Abstract: Background. Drug-target interaction is key in drug discovery, especially in the design of new lead compound. However, the work to find a new lead compound for a specific target is complicated and hard, and it always leads to many mistakes. Therefore computational techniques are commonly adopted in drug design, which can save time and costs to a significant extent. Results. To address the issue, a new prediction system is proposed in this work to identify drug-target interaction. First, drug-target pairs are encoded with a fragment technique and the software "PaDEL-Descriptor" The fragment technique is for encoding target proteins, which divides each protein sequence into several fragments in order and encodes each fragment with several physiochemical properties of amino acids. The software "PaDEL-Descriptor" creates encoding vectors for drug molecules. Second, the dataset of drug-target pairs is resampled and several overlapped subsets are obtained, which are then input into kNN (k-Nearest Neighbor) classifier to build an ensemble system. Conclusion. Experimental results on the drug-target dataset showed that our method performs better and runs faster than the state-of-the-art predictors.