Propagation of colour features. Feature propagation in a small example network (circles: compounds; squares: reactions). A: Network nodes carry feature vectors v = (r, g, b)T shown by RGB colours. Feature vectors for non-annotated elements are unknown and set to zero by definition (nodes shown in grey). B: After feature propagation, all nodes have distinct feature vectors, i.e. colours. Matching nodes by their colours would now allow to self-align the entire graph unambiguously.