SRP: A concise non-parametric similarity-rank-based model for predicting drug-target interactions

The identification of drug-target interactions in web lab is costly and time-consuming. Computational approaches become important to help identifying potential candidates for laboratory experiments. However, they usually involve solving optimization problems or assuming statistical distribution based on prior knowledge, and may require estimating tunable parameters. This paper is motivated by the concepts behind “follow-on” drugs. They are the drugs developed by drug companies to substitute the pioneering drug which was firstly discovered and patented for a specific target and determined a new therapeutic class. There are three observations from “follow-on” drugs. The first observation has been used by many existing methods: drugs interacting with a common target usually have higher similar scores (e.g. the similarity score in terms of chemical structure). The second one is that a drug candidate for a specific target gains more attention if it is more similar to those drugs interacting with the target than other known drugs, even though the similarity score is low. Lastly, people intuitively tend to design a “follow-on” drug for the targets already having more drugs because of less cost and less risk. In our approach, the above observations are translated into more evidences for predicted drug-target interaction. Designing an interaction tendency index to characterize these observations, we propose the similarity-rank-based predictor (SRP). Unlike other models, SRP is a non-parametric model and requires neither solving an optimization problem nor prior statistical knowledge. Based on real benchmark datasets, we show that our model is able to achieve higher accuracy than the two most recent models and our approach is able to cope with two real predicting scenario of missing interactions.