Accelerated Discovery of Potent Fusion Inhibitors for Respiratory Syncytial Virus

On the additive artificial intelligence-based discovery of nanoparticle neurodegenerative disease drug delivery systems

Neurodegenerative diseases are characterized by slowly progressing neuronal cell death. Conventional drug treatment strategies often fail because of poor solubility, low bioavailability, and the inability of the drugs to effectively cross the blood-brain barrier. Therefore, the development of new neurodegenerative disease drugs (NDDs) requires immediate attention. Nanoparticle (NP) systems are of increasing interest for transporting NDDs to the central nervous system. However, discovering effective nanoparticle neuronal disease drug delivery systems (N2D3Ss) is challenging because of the vast number of combinations of NP and NDD compounds, as well as the various assays involved. Artificial intelligence/machine learning (AI/ML) algorithms have the potential to accelerate this process by predicting the most promising NDD and NP candidates for assaying. Nevertheless, the relatively limited amount of reported data on N2D3S activity compared to assayed NDDs makes AI/ML analysis challenging. In this work, the IFPTML technique, which combines information fusion (IF), perturbation theory (PT), and machine learning (ML), was employed to address this challenge. Initially, we conducted the fusion into a unified dataset comprising 4403 NDD assays from ChEMBL and 260 NP cytotoxicity assays from journal articles. Through a resampling process, three new working datasets were generated, each containing 500,000 cases. We utilized linear discriminant analysis (LDA) along with artificial neural network (ANN) algorithms, such as multilayer perceptron (MLP) and deep learning networks (DLN), to construct linear and non-linear IFPTML models. The IFPTML-LDA models exhibited sensitivity (Sn) and specificity (Sp) values in the range of 70% to 73% (>375,000 training cases) and 70% to 80% (>125,000 validation cases), respectively. In contrast, the IFPTML-MLP and IFPTML-DLN achieved Sn and Sp values in the range of 85% to 86% for both training and validation series. Additionally, IFPTML-ANN models showed an area under the receiver operating curve (AUROC) of approximately 0.93 to 0.95. These results indicate that the IFPTML models could serve as valuable tools in the design of drug delivery systems for neurosciences.

Improving drug discovery with a hybrid deep generative model using reinforcement learning trained on a Bayesian docking approximation

Generative approaches to molecular design are an area of intense study in recent years as a method to generate new pharmaceuticals with desired properties. Often though, these types of efforts are constrained by limited experimental activity data, resulting in either models that generate molecules with poor performance or models that are overfit and produce close analogs of known molecules. In this paper, we reduce this data dependency for the generation of new chemotypes by incorporating docking scores of known and de novo molecules to expand the applicability domain of the reward function and diversify the compounds generated during reinforcement learning. Our approach employs a deep generative model initially trained using a combination of limited known drug activity and an approximate docking score provided by a second machine learned Bayes regression model, with final evaluation of high scoring compounds by a full docking simulation. This strategy results in molecules with docking scores improved by 10-20% compared to molecules of similar size, while being 130 × faster than a docking only approach on a typical GPU workstation. We also show that the increased docking scores correlate with (1) docking poses with interactions similar to known inhibitors and (2) result in higher MM-GBSA binding energies comparable to the energies of known DDR1 inhibitors, demonstrating that the Bayesian model contains sufficient information for the network to learn to efficiently interact with the binding pocket during reinforcement learning. This outcome shows that the combination of the learned latent molecular representation along with the feature-based docking regression is sufficient for reinforcement learning to infer the relationship between the molecules and the receptor binding site, which suggest that our method can be a powerful tool for the discovery of new chemotypes with potential therapeutic applications.

From animal studies into clinical trials: the relevance of animal models to develop vaccines and therapies to reduce disease severity and prevent hRSV infection

INTRODUCTION

Human respiratory syncytial virus (hRSV) is an important cause of lower respiratory tract infections in the pediatric and the geriatric population worldwide. There is a substantial economic burden resulting from hRSV disease during winter. Although no vaccines have been approved for human use, prophylactic therapies are available for high-risk populations. Choosing the proper animal models to evaluate different vaccine prototypes or pharmacological treatments is essential for developing efficient therapies against hRSV.

AREAS COVERED

This article describes the relevance of using different animal models to evaluate the effect of antiviral drugs, pharmacological molecules, vaccine prototypes, and antibodies in the protection against hRSV. The animal models covered are rodents, mustelids, bovines, and nonhuman primates. Animals included were chosen based on the available literature and their role in the development of the drugs discussed in this manuscript.

EXPERT OPINION

Choosing the correct animal model is critical for exploring and testing treatments that could decrease the impact of hRSV in high-risk populations. Mice will continue to be the most used preclinical model to evaluate this. However, researchers must also explore the use of other models such as nonhuman primates, as they are more similar to humans, prior to escalating into clinical trials.

