Development of Machine Learning Models and the Discovery of a New Antiviral Compound against Yellow Fever Virus

Organotypic culture of human brain explants as a preclinical model for AI-driven antiviral studies

Viral neuroinfections represent a major health burden for which the development of antivirals is needed. Antiviral compounds that target the consequences of a brain infection (symptomatic treatment) rather than the cause (direct-acting antivirals) constitute a promising mitigation strategy that requires to be investigated in relevant models. However, physiological surrogates mimicking an adult human cortex are lacking, limiting our understanding of the mechanisms associated with viro-induced neurological disorders. Here, we optimized the Organotypic culture of Post-mortem Adult human cortical Brain explants (OPAB) as a preclinical platform for Artificial Intelligence (AI)-driven antiviral studies. OPAB shows robust viability over weeks, well-preserved 3D cytoarchitecture, viral permissiveness, and spontaneous local field potential (LFP). Using LFP as a surrogate for neurohealth, we developed a machine learning framework to predict with high confidence the infection status of OPAB. As a proof-of-concept, we showed that antiviral-treated OPAB could partially restore LFP-based electrical activity of infected OPAB in a donor-dependent manner. Together, we propose OPAB as a physiologically relevant and versatile model to study neuroinfections and beyond, providing a platform for preclinical drug discovery.

A Predictive Model of Vaccine Reactogenicity Using Data from an In Vitro Human Innate Immunity Assay System

A primary concern in vaccine development is safety, particularly avoiding an excessive immune reaction in an otherwise healthy individual. An accurate prediction of vaccine reactogenicity using in vitro assays and computational models would facilitate screening and prioritization of novel candidates early in the vaccine development process. Using the modular in vitro immune construct model of human innate immunity, PBMCs from 40 healthy donors were treated with 10 different vaccines of varying reactogenicity profiles and then cell culture supernatants were analyzed via flow cytometry and a multichemokine/cytokine assay. Differential response profiles of innate activity and cell viability were observed in the system. In parallel, an extensive adverse event (AE) dataset for the vaccines was assembled from clinical trial data. A novel reactogenicity scoring framework accounting for the frequency and severity of local and systemic AEs was applied to the clinical data, and a machine learning approach was employed to predict the incidence of clinical AEs from the in vitro assay data. Biomarker analysis suggested that the relative levels of IL-1B, IL-6, IL-10, and CCL4 have higher predictive importance for AE risk. Predictive models were developed for local reactogenicity, systemic reactogenicity, and specific individual AEs. A forward-validation study was performed with a vaccine not used in model development, Trumenba (meningococcal group B vaccine). The clinically observed Trumenba local and systemic reactogenicity fell on the 26th and 93rd percentiles of the ranges predicted by the respective models. Models predicting specific AEs were less accurate. Our study presents a useful framework for the further development of vaccine reactogenicity predictive models.

Identification of potential inhibitors targeting yellow fever virus helicase through ligand and structure-based computational studies

Yellow fever is a flavivirus having plus-sensed RNA which encodes a single polyprotein. Host proteases cut this polyprotein into seven nonstructural proteins including a vital NS3 protein. The present study aims to identify the most effective inhibitor against the helicase (NS3) using different advanced ligand and structure-based computational studies. A set of 300 ligands was selected against helicase by chemical structural similarity model, which are similar to S-adenosyl-l-cysteine using infiniSee. This tool screens billions of compounds through a similarity search from in-built chemical spaces (CHEMriya, Galaxi, KnowledgeSpace and REALSpace). The pharmacophore was designed from ligands in the library that showed same features. According to the sequence of ligands, six compounds (29, 87, 99, 116, 148, and 208) were taken for pharmacophore designing against helicase protein. Subsequently, compounds from the library which showed the best pharmacophore shared-features were docked using FlexX functionality of SeeSAR and their optibrium properties were analyzed. Afterward, their ADME was improved by replacing the unfavorable fragments, which resulted in the generation of new compounds. The selected best compounds (301, 302, 303 and 304) were docked using SeeSAR and their pharmacokinetics and toxicological properties were evaluated using SwissADME. The optimal inhibitor for yellow fever helicase was 2-amino-N-(4-(dimethylamino)thiazol-2-yl)-4-methyloxazole-5-carboxamide (302), which exhibits promising potential for drug development.Communicated by Ramaswamy H. Sarma.

