AUTHOR=Huang Feng , Qiu Yang , Li Qiaojun , Liu Shichao , Ni Fuchuan 

TITLE=Predicting Drug-Disease Associations via Multi-Task Learning Based on Collective Matrix Factorization

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 8 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2020.00218

DOI=10.3389/fbioe.2020.00218

ISSN=2296-4185

ABSTRACT=Identifying drug-disease associations is a critical integral in drug development. Computationally prioritizing the candidate drug-disease associations has attracted growing attention due to its contribution on reducing the cost of laboratory screening. Drug-disease associations involve different association types, such as drug indications and drug side effects. However, the existing models for predicting drug-disease associations merely concentrate on an independent task: recommending novel indications to benefit the drug repositioning, predicting potential side effects to prevent drug-induced risk or only determining the existence of drug-disease association. They ignore the crucial prior knowledge of the correlations across different association types. Since the Comparative Toxicogenomics Database (CTD) annotates the drug-disease associations as therapeutic or marker/mechanism, we consider predicting the two types of associations. To this end, we propose a collective matrix factorization-based multi-task learning method (CMFMTL) in this paper. CMFMTL handles the problem as a multi-task learning where each task is to predict one type of associations, and two tasks complement and improve each other by capturing the relatedness between them. First, drug-disease associations are represented as a bipartite network with two types of links representing the therapeutic effects and non-therapeutic effects. Then, CMFMTL respectively approximates the association matrix regarding each link type by matrix tri-factorization, and shares the low-dimensional latent representations for drugs and diseases in the two related tasks for the goal of collective learning. Finally, CMFMTL puts the two tasks into a unified optimization framework. We also develop an efficient algorithm to solve our proposed optimization problem. In the computational experiments, CMFMTL outperforms several state-of-the-art methods both in the two tasks. Moreover, Case studies show that CMFMTL helps to find out novel drug-disease associations that are not included in CTD, and simultaneously predicts their association types.