Fig. 2
From: GCNCPR-ACPs: a novel graph convolution network method for ACPs prediction
The overview of the GCNCPR-ACPs predictor. Step 1, data construction: the ACP datasets are prepared to obtain the training and test datasets. Step 2, graph construction: the ACPs chains are used to construct the graphs using the amino acids as nodes. Step 3, GCNCPR model: the graph data is used as input for the GCNCPR model and to classify the ACP chain. Step 4, model evaluation: the classification results of our model are evaluated and compared with those of the other models