View article

To understand the structure-to-function relationship, life sciences researchers and biologists need to retrieve similar structures from protein databases and classify them into the same protein fold. With the technology innovation, the number of protein structures increases every day, so, retrieving structurally similar proteins using current algorithms may take hours or even days. Therefore, improving the efficiency of protein structure retrieval becomes an important research issue. In this paper, we propose three novel approaches for retrieving protein 3D structures, which rely on the 3D structure of the proteins. In the first approach, Discrete Fourier Transform is applied to protein structures. Additionally, some properties of the primary and secondary structure of the protein are taken. In the second approach, some modification of the ray based descriptor is applied on the backbone of the protein molecule. In the third approach, some wavelet transformations are applied on the distance matrix of the protein. We have compared our approaches with several existing approaches. Generally, our approaches give higher precision than existing approaches that where used in this research. The results show that the proposed ray based descriptor gives the best average retrieval accuracy (92.95%), while it is much simpler and faster than the other approaches.