Splice site detection with neural networks/Markov model hybrids

Splice sites play a very important role for identification of coding regions from DNA sequences of eukaryotic genomes. The paper proposes a novelty machine learning approach to the detection of splice site location in DNA sequences. The method is based on a hybrid of a Markov model and neural networks where parameters of the Markov model are learned by neural networks. Our proposed model is trained using a backpropagation algorithm. The experiments in the data set of Rogic show that this model performs well that 86% of acceptor sites and 89% of donor sites are correctly found. These results demonstrate the potential use of our approach.