1-Sulfonyl-3-amino-1H-1,2,4-triazoles as Yellow Fever Virus Inhibitors: Synthesis and Structure-Activity Relationship

Yellow fever virus (YFV) transmitted by infected mosquitoes causes an acute viral disease for which there are no approved small-molecule therapeutics. Our recently developed machine learning models for YFV inhibitors led to the selection of a new pyrazolesulfonamide derivative RCB16003 with acceptable in vitro activity. We report that the N-phenyl-1-(phenylsulfonyl)-1H-1,2,4-triazol-3-amine class, which was recently identified as active non-nucleoside reverse transcriptase inhibitors against HIV-1, can also be repositioned as inhibitors of yellow fever virus replication. As compared to other Flaviviridae or Togaviridae family viruses tested, both compounds RCB16003 and RCB16007 demonstrate selectivity for YFV over related viruses, with only RCB16007 showing some inhibition of the West Nile virus (EC50 7.9 μM, CC50 17 μM, SI 2.2). We also describe the absorption, distribution, metabolism, and excretion (ADME) in vitro and pharmacokinetics (PK) for RCB16007 in mice. This compound had previously been shown to not inhibit hERG, and we now describe that it has good metabolic stability in mouse and human liver microsomes, low levels of CYP inhibition, high protein binding, and no indication of efflux in Caco-2 cells. A single-dose oral PK study in mice has a T1/2 of 3.4 h and Cmax of 1190 ng/mL, suggesting good availability and stability. We now propose that the N-phenyl-1-(phenylsulfonyl)-1H-1,2,4-triazol-3-amine class may be prioritized for in vivo efficacy testing against YFV.

Atom-Based Machine Learning Model for Quantitative Property-Structure Relationship of Electronic Properties of Fusenes and Substituted Fusenes

This study presents the development of machine-learning-based quantitative structure-property relationship (QSPR) models for predicting electron affinity, ionization potential, and band gap of fusenes from different chemical classes. Three variants of the atom-based Weisfeiler-Lehman (WL) graph kernel method and the machine learning model Gaussian process regressor (GPR) were used. The data pool comprises polycyclic aromatic hydrocarbons (PAHs), thienoacenes, cyano-substituted PAHs, and nitro-substituted PAHs computed with density functional theory (DFT) at the B3LYP-D3/6-31+G(d) level of theory. The results demonstrate that the GPR/WL kernel methods can accurately predict the electronic properties of PAHs and their derivatives with root-mean-square deviations of 0.15 eV. Additionally, we also demonstrate the effectiveness of the active learning protocol for the GPR/WL kernel methods pipeline, particularly for data sets with greater diversity. The interpretation of the model for contributions of individual atoms to the predicted electronic properties provides reasons for the success of our previous degree of π-orbital overlap model.

"Freedom of design" in chemical compound space: towards rational in silico design of molecules with targeted quantum-mechanical properties

The rational design of molecules with targeted quantum-mechanical (QM) properties requires an advanced understanding of the structure-property/property-property relationships (SPR/PPR) that exist across chemical compound space (CCS). In this work, we analyze these fundamental relationships in the sector of CCS spanned by small (primarily organic) molecules using the recently developed QM7-X dataset, a systematic, extensive, and tightly converged collection of 42 QM properties corresponding to ≈4.2M equilibrium and non-equilibrium molecular structures containing up to seven heavy/non-hydrogen atoms (including C, N, O, S, and Cl). By characterizing and enumerating progressively more complex manifolds of molecular property space-the corresponding high-dimensional space defined by the properties of each molecule in this sector of CCS-our analysis reveals that one has a substantial degree of flexibility or "freedom of design" when searching for a single molecule with a desired pair of properties or a set of distinct molecules sharing an array of properties. To explore how this intrinsic flexibility manifests in the molecular design process, we used multi-objective optimization to search for molecules with simultaneously large polarizabilities and HOMO-LUMO gaps; analysis of the resulting Pareto fronts identified non-trivial paths through CCS consisting of sequential structural and/or compositional changes that yield molecules with optimal combinations of these properties.

