Abstract
Network inference and local classification models have been shown to be useful in predicting newly potential drug-target interactions (DTIs) for assisting in drug discovery or drug repositioning. The idea is to represent drugs, targets, and their interactions as a bipartite network or an adjacent matrix. However, existing methods have not yet addressed appropriately several issues, such as the powerless inference in the case of isolated subnetworks, the biased classifiers derived from insufficient positive samples, the need of training a number of local classifiers, and the unavailable relationship between known DTIs and unapproved drug-target pairs (DTPs). Designing more effective approaches to address those issues is always desirable. In this paper, after presenting better drug similarities and target similarities, we characterize each DTP as a feature vector of within-scores and between-scores so as to hold the following superiorities: (1) a uniform vector of all types of DTPs, (2) only one global classifier with less bias benefiting from adequate positive samples, and (3) more importantly, the visualized relationship between known DTIs and unapproved DTPs. The effectiveness of our approach is finally demonstrated via comparing with other popular methods under cross validation and predicting potential interactions for DTPs under the validation in existing databases.
Highlights
Since experimental determination of compound-protein interactions or potential drug-target interactions remains very challenging [1], there is a need to develop computational methods to assist those experiments
The first one is that one drug can interact with one or more proteins. Another is symmetrically the fact that one protein can be targeted by one or more drugs. These two observations led to the formation of drug-target interactions (DTIs) network [6] and made it possible to utilize DTIs to predict potential interactions among unapproved drug-target pairs (DTPs)
We shall first demonstrate the effectiveness of our topological similarity metric and our adaptive combination of similarities, compare our approach with other popular methods, including network-based inference model (NBI) [7] and bipartite local model (BLM) [8] and its GIP (AUC/area under the precisionrecall curve (AUPR)) 0.662/0.321 0.918/0.757
Summary
Since experimental determination of compound-protein interactions or potential drug-target interactions remains very challenging (e.g., requiring a huge amount of money and taking a very long period) [1], there is a need to develop computational methods to assist those experiments. The first one is that one drug can interact with one or more proteins. Another is symmetrically the fact that one protein can be targeted by one or more drugs. These two observations led to the formation of DTI network [6] and made it possible to utilize DTIs (approved drug-target pairs) to predict potential interactions among unapproved drug-target pairs (DTPs). The task to validate those predicted potential interactions is called drug repositioning or drug repurposing [7]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have