{"id":"https://openalex.org/W7018148658","doi":null,"title":"Creating and analysing an African pan-genome","display_name":"Creating and analysing an African pan-genome","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7018148658"},"language":"en","primary_location":{"id":"pmh:oai:localhost:11427/37209","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11427/37209","pdf_url":"https://open.uct.ac.za/bitstream/11427/37209/1/thesis_hsf_2022_bourn%20jessica%20jean.pdf","source":{"id":"https://openalex.org/S4306402129","display_name":"Open University of Cape Town (University of Cape Town)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157614274","host_organization_name":"University of Cape Town","host_organization_lineage":["https://openalex.org/I157614274"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://open.uct.ac.za/bitstream/11427/37209/1/thesis_hsf_2022_bourn%20jessica%20jean.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bourn, Jessica Jean","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bourn, Jessica Jean","raw_affiliation_strings":["Division of Computational Biology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Computational Biology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9609000086784363,"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":0.9609000086784363,"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/T10751","display_name":"Forensic and Genetic Research","score":0.00989999994635582,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.004900000058114529,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/human-reference-genome","display_name":"human reference genome","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C40583040","wikidata":"https://www.wikidata.org/wiki/Q1502105","display_name":"Human genetic variation","level":5,"score":0.6935999989509583},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5375000238418579},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C81977670","wikidata":"https://www.wikidata.org/wiki/Q585259","display_name":"Genetic diversity","level":3,"score":0.5214999914169312},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5038999915122986},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.49570000171661377},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4490000009536743},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.4374000132083893},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.39480000734329224},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3691999912261963},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C2993807623","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genetic data","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C53553401","wikidata":"https://www.wikidata.org/wiki/Q47307","display_name":"Genealogy","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C47042493","wikidata":"https://www.wikidata.org/wiki/Q265799","display_name":"Human genetics","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.263700008392334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2583000063896179},{"id":"https://openalex.org/C85721925","wikidata":"https://www.wikidata.org/wiki/Q31151","display_name":"Population genetics","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2524999976158142},{"id":"https://openalex.org/C76509639","wikidata":"https://www.wikidata.org/wiki/Q918036","display_name":"Race (biology)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:localhost:11427/37209","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11427/37209","pdf_url":"https://open.uct.ac.za/bitstream/11427/37209/1/thesis_hsf_2022_bourn%20jessica%20jean.pdf","source":{"id":"https://openalex.org/S4306402129","display_name":"Open University of Cape Town (University of Cape Town)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157614274","host_organization_name":"University of Cape Town","host_organization_lineage":["https://openalex.org/I157614274"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master