The Use of Artificial Neural Networks for Automatic Analysis and Genetic Identification of Gliadin Electrophoretic Spectra in Durum Wheat

Each wheat cultivar has a characteristic spectrum of gliadins. This makes it possible to use blocks of the components of reserve proteins as genetic markers when estimating seed purity and identity. However, identification of the blocks that constitute the electrophoretic spectrum is a complicated task. For this purpose artificial neural network (ANN) technology is proposed. Using experimental data, a teaching database and testing databases have been created. ANN was shown to be highly efficient (efficiency up to 100%) expert system for deciphering the electrophoretic spectra of gliadins of durum wheat cultivars.