Figure 1.

ROC curves containing 95% confidence intervals for different deep learning models on the S sites of the training dataset P.ELM, 10-fold cross validation was used. Area Under Curve (AUC) is defined as the area under the ROC curve to measure the performance of the model. (a) ROC curve of the TransPhos model; (b) ROC curve of the Convolution neural network (CNN) model. (c) ROC curve of the Long and short term memory network (LSTM) model. (d) ROC curve of the Recurrent Neural Networks (RNN) model. (e) ROC curve of the Fully connected neural networks (FCNN) model. (f) Performance comparison on the S sites of the P.ELM dataset.