Efficient Approaches for Retrieving Protein Tertiary Structures

Abstract

The 3D conformation of a protein in the space is the main factor which determines its function in living organisms. Due to the huge amount of newly discovered proteins, there is a need for fast and accurate computational methods for retrieving protein structures. Their purpose is to speed up the process of understanding the structure-to-function relationship which is crucial in the development of new drugs. There are many algorithms addressing the problem of protein structure retrieval. In this paper, we present several novel approaches for retrieving protein tertiary structures. We present our voxel-based descriptor. Then we present our protein ray-based descriptors which are applied on the interpolated protein backbone. We introduce five novel wavelet descriptors which perform wavelet transforms on the protein distance matrix. We also propose an efficient algorithm for distance matrix alignment named Matrix Alignment by Sequence Alignment within Sliding Window (MASASW), which has shown as much faster than DALI, CE, and MatAlign. We compared our approaches between themselves and with several existing algorithms, and they generally prove to be fast and accurate. MASASW achieves the highest accuracy. The ray and wavelet-based descriptors as well as MASASW are more accurate than CE.

iProStruct2D: Identifying protein structural classes by deep learning via 2D representations

“…Zhou, Chou, & Wong, 2006). Some noteworthy global approaches include the work in (Mirceva et al, 2012) where wavelet-based protein descriptors are proposed, the work in (Sael et al, 2008) where the 3D geometrical surface of the protein structures are represented by 3D Zernike descriptors, and the approaches proposed in (Harder et al, 2012) where Gauss integral vectors are extracted from protein structures represented as open curves.…”

Structural Protein Function Prediction - A Comprehensive Review

“…Some limitations of distance matrix are its sensitivity to the parameters and its high dimensionality. Wavelets were proposed to reduce the distance matrix dimensionality [60] and extract features [61]. Marsolo and Ramamohanarao [60] reduce the dimensionality of protein structure by generating a feature vector of approximation coefficients by applying 2-dimensional wavelet decomposition of the distance matrix which allows fast retrieval of similar structures.…”

“…An average accuracy of 87% was achieved at SCOP superfamily level using a k-d tree and a 10-nearest-neighbor on a dataset consists of 33,000 proteins. Recently, Mirceva et al [61] performed different wavelet transforms on the protein distance matrix and found that Daubechies2 wavelet gives the highest retrieval accuracy of 91.3%.…”

Dynamic Programming Used to Align Protein Structures with a Spectrum Is Robust

“…Over the last couple of years, there have been several publications that have promoted fast algorithms for database-wide comparisons [1,8,9,10] (see the related work in [11,12,13,14,15,16,17,18,19]). These algorithms are designed to efficiently discern if two proteins share a similar molecular structure.…”