A prior knowledge of protein structural class can provide useful information about its overall structure. So, it is
vitally important to develop a computational prediction method for fast and accurately determining the protein structural
class. In this paper, a dual-layer wavelet support vector machine (WSVM) is presented via the general form of Chou’s
pseudo amino acid composition, which is featured by introducing wavelet as a kernel and making decisions by the fusion
from three individual classifiers. As a demonstration, the rigorous jackknife cross-validation tests were performed on two
benchmark datasets, including the more challenging 25PDB dataset. Our success rates were reliable, and it has not escaped
from our notice that the present method has specific ability to predict the most difficult case of α+β class. The program
developed can be acquired freely on request from the authors.