deepDR: a network-based deep learning approach to<i>in silico</i>drug repositioning

TLDR

Traditional drug discovery is time‑consuming and high risk, while repurposing approved drugs offers a low‑cost, high‑efficiency alternative, and large‑scale heterogeneous biological networks enable novel in silico repositioning approaches. The study develops deepDR, a network‑based deep‑learning method for in silico drug repurposing that integrates ten heterogeneous networks. deepDR learns high‑level drug features from ten heterogeneous networks via a multi‑modal deep autoencoder, then uses a variational autoencoder to jointly encode drug‑disease pairs and infer novel drug–disease associations. deepDR achieved an AUROC of 0.908, outperforming existing network‑ and machine‑learning methods, and its predictions were validated with an AUROC of 0.826 against ClinicalTrials.gov, including novel drug candidates for Alzheimer’s and Parkinson’s diseases. Source code, data, and supplementary materials are available at https://github.com/ChengF-Lab/deepDR and Bioinformatics online.

Abstract

Traditional drug discovery and development are often time-consuming and high risk. Repurposing/repositioning of approved drugs offers a relatively low-cost and high-efficiency approach toward rapid development of efficacious treatments. The emergence of large-scale, heterogeneous biological networks has offered unprecedented opportunities for developing in silico drug repositioning approaches. However, capturing highly non-linear, heterogeneous network structures by most existing approaches for drug repositioning has been challenging.In this study, we developed a network-based deep-learning approach, termed deepDR, for in silico drug repurposing by integrating 10 networks: one drug-disease, one drug-side-effect, one drug-target and seven drug-drug networks. Specifically, deepDR learns high-level features of drugs from the heterogeneous networks by a multi-modal deep autoencoder. Then the learned low-dimensional representation of drugs together with clinically reported drug-disease pairs are encoded and decoded collectively via a variational autoencoder to infer candidates for approved drugs for which they were not originally approved. We found that deepDR revealed high performance [the area under receiver operating characteristic curve (AUROC) = 0.908], outperforming conventional network-based or machine learning-based approaches. Importantly, deepDR-predicted drug-disease associations were validated by the ClinicalTrials.gov database (AUROC = 0.826) and we showcased several novel deepDR-predicted approved drugs for Alzheimer's disease (e.g. risperidone and aripiprazole) and Parkinson's disease (e.g. methylphenidate and pergolide).Source code and data can be downloaded from https://github.com/ChengF-Lab/deepDR.Supplementary data are available online at Bioinformatics.