Supplement for "A Multiple Kernel Learning algorithm for drug-target interaction prediction"

AndrĂ© C. A. Nascimento, Ricardo B. C. PrudĂȘncio and Ivan G. Costa


Background: Drug-target networks are receiving a lot of attention in late years, given its relevance for pharmaceutical innovation and drug lead discovery. Many different in silico approaches for the identification of new drug-target interactions have been proposed, many of them based on kernel methods. Despite technical advances in the latest years, previous approaches are not able to cope with large drug-target interaction spaces and integrate multiple sources of biological information simultaneously.
Results: We propose KronRLS-MKL, a method suitable to the non-sparse combination of kernels in bipartite link prediction on drug-target networks. This method allows the integration of multiple heterogeneous information sources for the identification of new interactions, and can also work with networks of arbitrary size. Moreover, our method can also automatically select the more relevant kernels, returning weights indicating their importance in the drug-target prediction at hand. Empirical analysis on four data sets, using twenty distinct kernels indicates that our method has higher or comparable predictive performance than all evaluated methods. Moreover, the predicted weights reflect the predictive quality of each kernel on exhaustive pairwise experiments, which indicates the success of the method to automatically indicate relevant biological sources.
Conclusions: Our analysis show that the proposed data integration strategy is able to improve the quality of the predicted interactions, and can speed up the identification of new drug-target interactions as well as identify relevant information for the task.


The compressed folder contains data concerning:


Matlab implementation of the KronRLS-MKL algorithm [download]. To execute the experiments, uncompress the file in the same path of the "code" directory.


Contact the authors at for any questions or comments.