Figure 2From: Protein (multi-)location prediction: using location inter-dependencies in a probabilistic frameworkAdding, deleting, and reversing an edge in a Bayesian network during structure learning. The network on the left (i), is the starting point. Networks (ii), (iii), and (iv) show the addition, deletion, and reversal of an edge, respectively, as performed by the greedy hill climbing algorithm for structure learning.Back to article page