Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: miTAR: a hybrid deep learning-based approach for predicting miRNA targets

Fig. 1

Overview of the proposed DL-based approach for predicting miRNA targets. As inputs of the approach, miRNA sequences and gene sequences are padded separately and then concatenated directly. The approach contains one embedding, CNN, Max pooling, and BiRNN layer, and two dense layers. To prevent overfitting, a dropout is added following CNN, Max pooling, BiRNN and between the two Dense layers

Back to article page