Thesis"},{"id":"pmh:oai:open.uct.ac.za:11427/37209","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11427/37209","pdf_url":"https://open.uct.ac.za/bitstreams/e93d4c2f-1985-4a0a-a2c5-49b81f7efef0/download","source":{"id":"https://openalex.org/S4306402129","display_name":"Open University of Cape Town (University of Cape Town)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157614274","host_organization_name":"University of Cape Town","host_organization_lineage":["https://openalex.org/I157614274"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master Thesis"}],"best_oa_location":{"id":"pmh:oai:localhost:11427/37209","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11427/37209","pdf_url":"https://open.uct.ac.za/bitstream/11427/37209/1/thesis_hsf_2022_bourn%20jessica%20jean.pdf","source":{"id":"https://openalex.org/S4306402129","display_name":"Open University of Cape Town (University of Cape Town)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157614274","host_organization_name":"University of Cape Town","host_organization_lineage":["https://openalex.org/I157614274"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Master Thesis"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.428600013256073,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7018148658.pdf","grobid_xml":"https://content.openalex.org/works/W7018148658.grobid-xml"},"referenced_works_count":103,"referenced_works":["https://openalex.org/W1544273448","https://openalex.org/W1596936080","https://openalex.org/W1640614960","https://openalex.org/W1767772592","https://openalex.org/W1912672559","https://openalex.org/W1985423799","https://openalex.org/W1996265628","https://openalex.org/W2002732332","https://openalex.org/W2008528401","https://openalex.org/W2010380543","https://openalex.org/W2033409266","https://openalex.org/W2037331531","https://openalex.org/W2046137036","https://openalex.org/W2051317473","https://openalex.org/W2064337222","https://openalex.org/W2085755265","https://openalex.org/W2088379928","https://openalex.org/W2089668941","https://openalex.org/W2092138236","https://openalex.org/W2092513581","https://openalex.org/W2096634299","https://openalex.org/W2099642610","https://openalex.org/W2103441770","https://openalex.org/W2107164256","https://openalex.org/W2107772251","https://openalex.org/W2108108770","https://openalex.org/W2108234281","https://openalex.org/W2115501618","https://openalex.org/W2118970397","https://openalex.org/W2119180969","https://openalex.org/W2120358246","https://openalex.org/W2122707695","https://openalex.org/W2127230663","https://openalex.org/W2129316818","https://openalex.org/W2129933858","https://openalex.org/W2131271579","https://openalex.org/W2140026462","https://openalex.org/W2140869203","https://openalex.org/W2141637710","https://openalex.org/W2150933237","https://openalex.org/W2152869198","https://openalex.org/W2160969485","https://openalex.org/W2164158485","https://openalex.org/W2164773932","https://openalex.org/W2165446840","https://openalex.org/W2169766923","https://openalex.org/W2170551349","https://openalex.org/W2170747616","https://openalex.org/W2293733321","https://openalex.org/W2333116941","https://openalex.org/W2432815617","https://openalex.org/W2462549196","https://openalex.org/W2464063823","https://openalex.org/W2516720184","https://openalex.org/W2522993044","https://openalex.org/W2531587846","https://openalex.org/W2552622726","https://openalex.org/W2557610530","https://openalex.org/W2569156823","https://openalex.org/W2580314844","https://openalex.org/W2603734366","https://openalex.org/W2604017081","https://openalex.org/W2605897695","https://openalex.org/W2610508058","https://openalex.org/W2613409207","https://openalex.org/W2614266827","https://openalex.org/W2621352615","https://openalex.org/W2732431712","https://openalex.org/W2738561712","https://openalex.org/W2779603631","https://openalex.org/W2789843538","https://openalex.org/W2800550239","https://openalex.org/W2802380955","https://openalex.org/