Fig. 10
From: A new strategy for Cas protein recognition based on graph neural networks and SMILES encoding
Statistical analysis of the predicted scores of Model 1 and Model 2 on the independent dataset. (a, b) Model 1 showed moderate prediction accuracy with notable misjudgments, while Model 2 demonstrated higher accuracy and reliable identification of key samples. (c, d) In non-Cas1 protein tests, Model 1 exhibited moderate specificity with a significant false-positive rate, whereas Model 2 achieved high specificity and lower false-positive scores, confirming its enhanced recognition capability.
