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.

Advanced virtual screening enables the discovery of a host-targeting and broad-spectrum antiviral agent.

We employed an advanced virtual screening (AVS) approach to identify potential inhibitors of human dihydroorotate dehydrogenase (DHODH), a validated target for development of broad-spectrum antivirals. We screened a library of 495118 compounds and identified 495 compounds that exhibited better binding scores than the reference ligands involved in the screening. From the top 100 compounds, we selected 28 based on their consensus docking scores and structural novelty. Then, we conducted in vitro experiments to investigate the antiviral activity of selected compounds on HSV-1 infection, which is susceptible to DHODH inhibitors. Among the tested compounds, seven displayed statistically significant antiviral effects, with Comp 19 being the most potent inhibitor. We found that Comp 19 exerted its antiviral effect in a dose-dependent manner (IC50 = 1.1 µM) and exhibited the most significant antiviral effect when added before viral infection. In the biochemical assay, Comp 19 inhibited human DHODH in a dose-dependent manner with the IC50 value of 7.3 µM. Long-timescale molecular dynamics simulations (1000 ns) revealed that Comp 19 formed a very stable complex with human DHODH. Comp 19 also displayed broad-spectrum antiviral activity and suppressed cytokine production in THP-1 cells. Overall, our study provides evidence that AVS could be successfully implemented to discover novel DHODH inhibitors with broad-spectrum antiviral activity.

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.