Data discretization, also known as binning, is a frequently used technique in computer science, statistics, and their applications to biological data analysis. We present a new method for the discretization of real-valued data into a finite number of discrete values. Novel aspects of the method are the incorporation of an information-theoretic criterion and a criterion to determine the optimal number of values. While the method can be used for data clustering, the motivation for its development is the need for a discretization algorithm for several multivariate time series of heterogeneous data, such as transcript, protein, and metabolite concentration measurements. As several modeling methods for biochemical networks employ discrete variable states, the method needs to preserve correlations between variables as well as the dynamic features of the time series. A C++ implementation of the algorithm is available from the authors at http://polymath.vbi.vt.edu/discretization .
Download