Fig. 5: Performance comparison of alternative methods for prediction of four blood lipid traits (GLGC-training and UKBB-tuning/validation).
From: An ensemble penalized regression method for multi-ancestry polygenic risk prediction
We analyzed four blood lipid traits, a HDL, b LDL, c logTG, and d TC. PRS are trained using GLGC data that available for five populations: admixed African or African, East Asian, European, Hispanic, and South, and then tuned in individuals from UKBB of the corresponding ancestry: AFR, EAS, EUR, AMR, and SAS (see “Real data analysis” under “Methods” for ancestry composition). Performance is reported based on adjusted R2 accounting for sex, age, PC1-10 in a held-out validation sample of individuals from UKBB of the corresponding ancestry. Sample sizes for training, tuning and validation data are in Supplementary Data 7 and 8. Results for AMR are not included due to the small sample size of genetically inferred AMR ancestry individuals in UKBB. The PRS-CSx package is restricted to SNPs from HM3, whereas other alternative methods use SNPs from either HM3 or MEGA. Bars in the figure show the performance of adjusted R2 for each method in each dataset. Colors are described on the right side of the figure. Source data are provided in Supplementary Data 11.
