hPrint is an attempt to predict physical and functional interactions. It is using a sophisticated combination of random forest and Bayesian learning approaches in order to integrate various evidences (text mining, genetic relationships, evolutionary information, and domain profiles) for predicting PPI and integrating those predictions with known information. It is also a method for predicting interactions that was -for the first time- experimentally evaluated.
Large-scale de novo prediction of physical protein-protein association. Elefsinioti A, Sarac OS, Hegele A, Plake C, Hubner NC, Poser I, Sarov M, Hyman A, Mann M, Schroeder M, Stelzl U, Beyer A. Mol Cell Proteomics. 2011