Published Articles >> Table of Contents >> Abstract

Computer Graphics and Image Processing, XVII Brazilian Symposium on (SIBGRAPI'04)   pp. 17-24
An Image-Matching Approach to Protein Similarity Analysis
Fernando Fernandes Jr., Universidade Federal de Minas Gerais, Brazil
Rodrigo L. Carceroni, Universidade Federal de Minas Gerais, Brazil
Carlos E. R. Lopes, Universidade Federal de Minas Gerais, Brazil
Wagner Meira Jr., Universidade Federal de Minas Gerais, Brazil
Raquel C. de Melo, Universidade Federal de Minas Gerais, Brazil
Arnaldo de A. Araujo, Universidade Federal de Minas Gerais, Brazil
Marcelo M. Santoro, Universidade Federal de Minas Gerais, Brazil
Carlos H. Silveira, Universidade Federal de Minas Gerais, Brazil

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/SIBGRA.2004.1352938
Send link to a friend

Abstract
In this work we model the problem of identifying how close structurally two proteins are as a problem of measuring the similarity between color images that represent their contact maps, where the chromatic information encodes the chemical nature of the contacts. We study two conceptually distinct methods to measure the similarity between such contact maps: a content-based image retrieval one and another based on image registration. In experiments with contact maps constructed from the PDB, the image registration approach was able to identify with 100% precision 8 instances of a protein class mixed with 28 proteins of other classes. The content-based image retrieval approach had an accuracy only a little worse than that.
Back to Top Additional Information
Citation:  Fernando Fernandes Jr., Rodrigo L. Carceroni, Carlos E. R. Lopes, Wagner Meira Jr., Raquel C. de Melo, Arnaldo de A. Araujo, Marcelo M. Santoro, Carlos H. Silveira, "An Image-Matching Approach to Protein Similarity Analysis," sibgrapi, pp. 17-24,  Computer Graphics and Image Processing, XVII Brazilian Symposium on (SIBGRAPI'04),  2004