Prediction of interspecies transmission for avian influenza a virus based on BP neural network

The prediction of the transmissibility of avian influenza A viruses from birds to humans is very important for the public health. Recently, two categories of molecular patterns, which were associated with the phenotype of interspecies transmission, were found to exist among avian influenza A viruses with different subtypes. In the paper, we used the similar method based on wavelet packet decomposition to transform the viral sequences and used the energy features of viral genome as input to train BP neural network. The good results of experimentation were got to discriminate the two categories of molecular patterns. A novel method was constructed to predict the transmissibility of avian influenza A viruses.