W2805084391","https://openalex.org/W2898598946","https://openalex.org/W2901214479","https://openalex.org/W2922534626","https://openalex.org/W2932671560","https://openalex.org/W2944454672","https://openalex.org/W2948024819","https://openalex.org/W2950425965","https://openalex.org/W2953263404","https://openalex.org/W2964679279","https://openalex.org/W2964989753","https://openalex.org/W2966929769","https://openalex.org/W3005228641","https://openalex.org/W3011413344","https://openalex.org/W3018825730","https://openalex.org/W3028658133","https://openalex.org/W3030496926","https://openalex.org/W3032034316","https://openalex.org/W3044927940","https://openalex.org/W3096682848","https://openalex.org/W3097237895","https://openalex.org/W3137279194","https://openalex.org/W3159082119","https://openalex.org/W3163990482","https://openalex.org/W3198690628","https://openalex.org/W4224278121","https://openalex.org/W4234344490","https://openalex.org/W4235690512","https://openalex.org/W4294012180","https://openalex.org/W4298041974"],"related_works":["https://openalex.org/W2913204776","https://openalex.org/W3005228641","https://openalex.org/W2901214479","https://openalex.org/W4402677901","https://openalex.org/W7169033406","https://openalex.org/W4308878077","https://openalex.org/W4413372900","https://openalex.org/W4224278121","https://openalex.org/W3159082119","https://openalex.org/W3198690628"],"abstract_inverted_index":{"The":[0],"human":[1,16,61,131,381,419,425,567],"reference":[2,47,69,93,109,124,199,382],"genome":[3,70,110,342,355,383,426],"is":[4,71,142,150,516],"currently":[5,555],"a":[6,104,147,151,163,274,337,345,428,601,626,652],"core":[7],"resource":[8],"for":[9,33,94,528,557,566],"understanding":[10],"the":[11,26,37,46,54,68,88,92,108,120,144,156,168,174,181,183,198,207,251,290,301,305,316,329,334,358,367,380,391,422,432,439,448,454,472,480,487,495,508,512,522,529,553,583,596,623,655],"role":[12,653],"of":[13,28,40,53,67,84,91,122,127,139,146,154,209,318,333,340,348,393,396,431,453,462,475,483,489,531,589,600,609,625,629,640,657],"genetics":[14],"in":[15,25,50,59,80,101,180,270,390,535,582,654,660],"health,":[17],"disease,":[18,81],"and":[19,21,30,135,178,185,211,216,250,253,260,264,277,323,331,352,386,401,421,436,465,526,560,598,603,620,645,647],"variation,":[20],"has":[22,48,118,505],"been":[23,113,119,258],"invaluable":[24],"development":[27],"clinical":[29],"computational":[31],"tools":[32,220],"these":[34,648],"purposes.":[35],"However,":[36,447],"limited":[38],"number":[39],"individual":[41],"genomes":[42,416],"used":[43,297,556],"to":[44,72,107,205,217,221,272,299,311,366,411,444,471,479,494,510,524,574,613],"create":[45],"resulted":[49,389],"an":[51,64,213],"underrepresentation":[52],"extensive":[55],"genetic":[56,74,176,491,513],"diversity":[57,85,177],"present":[58],"different":[60,130,418],"populations.":[62,132,446],"Since":[63],"important":[65],"use":[66,121,145],"identify":[73],"variants":[75],"that":[76,97,159,170,376,438,467,501,540,562,576],"may":[77,543,650],"be":[78,544,571],"implicated":[79],"this":[82,141,202,261,586,592],"lack":[83],"could":[86],"limit":[87],"scientific":[89],"utility":[90],"ethnic":[95],"groups":[96,189,229,363,496,617],"are":[98,160,192,580],"poorly":[99],"represented":[100,196],"it.":[102],"As":[103,304],"result,":[105],"adaptations":[106],"structure":[111],"have":[112,256],"proposed.":[114],"One":[115],"such":[116],"proposal":[117],"multiple":[123,319],"genomes,":[125],"each":[126,268,372],"which":[128,149,325,388,511],"represent":[129],"A":[133,280],"logical":[134],"highly":[136],"practical":[137],"method":[138],"achieving":[140],"through":[143],"pan-genome,":[148],"curated":[152],"collection":[153],"all":[155,457],"DNA":[157],"sequences":[158,356,375,433,442,611],"found":[161],"within":[162,197,456],"population":[164],"under":[165],"study.":[166],"Despite":[167,585],"fact":[169],"African":[171,214,226,233,236,247,302,350,408,445,605,614],"populations":[172,320],"exhibit":[173],"greatest":[175],"variation":[179,451,