Figure 1.

Work flow of the Bayesian framework. Here, we have illustrated the steps necessary for the reconstruction of a hypothetical toy network using our Bayesian framework. The toy network consists of three nodes n₁, n₂ and n₃. The experimentally measured global responses of n₁, n₂ and n₃ to external perturbations are denoted by ${\mathit{R}}_1=\{R_{11},R_{12},\dots \}$, ${\mathit{R}}_2=\{R_{21},R_{22},\dots \}$ and ${\mathit{R}}_3=\{R_{31},R_{32},\dots \}$ respectively. For each node n_i, we first developed a set of modified MRA equations by introducing the binary variables A_ij (which indicates whether n_j,j≠i influences n_i) into the MRA equations. Then we used the BVSA algorithm to infer the probability of P(A_ij = 1|R). See Additional file 1 for details of each step of the BVSA algorithm.