Discovery of SARS-CoV-2 main protease inhibitors using a synthesis-directed de novo design model

AI in cellular engineering and reprogramming

During the last decade, artificial intelligence (AI) has increasingly been applied in biophysics and related fields, including cellular engineering and reprogramming, offering novel approaches to understand, manipulate, and control cellular function. The potential of AI lies in its ability to analyze complex datasets and generate predictive models. AI algorithms can process large amounts of data from single-cell genomics and multiomic technologies, allowing researchers to gain mechanistic insights into the control of cell identity and function. By integrating and interpreting these complex datasets, AI can help identify key molecular events and regulatory pathways involved in cellular reprogramming. This knowledge can inform the design of precision engineering strategies, such as the development of new transcription factor and signaling molecule cocktails, to manipulate cell identity and drive authentic cell fate across lineage boundaries. Furthermore, when used in combination with computational methods, AI can accelerate and improve the analysis and understanding of the intricate relationships between genes, proteins, and cellular processes. In this review article, we explore the current state of AI applications in biophysics with a specific focus on cellular engineering and reprogramming. Then, we showcase a couple of recent applications where we combined machine learning with experimental and computational techniques. Finally, we briefly discuss the challenges and prospects of AI in cellular engineering and reprogramming, emphasizing the potential of these technologies to revolutionize our ability to engineer cells for a variety of applications, from disease modeling and drug discovery to regenerative medicine and biomanufacturing.

Deconvoluting low yield from weak potency in direct-to-biology workflows with machine learning

High throughput and rapid biological evaluation of small molecules is an essential factor in drug discovery and development. Direct-to-biology (D2B), whereby compound purification is foregone, has emerged as a viable technique in time efficient screening, specifically for PROTAC design and biological evaluation. However, one notable limitation is the prerequisite of high yielding reactions to ensure the desired compound is indeed the compound responsible for biological activity. Herein, we report a machine learning based yield-assay deconfounder capable of deconvoluting low yield from low potency to identify false negatives. We validated this approach by identifying promising SARS-CoV-2 main protease inhibitors with nanomolar activity that rivaled potency observed from the standard D2B workflow. Furthermore, we show how our framework can be utilized in a broad, in silico screen to produce compounds of similar potency as a D2B assay.

Fragment-based screening targeting an open form of the SARS-CoV-2 main protease binding pocket

To identify starting points for therapeutics targeting SARS-CoV-2, the Paul Scherrer Institute and Idorsia decided to collaboratively perform an X-ray crystallographic fragment screen against its main protease. Fragment-based screening was carried out using crystals with a pronounced open conformation of the substrate-binding pocket. Of 631 soaked fragments, a total of 29 hits bound either in the active site (24 hits), a remote binding pocket (three hits) or at crystal-packing interfaces (two hits). Notably, two fragments with a pose that was sterically incompatible with a more occluded crystal form were identified. Two isatin-based electrophilic fragments bound covalently to the catalytic cysteine residue. The structures also revealed a surprisingly strong influence of the crystal form on the binding pose of three published fragments used as positive controls, with implications for fragment screening by crystallography.

On the origins of SARS-CoV-2 main protease inhibitors

In order to address the world-wide health challenge caused by the COVID-19 pandemic, the 3CL protease/SARS-CoV-2 main protease (SARS-CoV-2-Mpro) coded by its nsp5 gene became one of the biochemical targets for the design of antiviral drugs. In less than 3 years of research, 4 inhibitors of SARS-CoV-2-Mpro have actually been authorized for COVID-19 treatment (nirmatrelvir, ensitrelvir, leritrelvir and simnotrelvir) and more such as EDP-235, FB-2001 and STI-1558/Olgotrelvir or five undisclosed compounds (CDI-988, ASC11, ALG-097558, QLS1128 and H-10517) are undergoing clinical trials. This review is an attempt to picture this quite unprecedented medicinal chemistry feat and provide insights on how these cysteine protease inhibitors were discovered. Since many series of covalent SARS-CoV-2-Mpro inhibitors owe some of their origins to previous work on other proteases, we first provided a description of various inhibitors of cysteine-bearing human caspase-1 or cathepsin K, as well as inhibitors of serine proteases such as human dipeptidyl peptidase-4 or the hepatitis C protein complex NS3/4A. This is then followed by a description of the results of the approaches adopted (repurposing, structure-based and high throughput screening) to discover coronavirus main protease inhibitors.

