文献类型：期刊文献

英文题名：Target identification among known drugs by deep learning from heterogeneous networks

作者：Zeng, Xiangxiang[1];Zhu, Siyi[2];Lu, Weiqiang[3,4];Liu, Zehui[5];Huang, Jin[5];Zhou, Yadi[6];Fang, Jiansong[6];Huang, Yin[6,7];Guo, Huimin[7];Li, Lang[8];Trapp, Bruce D.[9];Nussinov, Ruth[10,11];Eng, Charis[6,12,13,14,15];Loscalzo, Joseph[16];Cheng, Feixiong[6,12,13]

机构：[1]Hunan Univ, Coll Informat Sci & Engn, Changsha 410082, Hunan, Peoples R China;[2]Xiamen Univ, Dept Comp Sci, Xiamen 361005, Fujian, Peoples R China;[3]East China Normal Univ, Shanghai Key Lab Regulatory Biol, Inst Biomed Sci, Shanghai 200241, Peoples R China;[4]East China Normal Univ, Sch Life Sci, Shanghai 200241, Peoples R China;[5]East China Univ Sci & Technol, Sch Pharm, Shanghai Key Lab New Drug Design, Shanghai 200237, Peoples R China;[6]Cleveland Clin, Lerner Res Inst, Genom Med Inst, 9500 Euclid Ave, Cleveland, OH 44106 USA;[7]China Pharmaceut Univ, Key Lab Drug Qual Control & Pharmacovigilance, Nanjing 210009, Peoples R China;[8]Ohio State Univ, Coll Med, Dept Biomed Informat, Columbus, OH 43210 USA;[9]Cleveland Clin, Lerner Res Inst, Dept Neurosci, Cleveland, OH 44022 USA;[10]NCI, Canc & Inammat Program, Leidos Biomed Res Inc, Frederick Natl Lab Canc Res, Frederick, MD 21702 USA;[11]Tel Aviv Univ, Sackler Sch Med, Dept Human Mol Genet & Biochem, IL-69978 Tel Aviv, Israel;[12]Case Western Reserve Univ, Cleveland Clin, Lerner Coll Med, Dept Mol Med, Cleveland, OH 44195 USA;[13]Case Western Reserve Univ, Sch Med, Case Comprehens Canc Ctr, Cleveland, OH 44106 USA;[14]Cleveland Clin, Taussig Canc Inst, Cleveland, OH 44195 USA;[15]Case Western Reserve Univ, Sch Med, Dept Genet & Genome Sci, Cleveland, OH 44106 USA;[16]Harvard Med Sch, Brigham & Womens Hosp, Dept Med, Boston, MA 02115 USA

年份：2020

卷号：11

期号：7

起止页码：1775

外文期刊名：CHEMICAL SCIENCE

收录：;EI(收录号：20201008249937);WOS:【SCI-EXPANDED(收录号:WOS:000515704400029)】；

基金：This work was supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health under Award Number K99HL138272 and R00HL138272 to F. C.; the National Institutes of Neurological Diseases of the National Institutes of Health under Award Number R3509730 to B. D. T.; and National Institutes of Health grants HL61795, HG007690, and HL119145 to J. L., and AHA grant 2017D007382 to J. L. This work has been also supported in part with Federal funds from the Frederick National Laboratory for Cancer Research, National Institutes of Health, under contract HHSN261200800001E. This research was supported (in part) by the Intramural Research Program of NIH, Frederick National Lab, Center for Cancer Research. The content of this publication does not necessarily reflect the views or policies of the Department of Health and Human Services, nor does mention of trade names, commercial products or organizations imply endorsement by the US Government. B. D. T. is the Morris and Ruth Grahame Endowed Chair in Biomedical Research at the Lerner Research Institute, Cleveland Clinic. C. E. is the Sondra J. and Stephen R. Hardis Endowed Chair of Cancer Genomic Medicine at the Cleveland Clinic and an ACS Clinical Research Professor.

语种：英文

外文关键词：Network embeddings - Deep learning - Genome

摘要：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.