The structure diagram of CnnCrispr. The other four pre-selected models were obtained by adding some parts on the basis of this frame. Rules for setting index values for different pair, and an example of index representation for a sgRNA-DNA sequence pair. Based on index representation, the unsupervised GloVe model was used to train the embedded vectors and embed the sequence information into the new input matrix. biLSTM layer was used to capture context information in input information. CNN containing 5 layers with different kernels, scanning the above results to obtain different features. The last fully connected layers were used to obtain the final result
展开▼