Medicinal chemistry strategies towards the development of non-covalent SARS-CoV-2 Mpro inhibitors

The main protease (Mpro) of SARS-CoV-2 is an attractive target in anti-COVID-19 therapy for its high conservation and major role in the virus life cycle. The covalent Mpro inhibitor nirmatrelvir (in combination with ritonavir, a pharmacokinetic enhancer) and the non-covalent inhibitor ensitrelvir have shown efficacy in clinical trials and have been approved for therapeutic use. Effective antiviral drugs are needed to fight the pandemic, while non-covalent Mpro inhibitors could be promising alternatives due to their high selectivity and favorable druggability. Numerous non-covalent Mpro inhibitors with desirable properties have been developed based on available crystal structures of Mpro. In this article, we describe medicinal chemistry strategies applied for the discovery and optimization of non-covalent Mpro inhibitors, followed by a general overview and critical analysis of the available information. Prospective viewpoints and insights into current strategies for the development of non-covalent Mpro inhibitors are also discussed.

Open science discovery of potent noncovalent SARS-CoV-2 main protease inhibitors

We report the results of the COVID Moonshot, a fully open-science, crowdsourced, and structure-enabled drug discovery campaign targeting the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) main protease. We discovered a noncovalent, nonpeptidic inhibitor scaffold with lead-like properties that is differentiated from current main protease inhibitors. Our approach leveraged crowdsourcing, machine learning, exascale molecular simulations, and high-throughput structural biology and chemistry. We generated a detailed map of the structural plasticity of the SARS-CoV-2 main protease, extensive structure-activity relationships for multiple chemotypes, and a wealth of biochemical activity data. All compound designs (>18,000 designs), crystallographic data (>490 ligand-bound x-ray structures), assay data (>10,000 measurements), and synthesized molecules (>2400 compounds) for this campaign were shared rapidly and openly, creating a rich, open, and intellectual property-free knowledge base for future anticoronavirus drug discovery.

Discovery of PLpro and Mpro Inhibitors for SARS-CoV-2

There are very few small-molecule antivirals for SARS-CoV-2 that are either currently approved (or emergency authorized) in the US or globally, including remdesivir, molnupiravir, and paxlovid. The increasing number of SARS-CoV-2 variants that have appeared since the outbreak began over three years ago raises the need for continual development of updated vaccines and orally available antivirals in order to fully protect or treat the population. The viral main protease (Mpro) and the papain-like protease (PLpro) are key for viral replication; therefore, they represent valuable targets for antiviral therapy. We herein describe an in vitro screen performed using the 2560 compounds from the Microsource Spectrum library against Mpro and PLpro in an attempt to identify additional small-molecule hits that could be repurposed for SARS-CoV-2. We subsequently identified 2 hits for Mpro and 8 hits for PLpro. One of these hits was the quaternary ammonium compound cetylpyridinium chloride with dual activity (IC50 = 2.72 ± 0.09 μM for PLpro and IC50 = 7.25 ± 0.15 μM for Mpro). A second inhibitor of PLpro was the selective estrogen receptor modulator raloxifene (IC50 = 3.28 ± 0.29 μM for PLpro and IC50 = 42.8 ± 6.7 μM for Mpro). We additionally tested several kinase inhibitors and identified olmutinib (IC50 = 0.54 ± 0.04 μM), bosutinib (IC50 = 4.23 ± 0.28 μM), crizotinib (IC50 = 3.81 ± 0.04 μM), and dacominitinib (IC50 = IC50 3.33 ± 0.06 μM) as PLpro inhibitors for the first time. In some cases, these molecules have also been tested by others for antiviral activity for this virus, or we have used Calu-3 cells infected with SARS-CoV-2. The results suggest that approved drugs can be identified with promising activity against these proteases, and in several cases we or others have validated their antiviral activity. The additional identification of known kinase inhibitors as molecules targeting PLpro may provide new repurposing opportunities or starting points for chemical optimization.

