Proteins interact among themselves, and different interactions form a very huge number of possible combinations representable as protein-to-protein interaction (PPI) networks that are mapped into graph structures. Protein complexes are a subset of mutually interacting proteins. Starting from a PPI network, protein complexes may be extracted by using computational methods.
We propose a new complexes meta-predictor which is capable of predicting protein complexes by integrating the results of different predictors. It is based on a distributed architecture that wraps predictor as web/grid services that is built on top of the grid infrastructure. The proposed meta-predictor first invokes different available predictors wrapped as services in a parallel way, then integrates their results using graph analysis, and finally evaluates the predicted results by comparing them against external databases storing experimentally determined protein complexes.
Ref: M. Cannataro, P.H. Guzzi, and P. Veltri, IMPRECO: Distributed prediction of protein complexes. In Proceedings of Future Generation Comp. Syst.. 2010, 434-440.
http://www.sciencedirect.com/science/article/pii/S0167739X09001113