{"doi":"10.1101/2020.08.11.243840","title":"Genetic-substructure and complex demographic history of South African Bantu speakers","abstract":"Abstract South Eastern Bantu-speaking (SEB) groups constitute more than 80% of the population in South Africa. Despite clear linguistic and geographic diversity, the genetic differences between these groups have not been systematically investigated. Based on genome-wide data of over 5000 individuals, representing eight major SEB groups, we provide strong evidence for fine-scale population structure that broadly aligns with geographic distribution and is also congruent with linguistic phylogeny (separation of Nguni, Sotho-Tswana and Tsonga speakers). Although differential Khoe-San admixture plays a key role, the structure persists after Khoe-San ancestry-masking. The timing of admixture, levels of sex-biased gene flow and population size dynamics also highlight differences in the demographic histories of individual groups. The comparisons with five Iron Age farmer genomes further support genetic continuity over ∼400 years in certain regions of the country. Simulated trait genome-wide association studies further show that the observed population structure could have major implications for biomedical genomics research in South Africa.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2020,"id":118655,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":50,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9231,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":231110,"name":"Ananyo Choudhury","orcid":"0000-0001-8225-9531","position":1,"is_corresponding":false},{"id":551721,"name":"Cesar Fortes‐Lima","orcid":"0000-0002-9310-5009","position":2,"is_corresponding":false},{"id":231111,"name":"Shaun Aron","orcid":"0000-0001-6200-0485","position":3,"is_corresponding":false},{"id":551722,"name":"Gavin Whitelaw","orcid":"0000-0003-1638-7222","position":4,"is_corresponding":false},{"id":551723,"name":"Koen Bostoen","orcid":"0000-0003-2284-6165","position":5,"is_corresponding":false},{"id":551724,"name":"Hilde Gunnink","orcid":"0000-0002-5508-8156","position":6,"is_corresponding":false},{"id":551725,"name":"Natalia Chousou‐Polydouri","orcid":"0000-0002-5693-975X","position":7,"is_corresponding":false},{"id":553003,"name":"Peter Delius","orcid":null,"position":8,"is_corresponding":false},{"id":443314,"name":"Stephen Tollman","orcid":"0000-0003-0744-7588","position":9,"is_corresponding":false},{"id":553004,"name":"Fresia Casas","orcid":null,"position":10,"is_corresponding":false},{"id":298901,"name":"Shane A. Norris","orcid":"0000-0001-7124-3788","position":11,"is_corresponding":false},{"id":436152,"name":"Felistas Mashinya","orcid":"0000-0002-4132-7558","position":12,"is_corresponding":false},{"id":436153,"name":"Marianne Alberts","orcid":"0000-0002-7628-8560","position":13,"is_corresponding":false},{"id":231123,"name":"Scott Hazelhurst","orcid":"0000-0002-0581-149X","position":14,"is_corresponding":false},{"id":275413,"name":"Carina M. Schlebusch","orcid":"0000-0002-8160-9621","position":15,"is_corresponding":false},{"id":231133,"name":"Michèle Ramsay","orcid":"0000-0002-4156-4801","position":16,"is_corresponding":false},{"id":231112,"name":"Dhriti Sengupta","orcid":"0000-0001-6315-7804","position":0,"is_corresponding":true}],"reference_count":68,"raw_metadata":null,"created_at":"2026-07-18T23:14:03.409507Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}