Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network

Fig. 2

The REDfold architecture. a The learning network schematic, including feature extraction and encoder-decoder network. The RNA sequence is first transformed into an input conformation, and then fed into the deep neural network. Based on the extracted feature map, the encoder-decoder network outputs a score map for the secondary structure prediction. b Dense Connected Module (DCM). The DCM is a series of BCM layers and densely connected between layers. The output feature map concatenates all feature maps from the BCM layers and the output feature map in the encoder network includes the input feature map. Each layer receives all feature maps from the preceding layers to improve the network parameter efficiency

Back to article page