Three-dimensional Krawtchouk descriptors for protein local surface shape comparison

PATTERN RECOGNITION

卷:93

Article

Sit, Atilla¹  Shin, Woong-Hee²  Kihara, Daisuke^2,3,4 

[1] Eastern Kentucky Univ, Dept Math & Stat, Richmond, KY 40475 USA

[2] Purdue Univ, Dept Biol Sci, W Lafayette, IN 47907 USA

[3] Purdue Univ, Dept Comp Sci, W Lafayette, IN 47907 USA

[4] Univ Cincinnati, Cincinnati Childrens Hosp Med Ctr, Dept Pediat, Cincinnati, OH 45229 USA

关键词: 3D image retrieval;    Local image comparison;    Region of interest;    Discrete orthogonal functions;    Krawtchouk polynomials;    Weighted Krawtchouk polynomials;    3D Krawtchouk moments;    Protein surface;    Ligand binding site;    Pocket comparison;    Structure-based function prediction;   

DOI  :  10.1016/j.patcog.2019.05.019

来源: Elsevier

【 摘 要 】

Direct comparison of three-dimensional (3D) objects is computationally expensive due to the need for translation, rotation, and scaling of the objects to evaluate their similarity. In applications of 3D object comparison, often identifying specific local regions of objects is of particular interest. We have recently developed a set of 2D moment invariants based on discrete orthogonal Krawtchouk polynomials for comparison of local image patches. In this work, we extend them to 3D and construct 3D Krawtchouk descriptors (3DKDs) that are invariant under translation, rotation, and scaling. The new descriptors have the ability to extract local features of a 3D surface from any region-of-interest. This property enables comparison of two arbitrary local surface regions from different 3D objects. We present the new formulation of 3DKDs and apply it to the local shape comparison of protein surfaces in order to predict ligand molecules that bind to query proteins. (C) 2019 Elsevier Ltd. All rights reserved.

【 授权许可】

Free