Finding out the desired drug combinations is a challenging task because of the number of different combinations that exist and the adversarial effects that may arise. In this work, we generate drug combinations over multiple stages using distance calculation metrics from supervised learning, clustering, and a statistical similarity calculation metric for deriving the optimal treatment sequences. The combination generation happens for each patient based on the characteristics (features) observed during each stage of treatment. Our approach considers not the drug-to-drug (one-to-one) effect, but rather the effect of group of drugs with another group of drugs. We evaluate the combinations using an FNN model and identify future improvement directions.