This work discusses the problem of forecasting the tertiary structure of a protein, based on its primary sequence. The problem is that science, with all its computing power and a set of experimental data, has not learned to build models that describe the process of protein molecule coagulation and predict the tertiary structure of a protein, based on its primary structure. However, it is wrong to assume that nothing is happening in this field of science. The regularities of folding (convolution) of the protein are known, methods for its modelling have been developed.
The mass spectrometry spectra are recognized as a screening tool for detecting discriminatory protein patterns. However, the mass spectra represent high dimensional data that have a large number of local maxima (a.k.a. peaks) which have to be analyzed; to tackle this problem we have developeda new three-step strategy. After preprocessing for classification of mass spectra, we use analgorithm clonal selection for synthesis collective binary classifiers in the form of wavelet-neural networks.