Skip to main content
Figure 6 | BMC Bioinformatics

Figure 6

From: Transmembrane helix prediction using amino acid property features and latent semantic analysis

Figure 6

Neural network architecture used for transmembrane feature classification: The neural network has an input layer with 4 nodes that take each of the 4 dimensions of the feature vectors as input. The output layer has 1 tansig neuron that fires a value between -1 and +1 corresponding to non-transmembrane and transmembrane respectively. There is a hidden layer between input and output layers consisting of 4 neurons. The network is connected fully in the forward direction.

Back to article page