Accelerating drug target inhibitor discovery with a deep generative foundation model

Inhibitor discovery for emerging drug-target proteins is challenging, especially when target structure or active molecules are unknown. Here, we experimentally validate the broad utility of a deep generative framework trained at-scale on protein sequences, small molecules, and their mutual interactions-unbiased toward any specific target. We performed a protein sequence-conditioned sampling on the generative foundation model to design small-molecule inhibitors for two dissimilar targets: the spike protein receptor-binding domain (RBD) and the main protease from SARS-CoV-2. Despite using only the target sequence information during the model inference, micromolar-level inhibition was observed in vitro for two candidates out of four synthesized for each target. The most potent spike RBD inhibitor exhibited activity against several variants in live virus neutralization assays. These results establish that a single, broadly deployable generative foundation model for accelerated inhibitor discovery is effective and efficient, even in the absence of target structure or binder information.

The Potential of Stilbene Compounds to Inhibit Mpro Protease as a Natural Treatment Strategy for Coronavirus Disease-2019

COVID-19 disease has had a global impact on human health with increased levels of morbidity and mortality. There is an unmet need to design and produce effective antivirals to treat COVID-19. This study aimed to explore the potential ability of natural stilbenes to inhibit the M^pro protease, an acute respiratory syndrome coronavirus-2 (SARS-CoV-2) enzyme involved in viral replication. The binding affinities of stilbene compounds against M^pro were scrutinized using molecular docking, prime molecular mechanics-generalized Born surface area (MM-GBSA) energy calculations, and molecular dynamic simulations. Seven stilbene molecules were docked with M^pro and compared with GC376 and N3, antivirals with demonstrated efficacy against M^pro. Ligand binding efficiencies and polar and non-polar interactions between stilbene compounds and M^pro were analyzed. The binding affinities of astringin, isorhapontin, and piceatannol were -9.319, -8.166, and -6.291 kcal/mol, respectively, and higher than either GC376 or N3 at -6.976 and -6.345 kcal/mol, respectively. Prime MM-GBSA revealed that these stilbene compounds exhibited useful ligand efficacy and binding affinity to M^pro. Molecular dynamic simulation studies of astringin, isorhapontin, and piceatannol showed their stability at 300 K throughout the simulation time. Collectively, these results suggest that stilbenes such as astringin, isorhapontin, and piceatannol could provide useful natural inhibitors of M^pro and thereby act as novel treatments to limit SARS-CoV-2 replication.

Viral proteases as therapeutic targets

Some medically important viruses-including retroviruses, flaviviruses, coronaviruses, and herpesviruses-code for a protease, which is indispensable for viral maturation and pathogenesis. Viral protease inhibitors have become an important class of antiviral drugs. Development of the first-in-class viral protease inhibitor saquinavir, which targets HIV protease, started a new era in the treatment of chronic viral diseases. Combining several drugs that target different steps of the viral life cycle enables use of lower doses of individual drugs (and thereby reduction of potential side effects, which frequently occur during long term therapy) and reduces drug-resistance development. Currently, several HIV and HCV protease inhibitors are routinely used in clinical practice. In addition, a drug including an inhibitor of SARS-CoV-2 main protease, nirmatrelvir (co-administered with a pharmacokinetic booster ritonavir as Paxlovid®), was recently authorized for emergency use. This review summarizes the basic features of the proteases of human immunodeficiency virus (HIV), hepatitis C virus (HCV), and SARS-CoV-2 and discusses the properties of their inhibitors in clinical use, as well as development of compounds in the pipeline.

