Discovery of new antiviral agents through artificial intelligence: In vitro and in vivo results.

In this research, we employed a deep reinforcement learning (RL)-based molecule design platform to generate a diverse set of compounds targeting the neuraminidase (NA) of influenza A and B viruses. A total of 60,291 compounds were generated, of which 86.5 % displayed superior physicochemical properties compared to oseltamivir. After narrowing down the selection through computational filters, nine compounds with non-sialic acid-like structures were selected for in vitro experiments. We identified two compounds, DS-22-inf-009 and DS-22-inf-021 that effectively inhibited the NAs of both influenza A and B viruses (IAV and IBV), including H275Y mutant strains at low micromolar concentrations. Molecular dynamics simulations revealed a similar pattern of interaction with amino acid residues as oseltamivir. In cell-based assays, DS-22-inf-009 and DS-22-inf-021 inhibited IAV and IBV in a dose-dependent manner with EC50 values ranging from 0.29 µM to 2.31 µM. Furthermore, animal experiments showed that both DS-22-inf-009 and DS-22-inf-021 exerted antiviral activity in mice, conferring 65 % and 85 % protection from IAV (H1N1 pdm09), and 65 % and 100 % protection from IBV (Yamagata lineage), respectively. Thus, these findings demonstrate the potential of RL to generate compounds with promising antiviral properties.

Design of new chemical entities targeting both native and H275Y mutant influenza a virus by deep reinforcement learning.

Influenza virus remains a major public health challenge due to its high morbidity and mortality and seasonal surge. Although antiviral drugs against the influenza virus are widely used as a first-line defense, the virus undergoes rapid genetic changes, resulting in the emergence of drug-resistant strains. Thus, new antiviral drugs that can outwit resistant strains are of significant importance. Herein, we used deep reinforcement learning (RL) algorithm to design new chemical entities (NCEs) that are able to bind to the native and H275Y mutant (oseltamivir-resistant) neuraminidases (NAs) of influenza A virus with better binding energy than oseltamivir. We generated more than 66211 NCEs, which were prioritized based on the filtering rules, structural alerts, and synthetic accessibility. Then, 18 NCEs with better MM/PBSA scores than oseltamivir were further analyzed in molecular dynamics (MD) simulations conducted for 100 ns. The MD experiments showed that 8 NCEs formed very stable complexes with the binding pocket of both native and H275Y mutant NAs of H1N1. Furthermore, most NCEs demonstrated much better binding affinity to group 2 (N2, N3, and N9) and influenza B virus NAs than oseltamivir. Although all 8 NCEs have non-sialic acid-like structures, they showed a similar binding mode as oseltamivir, indicating that it is possible to find new scaffolds with better binding and antiviral properties than sialic acid-like inhibitors. In conclusion, we have designed potential compounds as antiviral candidates for further synthesis and testing against wild and mutant influenza virus.Communicated by Ramaswamy H. Sarma.

Identification of Novel Potential VEGFR-2 Inhibitors Using a Combination of Computational Methods for Drug Discovery.

The vascular endothelial growth factor receptor 2 (VEGFR-2) is largely recognized as a potent therapeutic molecular target for the development of angiogenesis-related tumor treatment. Tumor growth, metastasis and multidrug resistance highly depends on the angiogenesis and drug discovery of the potential small molecules targeting VEGFR-2, with the potential anti-angiogenic activity being of high interest to anti-cancer research. Multiple small molecule inhibitors of the VEGFR-2 are approved for the treatment of different type of cancers, with one of the most recent, tivozanib, being approved by the FDA for the treatment of relapsed or refractory advanced renal cell carcinoma (RCC). However, the endogenous and acquired resistance of the protein, toxicity of compounds and wide range of side effects still remain critical issues, which lead to the short-term clinical effects and failure of antiangiogenic drugs. We applied a combination of computational methods and approaches for drug design and discovery with the goal of finding novel, potential and small molecule inhibitors of VEGFR2, as alternatives to the known inhibitors' chemical scaffolds and components. From studying several of these compounds, the derivatives of pyrido[1,2-a]pyrimidin-4-one and isoindoline-1,3-dione in particular were identified.

Photocrosslinked poly(amidoamine) nanoparticles for central nervous system targeting.

This study presents an innovative method for the synthesis of polymeric nanoparticles (NPs) for central nervous system (CNS) targeting. The method is based on Ultraviolet light (UV)-induced crosslinking of diacrylamide-terminated oligomers of poly(amidoamine)s (PAAs), a widely used class of synthetic polymers in biomedical field research, especially in drug delivery thanks to their excellent biocompatibility and controlled biodegradability. Previous attempts aiming at preparing PAA-based NPs by self-assembly were challenged by lack of structural stability and consequently their early degradation and premature drug release. Here, the UV-induced crosslinked PAA NPs demonstrated to overcome main disadvantages of the self-assembled ones, as they showed improved stability and controlled release properties. Besides the remarkable efficiency to produce monodisperse and stable PAA NPs, the UV-induced crosslinking method is featured by great versatility and low environmental impact, since it does not require use of organic solvents and multiple purification steps. The capability of PAA NPs to encapsulate a fluorescently labelled model protein was experimentally demonstrated in this study. Cell culture experiments showed that PAA NPs were biocompatible and highly permeable across an in vitro blood-brain barrier model, thus highlighting their great potential as drug delivery vectors for CNS delivery.