A Transferable Deep Learning Approach to Fast Screen Potent Antiviral Drugs against SARS-CoV-2

The COVID-19 pandemic calls for rapid development of effective treatments. Although various drug repurpose approaches have been used to screen the FDA-approved drugs and drug candidates in clinical phases against SARS-CoV-2, the coronavirus that causes this disease, no magic bullets have been found until now. We used directed message passing neural network to first build a broad-spectrum anti-beta-coronavirus compound prediction model, which gave satisfactory predictions on newly reported active compounds against SARS-CoV-2. Then we applied transfer learning to fine-tune the model with the recently reported anti-SARS-CoV-2 compounds. The fine-tuned model was applied to screen a large compound library with 4.9 million drug-like molecules from ZINC15 database and recommended a list of potential anti-SARS-CoV-2 compounds for further experimental testing. As a proof-of-concept, we experimentally tested 7 high-scored compounds that also demonstrated good binding strength in docking study against the 3C-like protease of SARS-CoV-2 and found one novel compound that inhibited the enzyme with an IC50 of 37.0 M. Our model is highly efficient and can be used to screen large compound databases with billions or more compounds to accelerate the drug discovery process for the treatment of COVID-19.

Scutellaria baicalensis extract and baicalein inhibit replication of SARS-CoV-2 and its 3C-like protease in vitro

COVID-19 has become a global pandemic that threatens millions of people worldwide. There is an urgent call for developing effective drugs against the virus (SARS-CoV-2) causing this disease. The main protease of SARS-CoV-2, 3C-like protease (3CLpro), is highly conserved across coronaviruses and is essential for the maturation process of viral polyprotein. Scutellariae radix (Huangqin in Chinese), the root of Scutellaria baicalensis has been widely used in traditional Chinese medicine to treat viral infection related symptoms. The extracts of S. baicalensis have exhibited broad spectrum antiviral activities. We studied the anti-SARS-CoV-2 activity of S. baicalensis and its ingredient compounds. We found that the ethanol extract of S. baicalensis inhibits SARS-CoV-2 3CLpro activity in vitro and the replication of SARS-CoV-2 in Vero cells with an EC50 of 0.74 g/ml. Among the major components of S. baicalensis, baicalein strongly inhibits SARS-CoV-2 3CLpro activity with an IC50 of 0.39 M. We further identified four baicalein analogue compounds from other herbs that inhibit SARS-CoV-2 3CLpro activity at microM concentration. Our study demonstrates that the extract of S. baicalensis has effective anti-SARS-CoV-2 activity and baicalein and analogue compounds are strong SARS-CoV-2 3CLpro inhibitors.

Engineering a zinc binding site into the de novo designed protein DS119 with a βαβ structure

Functional proteins designed de novo have potential application in chemical engineering, agriculture and healthcare. Metal binding sites are commonly used to incorporate functions. Based on a de novo designed protein DS119 with a βαβ structure, we have computationally engineered zinc binding sites into it using a home-made searching program. Seven out of the eight designed sequences tested were shown to bind Zn(2+) with micromolar affinity, and one of them bound Zn(2+) with 1:1 stoichiometry. This is the first time that metalloproteins with an α, β mixed structure have been designed from scratch.

Recent Advances in RNA Riboswitch / 生物化学与生物物理进展

Riboswitch is a novel type of posttranscriptional regulatory elements discovered by Breaker et al. in 2002. It can regulate gene expression by binding directly to small metabolites without the aid of protein molecules. Compared to normal protein-mediated regulation, riboswitch responds to metabolites more rapidly and sensitively. Its discovery opens a new world for RNA research. The recent advances in riboswitch researches were summarized, including crystal structure determination, mechanism and dynamics study, biosensor and antibacterial drug design. Topp et al. successfully reprogrammed E. coli to detect, follow, and precisely localize to a completely new chemical signal by using a synthetic riboswitch. This work provided new ideas for synthetic biology and artificial biology network. The advances in riboswitch 3D structure determination, reaction mechanism and dynamics provide useful information for rational drug design towards new generation of riboswitch-targeting antibacterials.