Point mutations in SARS-CoV-2 variants induce long-range dynamical perturbations in neutralizing antibodies

Monoclonal antibodies are emerging as a viable treatment for the coronavirus disease 19 (COVID-19). However, newly evolved variants of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) can reduce the efficacy of currently available antibodies and can diminish vaccine-induced immunity. Here, we demonstrate that the microscopic dynamics of neutralizing monoclonal antibodies can be profoundly modified by the mutations present in the spike proteins of the SARS-COV-2 variants currently circulating in the world population. The dynamical perturbations within the antibody structure, which alter the thermodynamics of antigen recognition, are diverse and can depend both on the nature of the antibody and on the spatial location of the spike mutation. The correlation between the motion of the antibody and that of the spike receptor binding domain (RBD) can also be changed, modulating binding affinity. Using protein-graph-connectivity networks, we delineated the mutant-induced modifications in the information-flow along allosteric pathway throughout the antibody. Changes in the collective dynamics were spatially distributed both locally and across long-range distances within the antibody. On the receptor side, we identified an anchor-like structural element that prevents the detachment of the antibodies; individual mutations there can significantly affect the antibody binding propensity. Our study provides insight into how virus neutralization by monoclonal antibodies can be impacted by local mutations in the epitope via a change in dynamics. This realization adds a new layer of sophistication to the efforts for rational design of monoclonal antibodies against new variants of SARS-CoV2, taking the allostery in the antibody into consideration.

Mutations in the new variants of SARS-CoV-2 spike protein modulates the dynamics of the neutralizing antibodies. Capturing such modulations from MD simulations and graph network model identifies the role of mutations in facilitating immune evasion.

Machine learning approaches for biomolecular, biophysical, and biomaterials research

A fluent conversation with a virtual assistant, person-tailored news feeds, and deep-fake images created within seconds-all those things that have been unthinkable for a long time are now a part of our everyday lives. What these examples have in common is that they are realized by different means of machine learning (ML), a technology that has fundamentally changed many aspects of the modern world. The possibility to process enormous amount of data in multi-hierarchical, digital constructs has paved the way not only for creating intelligent systems but also for obtaining surprising new insight into many scientific problems. However, in the different areas of biosciences, which typically rely heavily on the collection of time-consuming experimental data, applying ML methods is a bit more challenging: Here, difficulties can arise from small datasets and the inherent, broad variability, and complexity associated with studying biological objects and phenomena. In this Review, we give an overview of commonly used ML algorithms (which are often referred to as "machines") and learning strategies as well as their applications in different bio-disciplines such as molecular biology, drug development, biophysics, and biomaterials science. We highlight how selected research questions from those fields were successfully translated into machine readable formats, discuss typical problems that can arise in this context, and provide an overview of how to resolve those encountered difficulties.

Defining Levels of Automated Chemical Design

One application area of computational methods in drug discovery is the automated design of small molecules. Despite the large number of publications describing methods and their application in both retrospective and prospective studies, there is a lack of agreement on terminology and key attributes to distinguish these various systems. We introduce Automated Chemical Design (ACD) Levels to clearly define the level of autonomy along the axes of ideation and decision making. To fully illustrate this framework, we provide literature exemplars and place some notable methods and applications into the levels. The ACD framework provides a common language for describing automated small molecule design systems and enables medicinal chemists to better understand and evaluate such systems.

Bat coronaviruses related to SARS-CoV-2: what about their 3CL proteases (MPro)?

Despite a huge effort by the scientific community to determine the animal reservoir of SARS-CoV-2, which led to the identification of several SARS-CoV-2-related viruses both in bats and in pangolins, the origin of SARS-CoV-2 is still not clear. Recently, Temmam et al. reported the discovery of bat coronaviruses with a high degree of genome similarity with SARS-CoV-2, especially concerning the RBDs of the S protein, which mediates the capability of such viruses to enter and therefore infect human cells through a hACE2-dependent pathway. These viruses, especially the one named BANAL-236, showed a higher affinity for the hACE2 compared to the original strain of SARS-CoV-2. In the present work, we analyse the similarities and differences between the 3CL protease (main protease, M^pro) of these newly reported viruses and SARS-CoV-2, discussing their relevance relative to the efficacy of existing therapeutic approaches against COVID-19, particularly concerning the recently approved orally available Paxlovid, and the development of future ones.

