Target identification among known drugs by deep learning from heterogeneous networks
Top Cited Papers
Open Access
- 20 February 2020
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Chemical Science
- Vol. 11 (7), 1775-1797
- https://doi.org/10.1039/c9sc04336e
Abstract
Without foreknowledge of the complete drug target information, development of promising and affordable approaches for effective treatment of human diseases is challenging. Here, we develop deepDTnet, a deep learning methodology for new target identification and drug repurposing in a heterogeneous drug-gene-disease network embedding 15 types of chemical, genomic, phenotypic, and cellular network profiles. Trained on 732 U.S. Food and Drug Administration-approved small molecule drugs, deepDTnet shows high accuracy (the area under the receiver operating characteristic curve = 0.963) in identifying novel molecular targets for known drugs, outperforming previously published state-of-the-art methodologies. We then experimentally validate that deepDTnet-predicted topotecan (an approved topoisomerase inhibitor) is a new, direct inhibitor (IC50 = 0.43 mu M) of human retinoic-acid-receptor-related orphan receptor-gamma t (ROR-gamma t). Furthermore, by specifically targeting ROR-gamma t, topotecan reveals a potential therapeutic effect in a mouse model of multiple sclerosis. In summary, deepDTnet offers a powerful network-based deep learning methodology for target identification to accelerate drug repurposing and minimize the translational gap in drug development.Funding Information
- Foundation for the National Institutes of Health (HHSN261200800001E)
- National Institute of Neurological Disorders and Stroke (R3509730)
- National Heart, Lung, and Blood Institute (HG007690, HL119145, HL61795, K99HL138272, R00HL138272)
- American Heart Association (2017D007382)
This publication has 122 references indexed in Scilit:
- A TSPO ligand is protective in a mouse model of multiple sclerosisEMBO Molecular Medicine, 2013
- Prediction of Polypharmacological Profiles of Drugs by the Integration of Chemical, Side Effect, and Therapeutic SpaceJournal of Chemical Information and Modeling, 2013
- Large-scale prediction and testing of drug activity on side-effect targetsNature, 2012
- Topoisomerase inhibitors unsilence the dormant allele of Ube3a in neuronsNature, 2011
- Ursolic Acid Suppresses Interleukin-17 (IL-17) Production by Selectively Antagonizing the Function of RORγt ProteinOnline Journal of Public Health Informatics, 2011
- Predicting new molecular targets for known drugsNature, 2009
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009
- A Short Nur77-Derived Peptide Converts Bcl-2 from a Protector to a KillerCancer Cell, 2008
- Towards a proteome-scale map of the human protein–protein interaction networkNature, 2005
- Principles for modulation of the nuclear receptor superfamilyNature Reviews Drug Discovery, 2004