151],"set":[153],"number":[154,176],"before":[157,180],"after":[159,182],"target":[169],"species,":[170],"musculus,":[172],"occurring":[179],"every":[183],"possible":[184],"prediction":[185],"distance":[193],"metric.":[194],"We":[195],"found":[196],"our":[199],"proposed":[200],"algorithm,":[201],"we":[202],"predict":[206],"over":[207],"500,000":[208],"individual":[209],"with":[219],"accuracies":[220],"up":[221],"87%.":[223],"The":[224],"model":[225],"maintained":[226],"accuracy":[228],"greater":[229],"than":[230,244],"80%":[231],"when":[232],"all":[233],"blank":[235,240],"(sequences":[237],"consecutive":[239],"spaces)":[241],"less":[243],"200":[245],"characters":[246],"long.":[247]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}