Learning from COVID-19: How drug hunters can prepare for the next pandemic

Over 3 years, the SARS-CoV-2 pandemic killed nearly 7 million people and infected more than 767 million globally. During this time, our very small company was able to contribute to antiviral drug discovery efforts through global collaborations with other researchers, which enabled the identification and repurposing of multiple molecules with activity against SARS-CoV-2 including pyronaridine tetraphosphate, tilorone, quinacrine, vandetanib, lumefantrine, cetylpyridinium chloride, raloxifene, carvedilol, olmutinib, dacomitinib, crizotinib, and bosutinib. We highlight some of the key findings from this experience of using different computational and experimental strategies, and detail some of the challenges and strategies for how we might better prepare for the next pandemic so that potential antiviral treatments are available for future outbreaks.

Development of machine learning models based on molecular fingerprints for selection of small molecule inhibitors against JAK2 protein

Janus kinase 2 (JAK2) is emerging as a potential therapeutic target for many inflammatory diseases such as myeloproliferative disorders (MPD), cancer and rheumatoid arthritis (RA). In this study, we have collected experimental data of JAK2 protein containing 6021 unique inhibitors. We then characterized them based on Morgan (ECFP6) fingerprints followed by clustering into training and test set based on their molecular scaffolds. These data were used to build the classification models with various supervised machine learning (ML) algorithms that could prioritize novel inhibitors for future drug development against JAK2 protein. The best model built by Random Forest (RF) and Morgan fingerprints achieved the G-mean value of 0.84 on the external test set. As an application of our classification model, virtual screening was performed against Drugbank molecules in order to identify the potential inhibitors based on the confidence score by RF model. Nine potential molecules were identified, which were further subject to molecular docking studies to evaluate the virtual screening results of the best RF model. This proposed method can prove useful for developing novel target-specific JAK2 inhibitors.

Novel computational pipelines in antiviral structure‑based drug design (Review)

Viral infections constitute a fundamental and continuous challenge for the global scientific and medical community, as highlighted by the ongoing COVID-19 pandemic. In combination with prophylactic vaccines, the development of safe and effective antiviral drugs remains a pressing need for the effective management of rare and common pathogenic viruses. The design of potent antivirals can be informed by the study of the three-dimensional structure of viral protein targets. Structure-based design of antivirals in silico provides a solution to the arduous and costly process of conventional drug development pipelines. Furthermore, rapid advances in high-throughput computing, along with the growth of available biomolecular and biochemical data, enable the development of novel computational pipelines in the hunt of antivirals. The incorporation of modern methods, such as deep-learning and artificial intelligence, has the potential to revolutionize the structure-based design and repurposing of antiviral compounds, with minimal side effects and high efficacy. The present review aims to provide an outline of both traditional computational drug design and emerging, high-level computing strategies.

The Commoditization of AI for Molecule Design

Anyone involved in designing or finding molecules in the life sciences over the past few years has witnessed a dramatic change in how we now work due to the COVID-19 pandemic. Computational technologies like artificial intelligence (AI) seemed to become ubiquitous in 2020 and have been increasingly applied as scientists worked from home and were separated from the laboratory and their colleagues. This shift may be more permanent as the future of molecule design across different industries will increasingly require machine learning models for design and optimization of molecules as they become "designed by AI". AI and machine learning has essentially become a commodity within the pharmaceutical industry. This perspective will briefly describe our personal opinions of how machine learning has evolved and is being applied to model different molecule properties that crosses industries in their utility and ultimately suggests the potential for tight integration of AI into equipment and automated experimental pipelines. It will also describe how many groups have implemented generative models covering different architectures, for de novo design of molecules. We also highlight some of the companies at the forefront of using AI to demonstrate how machine learning has impacted and influenced our work. Finally, we will peer into the future and suggest some of the areas that represent the most interesting technologies that may shape the future of molecule design, highlighting how we can help increase the efficiency of the design-make-test cycle which is currently a major focus across industries.

