{"id":"https://openalex.org/W3111120365","doi":"https://doi.org/10.1109/cibcb48159.2020.9277703","title":"Phenotype Prediction of DNA Sequence Data: A Machine- and Statistical Learning Approach","display_name":"Phenotype Prediction of DNA Sequence Data: A Machine- and Statistical Learning Approach","publication_year":2020,"publication_date":"2020-10-27","ids":{"openalex":"https://openalex.org/W3111120365","doi":"https://doi.org/10.1109/cibcb48159.2020.9277703","mag":"3111120365"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb48159.2020.9277703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb48159.2020.9277703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","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/A5070959315","display_name":"Darlington Mapiye","orcid":"https://orcid.org/0000-0001-8403-8783"},"institutions":[{"id":"https://openalex.org/I4210162937","display_name":"IBM Research - Africa","ror":"https://ror.org/05c0m9m16","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210162937"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Darlington Mapiye","raw_affiliation_strings":["IBM Research, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"IBM Research, Johannesburg, South Africa","institution_ids":["https://openalex.org/I4210162937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033666817","display_name":"Mpho Mokoatle","orcid":"https://orcid.org/0000-0001-7689-2840"},"institutions":[{"id":"https://openalex.org/I4210162937","display_name":"IBM Research - Africa","ror":"https://ror.org/05c0m9m16","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210162937"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Mpho Mokoatle","raw_affiliation_strings":["IBM Research, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"IBM Research, Johannesburg, South Africa","institution_ids":["https://openalex.org/I4210162937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055041649","display_name":"Dineo Makoro","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162937","display_name":"IBM Research - Africa","ror":"https://ror.org/05c0m9m16","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210162937"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Dineo Makoro","raw_affiliation_strings":["IBM Research, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"IBM Research, Johannesburg, South Africa","institution_ids":["https://openalex.org/I4210162937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083071710","display_name":"St\u00e9phanie Muller","orcid":"https://orcid.org/0000-0003-3997-4446"},"institutions":[{"id":"https://openalex.org/I4210162937","display_name":"IBM Research - Africa","ror":"https://ror.org/05c0m9m16","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210162937"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Stephanie J. Muller","raw_affiliation_strings":["IBM Research, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"IBM Research, Johannesburg, South Africa","institution_ids":["https://openalex.org/I4210162937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044728608","display_name":"Gciniwe Dlamini","orcid":"https://orcid.org/0000-0002-8926-5595"},"institutions":[{"id":"https://openalex.org/I4210162937","display_name":"IBM Research - Africa","ror":"https://ror.org/05c0m9m16","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210162937"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Gciniwe S. Dlamini","raw_affiliation_strings":["IBM Research, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"IBM Research, Johannesburg, South Africa","institution_ids":["https://openalex.org/I4210162937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002170551","display_name":"James Mashiyane","orcid":"https://orcid.org/0000-0001-6602-8936"},"institutions":[{"id":"https://openalex.org/I4210162937","display_name":"IBM Research - Africa","ror":"https://ror.org/05c0m9m16","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210162937"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"James Mashiyane","raw_affiliation_strings":["IBM Research, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"IBM Research, Johannesburg, South Africa","institution_ids":["https://openalex.org/I4210162937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002276235","display_name":"Lavina Joseph","orcid":null},"institutions":[{"id":"https://openalex.org/I4387155312","display_name":"National Institute for Communicable Diseases","ror":"https://ror.org/007wwmx82","country_code":null,"type":"government","lineage":["https://openalex.org/I4387155312"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Lavina Joseph","raw_affiliation_strings":["The national institute for communicable diseases (NICD), Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"The national institute for communicable diseases (NICD), Johannesburg, South Africa","institution_ids":["https://openalex.org/I4387155312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022980689","display_name":"Nazir Ismail","orcid":"https://orcid.org/0000-0001-7696-3776"},"institutions":[{"id":"https://openalex.org/I4387155312","display_name":"National Institute for Communicable Diseases","ror":"https://ror.org/007wwmx82","country_code":null,"type":"government","lineage":["https://openalex.org/I4387155312"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Nazir