Fig. 5

Collective inference with SNP selection based on independent-SNP p-values. a AUC with varying penalizer λ under PL inference, where independent-SNP p-value cutoff p _c indicated was used to filter SNPs from the full genome-wide set in each cross-validation run. The mean SNP number \({\bar m}\) is the average over 5 runs. b AUC optimized over regularization (MF) with varying model sizes controlled by p _c . SNP selections were made from the full genome-wide data (r ²<1.0) and subsets generated by pruning based on LD thresholds indicated. Note that the maximum AUC position shifts to lower \({\bar m}\) with increasing degree of pruning (fewer SNPs with LD needed to account for association) and that an optimal level of pruning (r ²<0.5) exists for highest performance. Vertical lines are 95 % C.I