Skip to main content
. 2023 Jan 26;41(8):1117–1129. doi: 10.1038/s41587-022-01624-4

Fig. 4. Performance of two-helix design model.

Fig. 4

a, Training and validation accuracy during pretraining step. b, Training and validation accuracy during fine-tuning step. c, Helix sequence reconstruction accuracy with different numbers of masked residues. d, Comparison of differences between predicted and real selection logos using the developed model and ZFPred based on the mean-square error (MSE) of predicted position weight matricies (PWMs) to ground-truth PWMs. e, Comparison of differences between predicted and real selection logos using the two-helix model and concatenated logos from the single-helix design model. f, Comparison of differences between predicted and real selection logos using the two-helix model and concatenated logos from single-helix B1H selections. g, Predicted logos, real B1H logos and concatenated single-helix B1H logos for test set sequences.