Ismail","raw_affiliation_strings":["The national institute for communicable diseases (NICD), Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"The national institute for communicable diseases (NICD), Johannesburg, South Africa","institution_ids":["https://openalex.org/I4387155312"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071986018","display_name":"Shaheed Vally Omar","orcid":"https://orcid.org/0000-0001-6983-1636"},"institutions":[{"id":"https://openalex.org/I4387155312","display_name":"National Institute for Communicable Diseases","ror":"https://ror.org/007wwmx82","country_code":null,"type":"government","lineage":["https://openalex.org/I4387155312"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Shaheed Vally Omar","raw_affiliation_strings":["The national institute for communicable diseases (NICD), Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"The national institute for communicable diseases (NICD), Johannesburg, South Africa","institution_ids":["https://openalex.org/I4387155312"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5070959315"],"corresponding_institution_ids":["https://openalex.org/I4210162937"],"apc_list":null,"apc_paid":null,"fwci":0.1657,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50854636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"19","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","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/T12946","display_name":"Fractal and DNA sequence analysis","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":0.9970999956130981,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.6588868498802185},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6116483807563782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.558411180973053},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.45252883434295654},{"id":"https://openalex.org/keywords/phenotype","display_name":"Phenotype","score":0.43351370096206665},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.42399269342422485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41275620460510254},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.37577202916145325},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.36490529775619507},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1522561013698578},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11677902936935425},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10474744439125061}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6588868498802185},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6116483807563782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.558411180973053},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.45252883434295654},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.43351370096206665},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.42399269342422485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41275620460510254},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37577202916145325},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.36490529775619507},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1522561013698578},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11677902936935425},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10474744439125061}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cibcb48159.2020.9277703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb48159.2020.9277703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W1863711781","https://openalex.org/W1903088142","https://openalex.org/W1916589227","https://openalex.org/W1991754655","https://openalex.org/W1995808663","https://openalex.org/W1997102766","https://openalex.org/W2003347102","https://openalex.org/W2016017944","https://openalex.org/W2022986961","https://openalex.org/W2049345312","https://openalex.org/W2050820276","https://openalex.org/W2064675550","https://openalex.org/W2067657601","https://openalex.org/W2068721890","https://openalex.org/W2079735306","https://openalex.org/W2100161431","https://openalex.org/W2103441770","https://openalex.org/W2104422209","https://openalex.org/W2116261113","https://openalex.org/W2119562006","https://openalex.org/W2134751812","https://openalex.org/W2150600032","https://openalex.org/W2150774511","https://openalex.org/W2155368965","https://openalex.org/W2159954944","https://openalex.org/W2170951896","https://openalex.org/W2171963266","https://openalex.org/W2175402905","https://openalex.org/W2187089797","https://openalex.org/W2253535400","https://openalex.org/W2264881821","https://openalex.org/W2268029186","https://openalex.org/W2272721999","https://openalex.org/W2309415944","https://openalex.org/W2337747100","https://openalex.org/W2343416635","https://openalex.org/W2430356171","https://openalex.org/W2521268641","https://openalex.org/W2523414064","https://openalex.org/W2549052009","https://openalex.org/W2559133556","https://openalex.org/W2560296314","https://openalex.org/W2587097375","https://openalex.org/W2598104261","https://openalex.org/W2605595174","https://openalex.org/W2611595334","https://openalex.org/W2620760558","https://openalex.org/W2726481934","https://openalex.org/W2743