Artificial intelligence approach fighting COVID-19 with repurposing drugs

Ke, Yi Yu; Peng, Tzu Ting; Yeh, Teng Kuang; Huang, Wenzhun; Chang, Shao En; Wu, Szu Huei; Hung, Hui Chen; Hsu, Tsu; Lee, Shiow Ju; Song, Jeng Shin; Lin, Wen Hsing; Chiang, Tung Jung; Lin, Jau-Hong; Sytwu, Huey Kang; Chen, Chiung Tong

doi:10.1016/j.bj.2020.05.001

Cited by 184 publications

(128 citation statements)

References 46 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…In our screen, LDK378 produced a similar phenotype as nelfinavir but with an EC 50 greater than 40 μM. Of the three Class II molecules that increase the size and number of N-RNA condensates ( Figure 4A,B, Figure 4_figure supplements 1 and 2), tolcapone, a methyltransferase inhibitor, had been implicated in reducing viral production of an alpha coronavirus (49). The Class III molecules, nilotinib (a kinase inhibitor) and L-thyroxine (a thyroid hormone receptor agonist), did not quantitatively change droplet count or area (EC 50 > 40 μM) but had morphological effects on the droplets at 40 μM ( Figure 4A,B, Figure 4_figure supplements 1 and 2).…”

Section: Targeting Phase Separation Of the N Protein With Small Molecmentioning

confidence: 74%

SARS-CoV-2 nucleocapsid protein forms condensates with viral genomic RNA

Jack¹,

Ferro²,

Trnka³

et al. 2020

Preprint

View full text Add to dashboard Cite

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection causes COVID-19, a pandemic that seriously threatens global health. SARS CoV-2 propagates by packaging its RNA genome into membrane enclosures in host cells. The packaging of the viral genome into the nascent virion is mediated by the nucleocapsid (N) protein, but the underlying mechanism remains unclear. Here, we show that the N protein forms biomolecular condensates with viral RNA both in vitro and in mammalian cells. While the N protein forms spherical assemblies with unstructured RNA, it forms mesh like-structures with viral RNA strands that contain secondary structure elements. Cross-linking mass spectrometry identified an intrinsically-disordered region that forms interactions between N proteins in condensates, and truncation of this region disrupts phase separation. By screening 1,200 FDA approved drugs in vitro, we identified a kinase inhibitor nilotinib, which affects the morphology of N condensates in vitro and disrupts phase separation of the N protein in vivo. These results indicate that the N protein compartmentalizes viral RNA in infected cells through liquid-liquid phase separation, and this process can be disrupted by a possible drug candidate.

show abstract

Section: Targeting Phase Separation Of the N Protein With Small Molecmentioning

confidence: 74%

SARS-CoV-2 nucleocapsid protein forms condensates with viral genomic RNA

Jack¹,

Ferro²,

Trnka³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…AI can play important roles in the process of drug discovery [29]. In the hit identification step, AI is able to provide more reliable hits through machine learning [30]. The hits from different strategies need to be confirmed, and NMR plays critical roles in this step (Figure 1).…”

Section: Introductionmentioning

confidence: 99%

A Practical Perspective on the Roles of Solution NMR Spectroscopy in Drug Discovery

Li¹,

Kang

2020

Molecules

View full text Add to dashboard Cite

Solution nuclear magnetic resonance (NMR) spectroscopy is a powerful tool to study structures and dynamics of biomolecules under physiological conditions. As there are numerous NMR-derived methods applicable to probe protein–ligand interactions, NMR has been widely utilized in drug discovery, especially in such steps as hit identification and lead optimization. NMR is frequently used to locate ligand-binding sites on a target protein and to determine ligand binding modes. NMR spectroscopy is also a unique tool in fragment-based drug design (FBDD), as it is able to investigate target-ligand interactions with diverse binding affinities. NMR spectroscopy is able to identify fragments that bind weakly to a target, making it valuable for identifying hits targeting undruggable sites. In this review, we summarize the roles of solution NMR spectroscopy in drug discovery. We describe some methods that are used in identifying fragments, understanding the mechanism of action for a ligand, and monitoring the conformational changes of a target induced by ligand binding. A number of studies have proven that 19F-NMR is very powerful in screening fragments and detecting protein conformational changes. In-cell NMR will also play important roles in drug discovery by elucidating protein-ligand interactions in living cells.

show abstract

“…Presently, AI has been used extensively for drug research against Coronavirus disease (COVID-19) since AI platform can prove to be more useful for the identification of potential existing drugs with inhibitory human coronavirus (HCoV) activities by utilizing various learning datasets such as ( Ke et al., 2020 ): Reported or proven potential active compounds for combating SARS-CoV, SARS-CoV-2, influenza virus, human immunodeficiency virus (HIV) ( Ke et al., 2020 ). Inhibitors for known 3C-like protease (main protease of SARS-CoV-2) and other important protein targets translated by the SARS-CoV-2 viral genome ( Zhavoronkov et al., 2020 ).…”

Section: Introductionmentioning

confidence: 99%

“…Reported or proven potential active compounds for combating SARS-CoV, SARS-CoV-2, influenza virus, human immunodeficiency virus (HIV) ( Ke et al., 2020 ).…”

Section: Introductionmentioning

confidence: 99%

“…All the drugs predicted by using AI-based drug discovery could use to combat feline coronavirus in in-vitro cell-based assay and the results obtained from these assays will give the feedback to the AI system in order to relearn ( Ke et al., 2020 ). This may further lead to the generation of a modified AI-based model for the searching of existing drugs again.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AI-driven drug discovery: A boon against COVID-19?

Kaushik

Raj

2020

AI Open

View full text Add to dashboard Cite

The COVID-19 is an issue of international concern and threat to public health and there is an urgent need of drug/vaccine design. There is no vaccine or specific drug yet made as of July 23, 2020, for the coronavirus disease (COVID-19). Thus, the patients currently can only be treated symptomatically. A quick identification of the drugs for COVID-19 may act as a potential therapeutic medication which has been used earlier in patients to answer the present pandemic condition before it could get more worse. According to our view, an artificial intelligence (AI) based tool that may predict drugs/peptides directly from the sequences of infected patients and thereby, they might have better affinity with the target and contribute towards vaccine design against COVID-19. Researchers across the world proposed several vaccines/drugs for COVID-19 utilizing AI based approaches, however, testing of these proposed vaccines/drugs will be needed to verify the safety and feasibility for combating COVID-19.

show abstract

Artificial intelligence approach fighting COVID-19 with repurposing drugs

Cited by 184 publications

References 46 publications

SARS-CoV-2 nucleocapsid protein forms condensates with viral genomic RNA

SARS-CoV-2 nucleocapsid protein forms condensates with viral genomic RNA

A Practical Perspective on the Roles of Solution NMR Spectroscopy in Drug Discovery

AI-driven drug discovery: A boon against COVID-19?

Contact Info

Product

Resources

About