@article{79ab6ddc298448fea5108600de87af1c,
title = "Assembly of a pan-genome from deep sequencing of 910 humans of African descent",
abstract = "We used a deeply sequenced dataset of 910 individuals, all of African descent, to construct a set of DNA sequences that is present in these individuals but missing from the reference human genome. We aligned 1.19 trillion reads from the 910 individuals to the reference genome (GRCh38), collected all reads that failed to align, and assembled these reads into contiguous sequences (contigs). We then compared all contigs to one another to identify a set of unique sequences representing regions of the African pan-genome missing from the reference genome. Our analysis revealed 296,485,284 bp in 125,715 distinct contigs present in the populations of African descent, demonstrating that the African pan-genome contains ~10% more DNA than the current human reference genome. Although the functional significance of nearly all of this sequence is unknown, 387 of the novel contigs fall within 315 distinct protein-coding genes, and the rest appear to be intergenic.",
author = "Sherman, {Rachel M.} and Juliet Forman and Valentin Antonescu and Daniela Puiu and Michelle Daya and Nicholas Rafaels and Boorgula, {Meher Preethi} and Sameer Chavan and Candelaria Vergara and Ortega, {Victor E.} and Levin, {Albert M.} and Celeste Eng and Maria Yazdanbakhsh and Wilson, {James G.} and Javier Marrugo and Lange, {Leslie A.} and Williams, {L. Keoki} and Harold Watson and Ware, {Lorraine B.} and Olopade, {Christopher O.} and Olufunmilayo Olopade and Oliveira, {Ricardo R.} and Carole Ober and Nicolae, {Dan L.} and Meyers, {Deborah A.} and Alvaro Mayorga and Jennifer Knight-Madden and Tina Hartert and Hansel, {Nadia N.} and Foreman, {Marilyn G.} and Ford, {Jean G.} and Faruque, {Mezbah U.} and Dunston, {Georgia M.} and Luis Caraballo and Burchard, {Esteban G.} and Bleecker, {Eugene R.} and Araujo, {Maria I.} and Herrera-Paz, {Edwin F.} and Monica Campbell and Cassandra Foster and Taub, {Margaret A.} and Beaty, {Terri H.} and Ingo Ruczinski and Mathias, {Rasika A.} and Barnes, {Kathleen C.} and Salzberg, {Steven L.}",
note = "Funding Information: We gratefully acknowledge the contributions of P. Maul, T. Maul, P. Levett, A. Hennis, P. M. Lashley, R. Naidu, M. Howitt, T. Roach, A. Grant, E. V. Ponte, A. A. Cruz, E. Carvalho, S. Balcer-Whaley, M. Stockton-Porter, M. Yang, D. Mej{\'i}a-Mej{\'i}a, M. Meraz, J. Nu{\~n}ez, E. F. Herrera Mej{\'i}a, T. Ferguson, D. Ashley, S. Jimenez, N. Acevedo, D. Mercado, A. Jedlicka, H. Gui, R. Torres, A. K. May, C. Gilmore, P. Minton, Q. Niu, A. Falusi, and A. Odetunde. The authors also acknowledge the support of J. J. Shannon, K. Weiss, R. Miranda and the Indians Zenues guards, U. A. Ngoa, C. Rotimi, A. Adebowale, F. J. Malveaux, and E. Reece. We thank the numerous healthcare providers, community clinics and coinvestigators who assisted in the phenotyping and collection of DNA samples, and the families and patients for generously donating DNA samples to BAGS, BIAS, BREATHE, CAG, GRAAD, HONDAS, Jackson Heart Study, REACH, SAGE II, VALID, SAPPHIRE, SARP, COPDGene, JAAS, GALA II, PGCA, AEGS, and the asthma studies in Gabon and Palenque, Colombia. Special thanks to community leaders, teachers, doctors and personnel from health centers at the Garifuna communities for organizing the medical brigades and to the medical students at Universidad Cat{\'o}lica de Honduras, Campus San Pedro y San Pablo for their participation in the fieldwork related to HONDAS; study coordinator S. Salazar, and the recruiters in SAGE and GALA: D. Alva, G. Ayala-Rodriguez, U. Burley, L. Caine, E. Castellanos, J. Colon, D. DeJesus, I. Flexas, B. Lopez, B. Lopez, L. Martos, V. Medina, J. Olivo, M. Peralta, E. Pomares, J. Quraishi, J. Rodriguez, S. Saeedi, D. Soto, A. Taveras, E. Viera, M. LeNoir, K. Meade, M. Jensen, and A. Davis; and health liaisons and public health officers of the main Conde office, A. Concei{\c c}{\~a}o, L. Quintela, I. Santos, A. Lima, B. Valber Oliveira Silva, and I. S. Araujo, and students from the Federal University of Bahia who assisted in data collection in BIAS: R. Santana, R. Barbosa, A. P. Santana, C. Barros, M. Brand{\~a}o, L. Almeida, T. Cardoso, and D. Costa. We are grateful for the support from the international state governments and universities from Honduras, Colombia, Brazil, Gabon, Nigeria, The Netherlands, Jamaica, Barbados, and the United States, who made this work possible. Funding for this study was provided in part by NIH grants R01-HL129239 (S.L.S. and K.C.B.), R01-HG006677 (S.L.S.), and R01HL104608 (K.C.B. and R.A.M.). Publisher Copyright: {\textcopyright} 2018, The Author(s).",
year = "2019",
month = jan,
day = "1",
doi = "10.1038/s41588-018-0273-y",
language = "English (US)",
volume = "51",
pages = "30--35",
journal = "Nature Genetics",
issn = "1061-4036",
publisher = "Nature Publishing Group",
number = "1",
}