Machine-Learning Driven Drug Repurposing for COVID-19

The integration of machine learning methods into bioinformatics provides particular benefits in identifying how therapeutics effective in one context might have utility in an unknown clinical context or against a novel pathology. We aim to discover the underlying associations between viral proteins and antiviral therapeutics that are effective against them by employing neural network models. Using the National Center for Biotechnology Information virus protein database and the DrugVirus database, which provides a comprehensive report of broad-spectrum antiviral agents (BSAAs) and viruses they inhibit, we trained ANN models with virus protein sequences as inputs and antiviral agents deemed safe-in-humans as outputs. Model training excluded SARS-CoV-2 proteins and included only Phases II, III, IV and Approved level drugs. Using sequences for SARS-CoV-2 (the coronavirus that causes COVID-19) as inputs to the trained models produces outputs of tentative safe-in-human antiviral candidates for treating COVID-19. Our results suggest multiple drug candidates, some of which complement recent findings from noteworthy clinical studies. Our in-silico approach to drug repurposing has promise in identifying new drug candidates and treatments for other viruses.

[1]  Timothy Lee.  Protein Family Classification with Neural Networks , 2016 .

[2]  M. V. van Hemert,et al.  Cyclosporin A inhibits the replication of diverse coronaviruses. , 2011, The Journal of general virology.

[3]  Cathy H. Wu,et al.  Neural networks for full-scale protein sequence classification: Sequence encoding with singular value decomposition , 1995, Machine Learning.

[4]  Jie Hou,et al.  DeepSF: deep convolutional neural network for mapping protein sequences to folds , 2017, Bioinform..

[5]  Benjamin J. Polacco,et al.  A SARS-CoV-2 Protein Interaction Map Reveals Targets for Drug-Repurposing , 2020, Nature.

[6]  Vince Grolmusz,et al.  Near Perfect Protein Multi-Label Classification with Deep Neural Networks , 2017, Methods.

[7]  Xiangrong Liu,et al.  deepDR: a network-based deep learning approach to in silico drug repositioning , 2019, Bioinform..

[8]  Kwok-Hung Chan,et al.  Triple combination of interferon beta-1b, lopinavir–ritonavir, and ribavirin in the treatment of patients admitted to hospital with COVID-19: an open-label, randomised, phase 2 trial , 2020, The Lancet.

[9]  Renzhi Cao,et al.  Survey of Machine Learning Techniques in Drug Discovery. , 2019, Current drug metabolism.

[10]  Wu Zhong,et al.  Remdesivir and chloroquine effectively inhibit the recently emerged novel coronavirus (2019-nCoV) in vitro , 2020, Cell Research.

[11]  Yiming Bao,et al.  NCBI Viral Genomes Resource , 2014, Nucleic Acids Res..

[12]  gui-qiang Wang,et al.  A systematic review of lopinavir therapy for SARS coronavirus and MERS coronavirus—A possible reference for coronavirus disease‐19 treatment option , 2020, Journal of medical virology.

[13]  D. Jans,et al.  The FDA-approved drug ivermectin inhibits the replication of SARS-CoV-2 in vitro , 2020, Antiviral Research.

[14]  Yasuhiko Irie,et al.  Discovery and development of safe-in-man broad-spectrum antiviral agents , 2019, International Journal of Infectious Diseases.

[15]  Kristen Fortney,et al.  Drug Repurposing Using Deep Embeddings of Gene Expression Profiles. , 2018, Molecular pharmaceutics.

[16]  S. H. Basha.  Corona virus drugs – a brief overview of past, present and future , 2020 .

[17]  Ankur Taly,et al.  Using attribution to decode binding mechanism in neural network models for chemistry , 2018, Proceedings of the National Academy of Sciences.

[18]  Peter G. Schultz,et al.  A Large-scale Drug Repositioning Survey for SARS-CoV-2 Antivirals , 2020, bioRxiv.

[19]  Yan Zhao,et al.  Drug repositioning: a machine-learning approach through data integration , 2013, Journal of Cheminformatics.