Improving prediction of drug therapy outcome via integration of time series gene expression and Protein Protein Interaction network

Drug therapy to patients is often with partial success, and has been associated with a number of adverse reactions. Prediction of patients' response to therapy at the early stage of the treatment is crucial to avoiding those unnecessary adverse reactions. In this paper, a new approach that integrates time series gene expression and Protein Protein Interaction (PPI) network is presented to improve the prediction of patients' response to drug therapy. Experimental results showed that our method outperformed previous approaches. The method proposed here offers a huge potential for applications in pharmacogenomics and medicine.