Skip to main content

Table 3 The hyper-parameters of the proposed deep architecture

From: Large-scale prediction of protein ubiquitination sites using a multimodal deep architecture

Subnet Layer Hyper-parameters
Activation function Sizec Filters Drop-out
One hot vector 1D Convolution softsign 2 200 0.4
softsign 3 150 0.4
softsign 5 150 0.4
softsign 7 100 0.4
Densea relu 256 0.3
relu 128 0
relu 128
Phsico- chemical properties Dense softplus 1024 0.2
softplus 512 0.4
softplus 256 0.5
relu 128
PSSM profile 1D Convolution relu 1 200 0.5
relu 8 150 0.5
relu 9 200 0.5
1D Convolutionb relu 1 200 0.5
relu 3 150 0.5
relu 7 200 0.5
Dense relu 128 0.3
relu 128 0
Merged representations Dense softmax 2 0
  1. aDense layers represent for the fully connected layers in keras
  2. bThe layers were designed for trans-positioned PSSM profile
  3. cThe size of convolution layers means the kernel sizes, and the size of Dense layers denotes the number of hidden states