通过支持向量机对DNA/RNA结合蛋白、G蛋白偶联受体和药物ADME相关蛋白进行功能预测。

Function prediction for DNA-/RNA-binding proteins, GPCRs, and drug ADME-associated proteins by SVM.

作者信息

Cai Congzhong, Xiao Hanguang, Yuan Qianfei, Liu Xinghua, Wen Yufeng

机构信息

Department of Applied Physics, Chongqing University, Chongqing 400044, People's Republic of China.

出版信息

Protein Pept Lett. 2008;15(5):463-8. doi: 10.2174/092986608784567528.

DOI:10.2174/092986608784567528

PMID:18537735

Abstract

This paper explores the use of support vector machine (SVM) for protein function prediction. Studies are conducted on several groups of proteins with different functions including DNA-binding proteins, RNA-binding proteins, G-protein coupled receptors, drug absorption proteins, drug metabolizing enzymes, drug distribution and excretion proteins. The computed accuracy for the prediction of these proteins is found to be in the range of 82.32% to 99.7%, which illustrates the potential of SVM in facilitating protein function prediction.

摘要

本文探讨了支持向量机（SVM）在蛋白质功能预测中的应用。对几组具有不同功能的蛋白质进行了研究，包括DNA结合蛋白、RNA结合蛋白、G蛋白偶联受体、药物吸收蛋白、药物代谢酶、药物分布和排泄蛋白。发现这些蛋白质预测的计算准确率在82.32%至99.7%之间，这说明了支持向量机在促进蛋白质功能预测方面的潜力。