Machine intelligence design of 2019-nCoV drugs
Abstract
Wuhan coronavirus, called 2019-nCoV, is a newly emerged virus that infected more than 9692 people and leads to more than 213 fatalities by January 30, 2020. Currently, there is no effective treatment for this epidemic. However, the viral protease of a coronavirus is well-known to be essential for its replication and thus is an effective drug target. Fortunately, the sequence identity of the 2019-nCoV protease and that of severe-acute respiratory syndrome virus (SARS-CoV) is as high as 96.1%. We show that the protease inhibitor binding sites of 2019-nCoV and SARS-CoV are almost identical, which means all potential anti-SARS-CoV chemotherapies are also potential 2019-nCoV drugs. Here, we report a family of potential 2019-nCoV drugs generated by a machine intelligence-based generative network complex (GNC). The potential effectiveness of treating 2019-nCoV by using some existing HIV drugs is also analyzed.
02 /Specification & Classification
Click any tag to browse matching papers- Citations
- 53
- Organism
- Assay
- Research Focus
- Approach
Abstract summary
Claude Opus 5.5 · xhigh effort · 18 Oct 2026 · from the abstract · CC BY-NC 4.0
The 2019-nCoV protease shares 96.1% sequence identity and near-identical inhibitor binding sites with SARS-CoV, so a generative machine-learning model proposes candidate inhibitors; existing HIV drugs are also assessed.
When this was posted there was no effective treatment for the newly emerged 2019-nCoV, and the viral protease, required for replication, is the standard target. The authors argue that because this protease closely matches the SARS-CoV one, anti-SARS-CoV chemotherapies carry over, and they use a generative model to propose further inhibitors.
Key results
SuggestedThe protease of 2019-nCoV is close enough to the SARS-CoV protease, including at the inhibitor binding site, that the authors treat anti-SARS-CoV compounds as candidate 2019-nCoV drugs.
Sequence identity between the two proteases is given as 96.1%; the binding sites are described as almost identical, with no structural comparison statistics reported in the abstract. · Abstract
ClaimedA generative network complex produced a family of candidate 2019-nCoV protease inhibitors.
Reported as output of a machine-intelligence generative network complex (GNC); the abstract gives no number of compounds, no predicted affinities and no experimental test. · Abstract
ClaimedExisting HIV drugs are also analysed for potential effectiveness against 2019-nCoV.
Stated as an additional analysis of existing HIV drugs; neither the drugs nor any result of that analysis appear in the abstract. · Abstract
Methods, data and reproducibility
Sequence and inhibitor binding-site comparison between the 2019-nCoV and SARS-CoV proteases, then generation of candidate protease inhibitors with a machine intelligence-based generative network complex (GNC). Existing HIV drugs are analysed separately for possible activity against the new virus.
- Protease sequences of 2019-nCoV and SARS-CoV, compared for identity and for inhibitor binding sites · virus
- Existing HIV drugs assessed for possible activity against 2019-nCoV
- Methods & tools
- generative network complex (GNC)
Limitations (2)
- The abstract reports no validation of the generated compounds: no count of molecules, no predicted or measured binding affinities, no docking scores and no biochemical or cell assay. · noted in this summary
- The repurposing argument rests on protease sequence identity and a stated similarity of binding sites; no structure of the 2019-nCoV protease or evidence that anti-SARS-CoV compounds inhibit it is presented here. · noted in this summary
Who should read:Read this if you follow early computational repurposing claims for coronavirus proteases, or want a case of generative compound design argued from target homology alone.
Reproducibility ledger
Nobody has reported trying to reproduce this paper yet. Did you replicate an experiment or run the code? Your report saves the next lab a week.
Sign in to file a reproducibility report.
Related papers
- Therapeutic Drugs Targeting 2019-nCoV Main Protease by High-Throughput Screening
- Predicting commercially available antiviral drugs that may act on the novel coronavirus (2019-nCoV), Wuhan, China through a drug-target interaction deep learning model
B. R. Beck, B. Shin, … K. Kang·Computational and Structural Biotechnology JournalPeer-reviewed·Apr 4, 2020
- Potentially highly potent drugs for 2019-nCoV
Duc Duy Nguyen, Kaifu Gao, … Guo‐Wei Wei·bioRxiv·Feb 5, 2020
- Potential inhibitors for 2019-nCoV coronavirus M protease from clinically approved medicines
Xin Liu, Xiu‐Jie Wang·Journal of genetics and genomics/Journal of Genetics and GenomicsPeer-reviewed·Feb 1, 2020
- A drug repurposing screen identifies hepatitis C antivirals as inhibitors of the SARS-CoV-2 main protease.
J. D. Baker, R. L. Uhrich, … B. C. Kraemer·PLOS ONEPeer-reviewed·Feb 1, 2021
- Nelfinavir inhibits replication of severe acute respiratory syndrome coronavirus 2 in vitro.
N. Yamamoto, S. Matsuyama, … N. Yamamoto·bioRxiv·Apr 6, 2020