A Simple Protein Evolutionary Classification Method Based on the Mutual Relations Between Protein Sequences | Bentham Science

摘要

Background: Protein is a kind of important organics in life. It is varied with itssequences, structures and functions. Protein evolutionary classification is one of the popularresearch topics in computational bioinformatics. Many studies have used protein sequenceinformation to classify the evolutionary relationships of proteins. As the amount of proteinsequence data increases, efficient computational tools are needed to make efficient proteinevolutionary classifications with high accuracies in the big data paradigm.Methods: In this study, we propose a new simple and efficient computational approach based onthe normalized mutual information rates to compute the relationship between protein sequences,we then use the “distances” defined on the relationships to perform the evolutionary classificationsof proteins. The new method is computational efficient, model-free and unsupervised, which doesnot require training data when performing classifications.Results: Simulation studies on various examples demonstrate the efficiency of the new method.We use precision-recall curves to compare the efficiency of our new method with traditionalmethods, results show that the new method outperforms the traditional methods in most of thecases when performing evolutionary classifications.Conclusion: The new method is simple and proved to be efficient in protein evolutionaryclassifications, which is useful in future evolutionary analysis particularly in the big data paradigm.