Fig. 4: The predicted AUC by PRStuning and the actual AUC on testing data for four diseases with PRS models built from P+T, C+T, LDpred, and LDpred2 using different parameters. | Nature Communications

Fig. 4: The predicted AUC by PRStuning and the actual AUC on testing data for four diseases with PRS models built from P+T, C+T, LDpred, and LDpred2 using different parameters.

From: Tuning parameters for polygenic risk score methods using GWAS summary statistics from training data

Fig. 4

The four panels present the results of P+T, C+T, LDpred, and LDpred2, respectively. The dotted and solid horizontal lines refer to the highest AUC for PRStuning and testing data. The overall patterns of AUC predicted by PRStuning and calculated from testing data across different parameter values were similar. Detailed AUC values for different methods and tuning parameters are summarized in Supplementary Table 2. Source data are provided as a Source Data file.

Back to article page