Prediction of DNA-Binding Propensity of Proteins by the Ball-Histogram Method
We contribute a novel, ball-histogram approach to DNA-binding propensity prediction of proteins. Unlike state-of-the-art methods based on constructing an ad-hoc set of features describing the charged patches of the proteins, the ball-histogram technique enables a systematic, Monte-Carlo exploration of the spatial distribution of charged amino acids, capturing joint probabilities of specified amino acids occurring in certain distances from each other. This exploration yields a model for the prediction of DNA binding propensity. We validate our method in prediction experiments, achieving favorable accuracies. Moreover, our method also provides interpretable features involving spatial distributions of selected amino acids.
Unable to display preview. Download preview PDF.
- 2.Stawiski, E.W., Gregoret, L.M., Mandel-Gutfreund, Y.: Annotating nucleic acid-binding function based on protein structure. J. Mol. Biol. (2003)Google Scholar
- 6.Bhardwaj, et al.: Kernel-based machine learning protocol for predicting DNA-binding proteins. Nuc. Acids Res. (2005)Google Scholar
- 8.Moreland, J.L., Gramada, A., Buzko, O.V., Zhang, Q., Bourne, P.E.: The Molecular Biology Toolkit (MBT): A Modular Platform for Developing Molecular Visualization Applications. BMC Bioinformatics (2005)Google Scholar
- 10.Caruana, R., Karampatziakis, N., Yessenalina, A.: An empirical evaluation of supervised learning in high dimensions. In: International Conference on Machine Learning (ICML), pp. 96–103 (2008)Google Scholar
- 12.Pabo, C.O., Sauer, R.T.: Transcription factors: structural families and principles of DNA recognition. Annual Review of Biochemistry 20, 137–151 (1992)Google Scholar