Published online 10 November 2005
Article |
Kernel-based machine learning protocol for predicting DNA-binding proteins
Bioinformatics Program, Department of Bioengineering, University of Illinois at Chicago Chicago, IL 60607, USA
*To whom correspondence should be addressed at Department of Bioengineering, University of Illinois at Chicago, 851 S. Morgan Street (M/C 063), Room 218, Chicago, IL 60607, USA. Tel: +1 312 413 2021; Fax: +1 312 413 2018; Email: huilu{at}uic.edu
Received June 20, 2005. Revised August 2, 2005. Accepted October 18, 2005.
DNA-binding proteins (DNA-BPs) play a pivotal role in various intra- and extra-cellular activities ranging from DNA replication to gene expression control. Attempts have been made to identify DNA-BPs based on their sequence and structural information with moderate accuracy. Here we develop a machine learning protocol for the prediction of DNA-BPs where the classifier is Support Vector Machines (SVMs). Information used for classification is derived from characteristics that include surface and overall composition, overall charge and positive potential patches on the protein surface. In total 121 DNA-BPs and 238 non-binding proteins are used to build and evaluate the protocol. In self-consistency, accuracy value of 100% has been achieved. For cross-validation (CV) optimization over entire dataset, we report an accuracy of 90%. Using leave 1-pair holdout evaluation, the accuracy of 86.3% has been achieved. When we restrict the dataset to less than 20% sequence identity amongst the proteins, the holdout accuracy is achieved at 85.8%. Furthermore, seven DNA-BPs with unbounded structures are all correctly predicted. The current performances are better than results published previously. The higher accuracy value achieved here originates from two factors: the ability of the SVM to handle features that demonstrate a wide range of discriminatory power and, a different definition of the positive patch. Since our protocol does not lean on sequence or structural homology, it can be used to identify or predict proteins with DNA-binding function(s) regardless of their homology to the known ones.
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  M. Gao and J. Skolnick DBD-Hunter: a knowledge-based method for the prediction of DNA-protein interactions Nucleic Acids Res., July 1, 2008; 36(12): 3978 - 3992. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
S. Shazman, G. Celniker, O. Haber, F. Glaser, and Y. Mandel-Gutfreund Patch Finder Plus (PFplus): A web server for extracting and displaying positive electrostatic patches on protein surfaces Nucleic Acids Res., July 13, 2007; 35(suppl_2): W526 - W530. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 K. Fujishima, M. Komasa, S. Kitamura, H. Suzuki, M. Tomita, and A. Kanai Proteome-Wide Prediction of Novel DNA/RNA-Binding Proteins Using Amino Acid Composition and Periodicity in the Hyperthermophilic Archaeon Pyrococcus furiosus DNA Res, June 15, 2007; (2007) dsm011v1. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 Z.-Q. Ye, S.-Q. Zhao, G. Gao, X.-Q. Liu, R. E. Langlois, H. Lu, and L. Wei Finding new structural and sequence attributes to predict possible disease association of single amino acid polymorphism (SAP) Bioinformatics, June 15, 2007; 23(12): 1444 - 1450. [Abstract] [Full Text] [PDF]
|
|