Tuning gradient boosting for imbalanced bioassay modelling with custom loss functions

While in the last years there has been a dramatic increase in the number of available bioassay datasets, many of them suffer from extremely imbalanced distribution between active and inactive compounds. Thus, there is an urgent need for novel approaches to tackle class imbalance in drug discovery. Inspired by recent advances in computer vision, we investigated a panel of alternative loss functions for imbalanced classification in the context of Gradient Boosting and benchmarked them on six datasets from public and proprietary sources, for a total of 42 tasks and 2 million compounds. Our findings show that with these modifications, we achieve statistically significant improvements over the conventional cross-entropy loss function on five out of six datasets. Furthermore, by employing these bespoke loss functions we are able to push Gradient Boosting to match or outperform a wide variety of previously reported classifiers and neural networks. We also investigate the impact of changing the loss function on training time and find that it increases convergence speed up to 8 times faster. As such, these results show that tuning the loss function for Gradient Boosting is a straightforward and computationally efficient method to achieve state-of-the-art performance on imbalanced bioassay datasets without compromising on interpretability and scalability.

Graphical Abstract

Bis(Benzofuran-1,3-N,N-heterocycle)s as Symmetric and Synthetic Drug Leads against Yellow Fever Virus

The yellow fever virus (YFV) is an emerging RNA virus and has caused large outbreaks in Africa and Central and South America. The virus is often transmitted through infected mosquitoes and spreads from area to area because of international travel. Being an acute viral hemorrhagic disease, yellow fever can be prevented by an effective, safe, and reliable vaccine, but not be eliminated. Currently, there is no antiviral drug available for its cure. Thus, two series of novel bis(benzofuran−1,3-imidazolidin-4-one)s and bis(benzofuran−1,3-benzimidazole)s were designed and synthesized for the development of anti-YFV lead candidates. Among 23 new bis-conjugated compounds, 4 of them inhibited YFV strain 17D (Stamaril) on Huh-7 cells in the cytopathic effect reduction assays. These conjugates exhibited the most compelling efficacy and selectivity with an EC50 of <3.54 μM and SI of >15.3. The results are valuable for the development of novel antiviral drug leads against emerging diseases.

Feasibility and application of machine learning enabled fast screening of poly-beta-amino-esters for cartilage therapies

Despite the large prevalence of diseases affecting cartilage (e.g. knee osteoarthritis affecting 16% of population globally), no curative treatments are available because of the limited capacity of drugs to localise in such tissue caused by low vascularisation and electrostatic repulsion. While an effective delivery system is sought, the only option is using high drug doses that can lead to systemic side effects. We introduced poly-beta-amino-esters (PBAEs) to effectively deliver drugs into cartilage tissues. PBAEs are copolymer of amines and di-acrylates further end-capped with other amine; therefore encompassing a very large research space for the identification of optimal candidates. In order to accelerate the screening of all possible PBAEs, the results of a small pool of polymers (n = 90) were used to train a variety of machine learning (ML) methods using only polymers properties available in public libraries or estimated from the chemical structure. Bagged multivariate adaptive regression splines (MARS) returned the best predictive performance and was used on the remaining (n = 3915) possible PBAEs resulting in the recognition of pivotal features; a further round of screening was carried out on PBAEs (n = 150) with small variations of structure of the main candidates from the first round. The refinements of such characteristics enabled the identification of a leading candidate predicted to improve drug uptake > 20 folds over conventional clinical treatment; this uptake improvement was also experimentally confirmed. This work highlights the potential of ML to accelerate biomaterials development by efficiently extracting information from a limited experimental dataset thus allowing patients to benefit earlier from a new technology and at a lower price. Such roadmap could also be applied for other drug/materials development where optimisation would normally be approached through combinatorial chemistry.