Submit Manuscript  

Article Details


Computational Methods for Predicting DNA Binding Proteins

Author(s):

Gaofeng Pan, Jiandong Wang, Liang Zhao, William Hoskins and Jijun Tang*   Pages 1 - 13 ( 13 )

Abstract:


Background: DNA-binding proteins are very important to many biomolecular functions. The traditional experimental methods are expensive and time consuming. So computational methods that can predict whether a protein is a DNA-binding protein or not are very helpful to researchers. Machine learning has been widely used in many research areas. Many researchers proposed machine learning methods to do DNA-binding protein prediction. To know their advantage and disadvantage is meaningful.

Objective: There are many computational methods that can predict DNA-binding proteins. Every method uses different features and different classifier algorithms. We want to take a review over those methods to find out some common procedures that can help researchers to develop more accurate methods.

Method: Firstly, we talked about the information stored in the protein sequence and gene sequence. That information is the basement to find out the patterns leading to bind. Then, feature extraction methods and classifier algorithms are discussed. At last, give out some commonly used benchmark dataset and evaluate several methods.

Conclusion: In this review, we analyze some popular computational methods which can do DNA-binding protein. From those methods, we find out many useful skills to build up an accurate DNA-binding protein classifier. Those can help researchers to build up more useful computational tools. Currently, there are some machine learning methods have good performance on predicting DNA-binding proteins. The performance can be improved by using different kind of features and classifiers

Keywords:

DNA-binding protein, machine learning, feature extraction, PseAAC, DWT, benchmark dataset

Affiliation:

Department of Computer Science, College of Computer Science and Engineering, University of South Carolina, South Carolina, Department of Computer Science, College of Computer Science and Engineering, University of South Carolina, South Carolina, Department of Computer Science, College of Computer Science and Engineering, University of South Carolina, South Carolina, Department of Computer Science, College of Computer Science and Engineering, University of South Carolina, South Carolina, Department of Computer Science, College of Computer Science and Engineering, University of South Carolina, South Carolina



Read Full-Text article