Fig. 2From: PUMAS: fine-tuning polygenic risk scores with GWAS summary statisticsComparison of PUMAS and repeated learning. A, C Model tuning results based on PUMAS. B, D Results of repeated learning with individual-level data as input. The proportion of causal variants was set to be 0.001 in A and B and 0.1 in C and D. The X-axis shows the log-transformed p-value thresholds. The Y-axis shows the predictive performance quantified by average R2 across four folds. Parameter α was set to be 0 in this simulation (the “Methods” section). Results for other settings are summarized in Additional file 1: Fig. S1-S9Back to article page