Resistance to drugs that treat infectious disease is a major problem worldwide. The rapid emergence of drug resistance is not well understood. We present two in silico models for the discovery of drug resistance mechanisms and for combating the evolution of resistance, respectively. In the first model, we computationally investigated subgraphs of a biological interaction network that show substantial adaptations when cells transcriptionally respond to a changing environment or treatment. As a case study, we investigated the response of the malaria parasite Plasmodium falciparum to chloroquine and tetracycline treatments. The second model involves a machine learning technique that combines clustering, common distance similarity measurements, and hierarchical clustering to propose new combinations of drug targets.