A data-driven drug repositioning framework discovered a
potential therapeutic agent targeting COVID-19
Yiyue Ge1,2,†, Tingzhong Tian1,2,†, Suling Huang3,†, Fangping Wan1,†, Jingxin Li2,†,
Shuya Li1, Hui Yang11, Lixiang Hong1, Nian Wu1, Enming Yuan1, Lili Cheng4, Yipin
Lei11, Hantao Shu1, Xiaolong Feng6,7, Ziyuan Jiang5, Ying Chi2, Xiling Guo2, Lunbiao
Cui2, Liang Xiao10, Zeng Li10 , Chunhao Yang3, Zehong Miao3, Haidong Tang4, Ligong
Chen4, Hainian Zeng11, Dan Zhao1,* , Fengcai Zhu2,8,*, Xiaokun Shen10,*, Jianyang
1Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, 100084, China.
2NHC Key laboratory of Enteric Pathogenic Microbiology, Jiangsu Provincial Center for Diseases
Control and Prevention, Nanjing, Jiangsu Province, 210009, China.
3Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai, 201203, China.
4School of Pharmaceutical Sciences, Beijing Advanced Innovation Center for Structural Biology,
Tsinghua University, Beijing, 100084, China.
5Department of Automation, Tsinghua University, Beijing, 100084, China.
6School of Electronic Information and Communications, Huazhong University of Science and
Technology, Wuhan, Hubei Province, 430074, China.
7Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and
Technology, Wuhan, Hubei Province, 430030, China.
8Center for Global Health, Nanjing Medical University, Nanjing, Jiangsu Province, 210009, China.
9MOE Key Laboratory of Bioinformatics, Tsinghua University, Beijing, 100084, China.
10Convalife (Shanghai) Co., Ltd., Shanghai, 201203, China.
11Silexon AI Technology Co., Ltd., Nanjing, Jiangsu Province, 210033, China.
†These authors contributed equally to this work.
The global spread of SARS-CoV-2 requires an urgent need to ﬁnd eﬀective therapeu-
tics for the treatment of COVID-19. We developed a data-driven drug repositioning
framework, which applies both machine learning and statistical analysis approaches
to systematically integrate and mine large-scale knowledge graph, literature and tran-
scriptome data to discover the potential drug candidates against SARS-CoV-2. The
retrospective study using the past SARS-CoV and MERS-CoV data demonstrated that
our machine learning based method can successfully predict eﬀective drug candidates
Email addresses: firstname.lastname@example.org (Dan Zhao), email@example.com (Fengcai
Zhu), firstname.lastname@example.org (Xiaokun Shen), email@example.com (Jianyang Zeng)
March 11, 2020
author/funder. All rights reserved. No reuse allowed without permission.
The copyright holder for this preprint (which was not peer-reviewed) is the. https://doi.org/10.1101/2020.03.11.986836doi: bioRxiv preprint