492,514,534],"world,":[182],"many":[184],"sometimes":[186],"ancient":[187],"ethnolinguistic":[188],"from":[190,267,379,407,417],"Africa":[191],"among":[193],"those":[194,541],"least":[195],"genome.":[200],"Consequently,":[201,521],"study":[203,262,593],"aimed":[204],"explore":[206],"feasibility":[208],"creating":[210],"analysing":[212],"pangenome,":[215],"begin":[218],"developing":[219],"achieve":[222],"this.":[223],"Several":[224],"distinct":[225],"regional":[227,361,615],"ancestral":[228,362,481,616],"\u2013":[230,255],"namely":[231],"east":[232,235],"Nilo-Saharan,":[234],"Afro-Asiatic,":[237],"far":[238],"west":[239,242],"Niger-Congo,":[240,243,245],"central":[241,246],"Bantu-speaking":[244],"rainforest":[248],"hunter-gatherer,":[249],"Khoe":[252],"San":[254],"previously":[257,637],"identified,":[259],"included":[263],"analysed":[265],"samples":[266,459],"group":[269,482],"order":[271],"assemble":[273,300],"more":[275],"inclusive":[276,604],"representative":[278],"pan-genome.":[279,303,606],"software":[281],"pipeline":[282,307,335],"developed":[283],"by":[284],"Duan":[285],"et":[286],"al.":[287],"(2019),":[288],"termed":[289],"HUman":[291],"Pan-genome":[292],"ANalysis":[293],"(HUPAN)":[294],"pipeline,":[295],"was":[296,308,364],"here":[298],"HUPAN":[306,369],"originally":[309],"designed":[310],"analyse":[312],"only":[313],"single":[314],"populations,":[315,420],"inclusion":[317],"required":[321],"modifications":[322],"improvements,":[324],"were":[326,377,384,468,618,643],"implemented":[327],"following":[328],"testing":[330],"analysis":[332,452,599],"using":[336],"smaller":[338],"dataset":[339,347,440,474],"whole":[341,354,415],"sequences.":[343,632],"Subsequently,":[344],"final":[346],"168":[349,458],"high-":[351],"medium-coverage":[353],"representing":[357],"seven":[359],"separate":[360],"submitted":[365],"adapted":[368],"pipeline.":[370],"For":[371],"group,":[373],"nucleotide":[374],"absent":[378],"assembled":[385],"extracted,":[387],"identification":[392,488],"43.37":[394],"Mbp":[395],"non-redundant":[397,627],"non-reference":[398,610,631],"genomic":[399],"sequence":[400],"31":[402],"novel":[403],"predicted":[404],"protein-coding":[405],"genes":[406],"individuals.":[409],"Alignment":[410],"other":[412],"pan-genome":[413,455,568,641,658],"sequences,":[414],"complete":[423],"telomere-to-telomere":[424],"validated":[427],"large":[429],"portion":[430],"as":[434],"nonreference":[435],"confirmed":[437],"contained":[441],"specific":[443,493,612],"gene":[449,463],"presence-absence":[450],"revealed":[460],"patterns":[461],"presence":[464],"absence":[466],"strongly":[469],"correlated":[470],"sample":[473],"origin,":[476],"rather":[477],"than":[478],"origin.":[484],"This":[485],"hindered":[486],"genuine":[490],"analysed.":[497],"Further,":[498],"it":[499],"appears":[500],"previous":[502,536],"pan-genomic":[503,537,590],"research":[504,538,569,642,659],"not":[506],"investigated":[507],"degree":[509],"identified":[515,619,644],"dataset-specific":[517],"or":[518,546],"truly":[519],"population-specific.":[520],"failure":[523],"acknowledge":[525],"account":[527],"effects":[530],"spurious":[532],"inter-dataset":[533],"indicates":[539],"analyses":[542],"incomplete":[545],"ambiguous.":[547],"This,":[548],"therefore,":[549],"calls":[550],"into":[551],"question":[552],"methods":[554,565],"pangenomic":[558],"research,":[559,591],"highlights":[561],"robust,":[563],"standardised":[564],"must":[570],"agreed":[572],"on":[573],"ensure":[575],"comprehensive":[577,602],"population-specific":[578],"pan-genomes":[579],"produced":[581],"future.":[584,661],"inherent":[587],"weakness":[588],"successfully":[594],"enabled":[595],"creation":[597],"Unique":[607],"sets":[608],"obtained,":[621],"enabling":[622],"assembly":[624],"set":[628],"pan-African":[630],"Furthermore,":[633],"certain":[634],"complex":[635],"but":[636],"unconsidered":[638],"aspects":[639],"explored,":[646],"observations":[649],"play":[651],"advancement":[656]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}