Treatment of Respiratory Viral Coinfections

With the advent of rapid multiplex PCR, physicians have been able to test for multiple viral pathogens when a patient presents with influenza-like illness. This has led to the discovery that many respiratory infections are caused by more than one virus. Antiviral treatment of viral coinfections can be complex because treatment of one virus will affect the time course of the other virus. Since effective antivirals are only available for some respiratory viruses, careful consideration needs to be given on the effect treating one virus will have on the dynamics of the other virus, which might not have available antiviral treatment. In this study, we use mathematical models of viral coinfections to assess the effect of antiviral treatment on coinfections. We examine the effect of the mechanism of action, relative growth rates of the viruses, and the assumptions underlying the interaction of the viruses. We find that high antiviral efficacy is needed to suppress both infections. If high doses of both antivirals are not achieved, then we run the risk of lengthening the duration of coinfection or even of allowing a suppressed virus to replicate to higher viral titers.

Probing In Silico the Benzimidazole Privileged Scaffold for the Development of Drug-like Anti-RSV Agents

Targeting the fusion (F) protein has been recognized as a fruitful strategy for the development of anti-RSV agents. Despite the considerable efforts so far put into the development of RSV F protein inhibitors, the discovery of adequate therapeutics for the treatment of RSV infections is still awaiting a positive breakthrough. Several benzimidazole-containing derivatives have been discovered and evaluated in clinical trials, with only some of them being endowed with a promising pharmacokinetic profile. In this context, we applied a computational study based on a careful analysis of a number of X-ray crystallographic data of the RSV F protein, in the presence of different clinical candidates. A deepen comparison of the related electrostatic features and H-bonding motifs allowed us to pave the way for the following molecular dynamic simulation of JNJ-53718678 and then to perform docking studies of the in-house library of potent benzimidazole-containing anti-RSV agents. The results revealed not only the deep flexibility of the biological target but also the most relevant and recurring key contacts supporting the benzimidazole F protein inhibitor ability. Among them, several hydrophobic interactions and π-π stacking involving F140 and F488 proved to be mandatory, as well as H-bonding to D486. Specific requirements turning in RSV F protein binding ability were also explored thanks to structure-based pharmacophore analysis. Along with this, in silico prediction of absorption, distribution, metabolism, excretion (ADME) properties, and also of possible off-target events was performed. The results highlighted once more that the benzimidazole ring represents a privileged scaffold whose properties deserve to be further investigated for the rational design of novel and orally bioavailable anti-RSV agents.

Towards machine learning discovery of dual antibacterial drug-nanoparticle systems

Artificial Intelligence/Machine Learning (AI/ML) algorithms may speed up the design of DADNP systems formed by Antibacterial Drugs (AD) and Nanoparticles (NP). In this work, we used IFPTML = Information Fusion (IF) + Perturbation-Theory (PT) + Machine Learning (ML) algorithm for the first time to study of a large dataset of putative DADNP systems composed by >165 000 ChEMBL AD assays and 300 NP assays vs. multiple bacteria species. We trained alternative models with Linear Discriminant Analysis (LDA), Artificial Neural Networks (ANN), Bayesian Networks (BNN), K-Nearest Neighbour (KNN) and other algorithms. IFPTML-LDA model was simpler with values of Sp ≈ 90% and Sn ≈ 74% in both training (>124 K cases) and validation (>41 K cases) series. IFPTML-ANN and KNN models are notably more complicated even when they are more balanced Sn ≈ Sp ≈ 88.5%-99.0% and AUROC ≈ 0.94-0.99 in both series. We also carried out a simulation (>1900 calculations) of the expected behavior for putative DADNPs in 72 different biological assays. The putative DADNPs studied are formed by 27 different drugs with multiple classes of NP and types of coats. In addition, we tested the validity of our additive model with 80 DADNP complexes experimentally synthetized and biologically tested (reported in >45 papers). All these DADNPs show values of MIC < 50 μg mL^-1 (cutoff used) better that MIC of AD and NP alone (synergistic or additive effect). The assays involve DADNP complexes with 10 types of NP, 6 coating materials, NP size range 5-100 nm vs. 15 different antibiotics, and 12 bacteria species. The IFPTML-LDA model classified correctly 100% (80 out of 80) DADNP complexes as biologically active. IFPMTL additive strategy may become a useful tool to assist the design of DADNP systems for antibacterial therapy taking into consideration only information about AD and NP components by separate.

Anno 2021: Which antivirals for the coming decade?

Despite considerable progress in the development of antiviral drugs, among which anti-immunodeficiency virus (HIV) and anti-hepatitis C virus (HCV) medications can be considered real success stories, many viral infections remain without an effective treatment. This not only applies to infectious outbreaks caused by zoonotic viruses that have recently spilled over into humans such as severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2), but also ancient viral diseases that have been brought under control by vaccination such as variola (smallpox), poliomyelitis, measles, and rabies. A largely unsolved problem are endemic respiratory infections due to influenza, respiratory syncytial virus (RSV), and rhinoviruses, whose associated morbidity will likely worsen with increasing air pollution. Furthermore, climate changes will expose industrialized countries to a dangerous resurgence of viral hemorrhagic fevers, which might also become global infections. Herein, we summarize the recent progress that has been made in the search for new antivirals against these different threats that the world population will need to confront with increasing frequency in the next decade.