3D Shape Histograms for Similarity Search and Classification in Spatial Databases
SSD '99 Proceedings of the 6th International Symposium on Advances in Spatial Databases
A Multi-Level Approach to SCOP Fold Recognition
BIBE '05 Proceedings of the Fifth IEEE Symposium on Bioinformatics and Bioengineering
Alternate Representation of Distance Matrices for Characterization of Protein Structure
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Three-Dimensional Shape-Structure Comparison Method for Protein Classification
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Protein Structure Comparison and Alignment Using Residue Contexts
AINAW '08 Proceedings of the 22nd International Conference on Advanced Information Networking and Applications - Workshops
Using decision templates to predict subcellular localization of protein
PRIB'07 Proceedings of the 2nd IAPR international conference on Pattern recognition in bioinformatics
Prediction of protein subcellular localizations using moment descriptors and support vector machine
PRIB'06 Proceedings of the 2006 international conference on Pattern Recognition in Bioinformatics
An overview of statistical learning theory
IEEE Transactions on Neural Networks
A comparison of methods for multiclass support vector machines
IEEE Transactions on Neural Networks
Mining of protein contact maps for protein fold prediction
Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery
Hi-index | 0.00 |
It is an urgent need to understand the structure-function relationship in proteomic era. One of the important techniques to meet this demand is to analyze and represent the spatial structure of domain which is the functional unit of the whole protein, and perform fast domain classification. In this paper, we introduce a novel method of rapid domain classification. Instead of analyzing directly protein sequence or 3-D tertiary structure, the presented method maps firstly tertiary structure of protein domain into 2-D C***-C*** distance matrix. Then, two distance functions for alpha helix and beta strand are modeled by considering their geometrical properties respectively. After that, the distance functions are further applied to mine secondary structure elements in such distance matrix with the way similar to image processing. Furthermore, composition feature and arrangement feature of secondary structure elements are presented to characterize domain structure for classification of structural class and fold in Structural Classification of Proteins (SCOP) database. Finally, the results compared with other methods show that the presented method can perform effectively and efficiently automatic classification of domain with the benefit of low dimension and meaningful features, but also no need of complicated classifier system.