An ACO based functional module detection algorithm for protein interaction networks

Protein-protein interactions (PPIs) play fundamental roles in nearly all biological processes and differ based on the composition, affinity and lifetime of the association. A vast amount of PPI data for various organisms is available from MIPS, DIP and other sources. The identification of functional modules in PPI network is of great interest because they often reveal unknown functional ties between proteins and hence predict functions for unknown proteins. However the noise in the PPI network and the complexity of the network structure present great challenges to the functional module detection problem. In this paper, we propose a flexible framework which integrates the topological features of the network and the Ant Colony Optimization (ACO) algorithm to solve the problem. We first create an reliability measurement of the protein-protein interaction to rebuild the PPI network. Then we reformulate the problem to an optimal path detecting problem from the perspective of information flow. Last, an ACO-based functional module detection method is proposed by simulating the ants' behavior. We evaluate the proposed technique on the yeast protein-protein interaction network with MIPS functional categories and compare it with several other existing techniques. Our experiments show that our approach achieves better accuracy than other existing methods.