Fig. 2: Performance comparison of various kcat and Km models on 10-fold unbiased datasets.
From: Robust enzyme discovery and engineering with deep learning using CataPro
a, b, and c show the PCC, SCC, and RMSE achieved by the kcat prediction models on the kcat dataset. d, e, and f show the PCC, SCC, and RMSE achieved by the Km prediction models on the Km dataset. It is worth noting that all models, including DLKcat and UniKP, were trained (or re-trained) on the 10-fold unbiased datasets for kcat and Km. In panels a-f, CataPro and CataPro+SaProt are highlighted in red, while other models are represented in blue. g Workflow of Extra Tree-based CataPro. h shows the performance of CataPro (Extra Tree) and UniKP on unbiased and biased datasets. The top two subplots in panel h display the results for the kcat dataset, while the bottom two subplots show the results for the Km dataset. In the four subplots of panel h, the performance of models on the unbiased datasets is highlighted in red, while the performance on the biased datasets is represented in blue. Source data are provided as a Source Data file.
