@article {Yoo600353, author = {Seong-Keun Yoo and Chang-Uk Kim and Hie Lim Kim and Sungjae Kim and Jong-Yeon Shin and Namcheol Kim and Joshua SungWoo Yang and Kwok-Wai Lo and Belong Cho and Fumihiko Matsuda and Stephan C. Schuster and Changhoon Kim and Jong-Il Kim and Jeong-Sun Seo}, title = {Whole-genome reference panel of 1,781 Northeast Asians improves imputation accuracy of rare and low-frequency variants}, elocation-id = {600353}, year = {2019}, doi = {10.1101/600353}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Genotype imputation using the reference panel is a cost-effective strategy to fill millions of missing genotypes for the purpose of various genetic analyses. Here, we present the Northeast Asian Reference Database (NARD), including whole-genome sequencing data of 1,781 individuals from Korea, Mongolia, Japan, China, and Hong Kong. NARD provides the genetic diversities of Korean (n=850) and Mongolian (n=386) ancestries that were not present in the 1000 Genomes Project Phase 3 (1KGP3). We combined and re-phased the genotypes from NARD and 1KGP3 to construct a union set of haplotypes. This approach established a robust imputation reference panel for the Northeast Asian populations, which yields the greatest imputation accuracy of rare and low-frequency variants compared with the existing panels. Also, we illustrate that NARD can potentially improve disease variant discovery by reducing pathogenic candidates. Overall, this study provides a decent reference panel for the genetic studies in Northeast Asia.}, URL = {https://www.biorxiv.org/content/early/2019/04/22/600353}, eprint = {https://www.biorxiv.org/content/early/2019/04/22/600353.full.pdf}, journal = {bioRxiv} }