Abstract
Co-administration of two or more drugs simultaneously can result in adverse drug reactions. Identifying drug-drug interactions (DDIs) is necessary, especially for drug development and for repurposing old drugs. DDI prediction can be viewed as a matrix completion task, for which matrix factorization (MF) appears as a suitable solution. This paper presents a novel Graph Regularized Probabilistic Matrix Factorization (GRPMF) method, which incorporates expert knowledge through a novel graph-based regularization strategy within an MF framework. An efficient and sounded optimization algorithm is proposed to solve the resulting non-convex problem in an alternating fashion. The performance of the proposed method is evaluated through the DrugBank dataset, and comparisons are provided against state-of-the-art techniques. The results demonstrate the superior performance of GRPMF when compared to its counterparts.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
e-mail: (emilie.chouzenoux{at}centralesupelec.fr, stuti.jain{at}inria.fr).
e-mail: (angshul{at}iiitd.ac.in, kritik{at}iiitd.ac.in).
This work received support from the Associate Team COMPASS between Inria and IIIT Delhi. E.C. and S.J. acknowledge support from the European Research Council Starting Grant MAJORIS ERC-2019-STG-850925.
1 In our experimental part, due to specificity of the retained dataset, R is a binary valued matrix. However, our framework holds for any type of realvalued symmetric DDI matrix R.
