We first performed simulations to demonstrate AnnoPred’s ability to improve risk prediction accuracy. We compared AnnoPred with four popular PRS approaches (Methods), including PRS based on genome-wide significant SNPs (PRSsig), PRS based on all SNPs in the dataset (PRSall), PRS based on tuned cutoffs for p-values and LD pruning (PRSP+T), and recently proposed LDpred [10]. Mean correlations between simulated and predicted traits were calculated from 100 replicates under different simulation settings (Methods). AnnoPred showed the best prediction performance in all settings when the causal SNPs are highly enriched in annotated regions (Table 1, S2 Table and S2 Fig). In general, performance of PRSsig, PRSP+T, LDpred, and AnnoPred all improved under a sparser genetic model and higher trait heritability. PRSall showed comparable performance between sparse and polygenic models but its prediction accuracy was consistently worse than other methods. Sample size in the training set was also crucial for risk prediction accuracy. Increasing sample size could lead to continuous improvement in prediction accuracy under different settings (Fig 1).
