Figure 1.

Example Bayesian network. A Bayesian network is a directed acyclic graph whose nodes represent random variables. In our work, the root node (A in this figure) always represents the disease state variable, and all other nodes represent the abundance value of specific mass spectrum features. Arcs are assumed to represent causality, so that the state of A causes a change in the probability that B will take on a certain value.

Kuschner et al. BMC Bioinformatics 2010 11:177   doi:10.1186/1471-2105-11-177
Download authors' original image