945814","https://openalex.org/W2767106145","https://openalex.org/W2771835478","https://openalex.org/W2794746716","https://openalex.org/W2855293443","https://openalex.org/W2890343433","https://openalex.org/W2898604559","https://openalex.org/W2901155787","https://openalex.org/W2917077245","https://openalex.org/W2917821234","https://openalex.org/W2919121574","https://openalex.org/W2949839865","https://openalex.org/W2950657048","https://openalex.org/W2952342008","https://openalex.org/W2958994046","https://openalex.org/W2962807110","https://openalex.org/W2963026768","https://openalex.org/W2963042606","https://openalex.org/W2963355447","https://openalex.org/W2970734239","https://openalex.org/W3000276226","https://openalex.org/W4247053599","https://openalex.org/W4299286960","https://openalex.org/W4299838440","https://openalex.org/W6640218462","https://openalex.org/W6685537299","https://openalex.org/W6691951137","https://openalex.org/W6692935382","https://openalex.org/W6693001639","https://openalex.org/W6698540767","https://openalex.org/W6742632731","https://openalex.org/W6772863202"],"related_works":["https://openalex.org/W1840542775","https://openalex.org/W2416830231","https://openalex.org/W179926425","https://openalex.org/W3003578468","https://openalex.org/W2336657400","https://openalex.org/W1483913375","https://openalex.org/W2088351705","https://openalex.org/W2086883243","https://openalex.org/W2551532359","https://openalex.org/W2146607527"],"abstract_inverted_index":{"Advancements":[0],"made":[1],"in":[2,49,185,238],"high-throughput":[3],"sequencing":[4,13,104,114,268],"technologies":[5],"have":[6],"continued":[7],"to":[8,74,136,155,210,292,324],"generate":[9],"large":[10],"amounts":[11],"of":[12,19,32,62,78,96,110,118,132,141,150,169,233,250,287,314],"data":[14,25,52,64,99,168,183,330],"enabling":[15],"the":[16,60,76,124,139,162,175,214,220,285,289,299,318],"holistic":[17],"investigation":[18],"complex":[20,340],"biological":[21,341],"phenomena.":[22],"Genomic":[23],"sequence":[24,51,98,143,167,182],"are":[26,191,336],"used":[27,209],"for":[28,59,90,264,278,338],"a":[29,54,84,107,116,119,170,230,261,272,321],"wide":[30],"range":[31],"applications":[33],"such":[34,307],"as":[35,69,71,219,308],"gene":[36],"annotations,":[37],"expression":[38],"studies,":[39],"personalized":[40],"treatment":[41],"and":[42,66,86,152,159,188,213,246,255,275,310,312,331],"precision":[43],"medicine.":[44],"However,":[45],"this":[46,82,239],"rapid":[47],"expansion":[48],"available":[50],"poses":[53],"tremendous":[55],"computational":[56],"challenge,":[57],"calling":[58],"development":[61],"novel":[63],"processing":[65,309],"analytic":[67],"methods,":[68],"well":[70],"computing":[72,176,305],"resources":[73,306],"match":[75],"volume":[77],"these":[79],"datasets.":[80],"In":[81],"work,":[83],"machine-":[85],"statistical":[87],"learning":[88],"approach":[89,125,263],"classification":[91,157,227,277,315],"based":[92],"on":[93,106],"k-mer":[94,221,231,236,273,290],"representations":[95],"DNA":[97],"is":[100,126],"proposed.":[101],"While":[102],"targeted":[103],"focuses":[105],"specific":[108],"region":[109],"interest,":[111],"whole":[112,129,165,180,266],"genome":[113,130,166,181,267],"enables":[115],"view":[117],"species'":[120],"entire":[121],"genome.":[122],"Thus,":[123],"tested":[127],"using":[128,197],"sequences":[131],"Mycobacterium":[133,199],"tuberculosis":[134,200],"isolates":[135],"(i)":[137],"reduce":[138],"size":[140,149,222,232,291],"genomic":[142,329],"data,":[144,269],"(ii)":[145],"identify":[146,332],"an":[147,241],"optimum":[148],"k-mers":[151,206],"utilize":[153],"it":[154],"build":[156],"models,":[158],"(iii)":[160],"predict":[161],"phenotype":[163,279,333],"from":[164,328],"given":[171],"bacterial":[172],"isolate.":[173],"Furthermore,":[174,317],"challenges":[177],"associated":[178],"with":[179],"analyses":[184,203],"producing":[186],"interpretable":[187],"explainable":[189,296],"insights":[190],"described.":[192],"Classification":[193],"models":[194],"were":[195],"trained":[196],"104":[198],"isolates.":[201],"Cluster":[202],"showed":[204],"that":[205,301],"can":[207],"be":[208],"discriminate":[211],"phenotypes":[212],"discrimination":[215],"becomes":[216],"more":[217,294],"concise":[218],"increases.":[223],"The":[224,281],"best":[225],"performing":[226,276],"model":[228],"had":[229],"10":[234],"(longest":[235],"considered":[237],"study)":[240],"accuracy,":[242,304],"recall,":[243],"precision,":[244],"specificity,":[245],"Matthews":[247],"Correlation":[248],"coefficient":[249],"72.0%,":[251],"80.5%,":[252,253],"63.6%,":[254],"0.4,":[256],"respectively.":[257],"This":[258],"study":[259],"provides":[260,320],"comprehensive":[262],"resampling":[265],"objectively":[270],"selecting":[271],"size,":[274],"prediction.":[280],"analysis":[282,319],"also":[283],"highlights":[284],"importance":[286],"increasing":[288],"produce":[293],"biologically":[295],"results,":[297],"highlighting":[298],"interplay":[300],"exists":[302],"between":[303],"memory,":[311],"explainability":[313],"results.":[316],"new":[322],"way":[323],"extract":[325],"genetic":[326],"information":[327],"relationships":[334],"which":[335],"integral":[337],"explaining":[339],"mechanisms.":[342]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}