Learning to predict reading frames in E. coli DNA sequences

Two fundamental problems in analyzing DNA sequences are (1) locating the regions of a DNA sequence that encode proteins, and (2) determining the reading frame for each region. The authors investigate using artificial neural networks (ANNs) to find coding regions, determine reading frames, and detect frameshift errors in E. coli DNA sequences. They describe the adaptation of the approach used by E.C. Uberbacher and R.J. Mural (1991) to identify coding regions in human DNA, and compare the performance of ANNs to several conventional methods for predicting reading frames. The experiments demonstrated that ANNs can outperform these conventional approaches.