Three-dimensional Krawtchouk descriptors for protein local surface shape comparison
作者：
Highlights：
• 2D Krawtchouk descriptors have been extended to 3D for local comparison of 3D surfaces.
• The location of the region-of-interest can be controlled by changing three parameters.
• The new formulation has many advantages over similar approaches, including minimal redundancy and discriminative performance.
• The new method uses only a small number of invariant descriptors per image for an efficient local image retrieval.
• The new descriptors have the potential to be applied to predicting biological function of proteins and computational drug design.
摘要
•2D Krawtchouk descriptors have been extended to 3D for local comparison of 3D surfaces.•The location of the region-of-interest can be controlled by changing three parameters.•The new formulation has many advantages over similar approaches, including minimal redundancy and discriminative performance.•The new method uses only a small number of invariant descriptors per image for an efficient local image retrieval.•The new descriptors have the potential to be applied to predicting biological function of proteins and computational drug design.
论文关键词：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
论文评审过程：Received 27 December 2018, Revised 26 April 2019, Accepted 8 May 2019, Available online 8 May 2019, Version of Record 10 May 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.05.019
