Predicting associations among drugs, targets and diseases by tensor decomposition for drug repositioning
Open Access
- 16 December 2019
- journal article
- research article
- Published by Springer Nature in BMC Bioinformatics
- Vol. 20 (S26) , 1-19
Abstract
Background: Development of new drugs is a time-consuming and costly process, and the cost is still increasing in recent years. However, the number of drugs approved by FDA every year per dollar spent on development is declining. Drug repositioning, which aims to find new use of existing drugs, attracts attention of pharmaceutical researchers due to its high efficiency. A variety of computational methods for drug repositioning have been proposed based on machine learning approaches, network-based approaches, matrix decomposition approaches, etc. Results: We propose a novel computational method for drug repositioning. We construct and decompose three-dimensional tensors, which consist of the associations among drugs, targets and diseases, to derive latent factors reflecting the functional patterns of the three kinds of entities. The proposed method outperforms several baseline methods in recovering missing associations. Most of the top predictions are validated by literature search and computational docking. Latent factors are used to cluster the drugs, targets and diseases into functional groups. Topological Data Analysis (TDA) is applied to investigate the properties of the clusters. We find that the latent factors are able to capture the functional patterns and underlying molecular mechanisms of drugs, targets and diseases. In addition, we focus on repurposing drugs for cancer and discover not only new therapeutic use but also adverse effects of the drugs. In the in-depth study of associations among the clusters of drugs, targets and cancer subtypes, we find there exist strong associations between particular clusters. Conclusions: The proposed method is able to recover missing associations, discover new predictions and uncover functional clusters of drugs, targets and diseases. The clustering of drugs, targets and diseases, as well as the associations among the clusters, provides a new guiding framework for drug repositioning.Keywords
This publication has 46 references indexed in Scilit:
- Pathway-Based Drug Repositioning for Cancers: Computational Prediction and Experimental ValidationJournal of Medicinal Chemistry, 2018
- Accurate Drug Repositioning through Non-tissue-Specific Core Signatures from Cancer TranscriptomesCell Reports, 2018
- Interaction of antidiabetic α‐glucosidase inhibitors and gut bacteria α‐glucosidaseProtein Science, 2018
- Malignancy Incidence, Management, and Prevention in Patients with Rheumatoid ArthritisRheumatology and Therapy, 2017
- Deep-Learning-Based Drug–Target Interaction PredictionJournal of Proteome Research, 2017
- Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic DataMolecular Pharmaceutics, 2016
- Target-Based Drug Repositioning Using Large-Scale Chemical–Protein Interactome DataJournal of Chemical Information and Modeling, 2015
- Arsenic downregulates gene expression at the postsynaptic density in mouse cerebellum, including genes responsible for long-term potentiation and depressionToxicology Letters, 2014
- Focus on mTOR inhibitors and tacrolimus in renal transplantation: Pharmacokinetics, exposure–response relationships, and clinical outcomesTransplant Immunology, 2014
- Predicting Drug–Target Interactions Using Probabilistic Matrix FactorizationJournal of Chemical Information and Modeling, 2013