Fig. 6: Enhancing high k_cat prediction through re-weighting methods and unified framework for K_m and k_cat / K_m predictions.

a The distribution of k_cat values in the k_cat dataset. All samples are divided into 50 bins. b The absolute error between experimentally measured k_cat values and predicted k_cat values of each sample. The k_cat values of all samples were predicted independently using five-fold cross-validation. c Root mean square error (RMSE) between experimentally measured k_cat values and predicted k_cat values of 149 samples with k_cat values higher than 4 (logarithm value) using various re-weighting methods and the initial UniKP. d, e RMSE, coefficient of determination (R²) between experimentally measured K_m values and predicted K_m values on K_m test set. f Scatter plot illustrating the Pearson coefficient correlation (PCC) between experimentally measured k_cat / K_m values and predicted k_cat / K_m values of UniKP for k_cat / K_m dataset (N = 910). The color gradient represents the density of data points, ranging from blue (0.02) to red (0.28). Source data are provided as a Source Data file.