Computationally driven discovery of SARS-CoV-2 Mpro inhibitors: from design to experimental validation

We report a fast-track computationally driven discovery of new SARS-CoV-2 main protease (M^pro) inhibitors whose potency ranges from mM for the initial non-covalent ligands to sub-μM for the final covalent compound (IC₅₀ = 830 ± 50 nM). The project extensively relied on high-resolution all-atom molecular dynamics simulations and absolute binding free energy calculations performed using the polarizable AMOEBA force field. The study is complemented by extensive adaptive sampling simulations that are used to rationalize the different ligand binding poses through the explicit reconstruction of the ligand–protein conformation space. Machine learning predictions are also performed to predict selected compound properties. While simulations extensively use high performance computing to strongly reduce the time-to-solution, they were systematically coupled to nuclear magnetic resonance experiments to drive synthesis and for in vitro characterization of compounds. Such a study highlights the power of in silico strategies that rely on structure-based approaches for drug design and allows the protein conformational multiplicity problem to be addressed. The proposed fluorinated tetrahydroquinolines open routes for further optimization of M^pro inhibitors towards low nM affinities.

The dominant binding mode of the QUB-00006-Int-07 main protease inhibitor during absolute binding free energy simulations.

Artificial Intelligence Technologies for COVID-19 De Novo Drug Design

The recent covid crisis has provided important lessons for academia and industry regarding digital reorganization. Among the fascinating lessons from these times is the huge potential of data analytics and artificial intelligence. The crisis exponentially accelerated the adoption of analytics and artificial intelligence, and this momentum is predicted to continue into the 2020s and beyond. Drug development is a costly and time-consuming business, and only a minority of approved drugs generate returns exceeding the research and development costs. As a result, there is a huge drive to make drug discovery cheaper and faster. With modern algorithms and hardware, it is not too surprising that the new technologies of artificial intelligence and other computational simulation tools can help drug developers. In only two years of covid research, many novel molecules have been designed/identified using artificial intelligence methods with astonishing results in terms of time and effectiveness. This paper reviews the most significant research on artificial intelligence in de novo drug design for COVID-19 pharmaceutical research.

Stopping pandemics before they start: Lessons learned from SARS-CoV-2

The vaccine and drug discovery responses to COVID-19 have worked far better than could have been imagined. Yet by the end of 2021, more than 5 million people had died, and the pandemic continues to evolve and rage globally. This Review will describe how each of the vaccines, antibody therapies, and antiviral drugs that have been approved to date were built on decades of investment in technology and basic science. We will caution that the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus has so far proven a straightforward test of our pandemic preparedness, and we will recommend steps we should undertake now to prepare for, to minimize the effects of, and ideally to prevent future pandemics. Other Reviews in this series describe the interactions of SARS-CoV-2 with the immune system and those therapies that target the host response to infection.

High-Throughput Virtual Screening and Validation of a SARS-CoV-2 Main Protease Noncovalent Inhibitor

Despite the recent availability of vaccines against the acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the search for inhibitory therapeutic agents has assumed importance especially in the context of emerging new viral variants. In this paper, we describe the discovery of a novel noncovalent small-molecule inhibitor, MCULE-5948770040, that binds to and inhibits the SARS-Cov-2 main protease (Mpro) by employing a scalable high-throughput virtual screening (HTVS) framework and a targeted compound library of over 6.5 million molecules that could be readily ordered and purchased. Our HTVS framework leverages the U.S. supercomputing infrastructure achieving nearly 91% resource utilization and nearly 126 million docking calculations per hour. Downstream biochemical assays validate this Mpro inhibitor with an inhibition constant (Ki) of 2.9 μM (95% CI 2.2, 4.0). Furthermore, using room-temperature X-ray crystallography, we show that MCULE-5948770040 binds to a cleft in the primary binding site of Mpro forming stable hydrogen bond and hydrophobic interactions. We then used multiple μs-time scale molecular dynamics (MD) simulations and machine learning (ML) techniques to elucidate how the bound ligand alters the conformational states accessed by Mpro, involving motions both proximal and distal to the binding site. Together, our results demonstrate how MCULE-5948770040 inhibits Mpro and offers a springboard for further therapeutic design.

Application of Artificial Intelligence in COVID-19 Diagnosis and Therapeutics

The coronavirus disease 2019 (COVID-19) pandemic began at the end of December 2019, giving rise to a high rate of infections and causing COVID-19-associated deaths worldwide. It was first reported in Wuhan, China, and since then, not only global leaders, organizations, and pharmaceutical/biotech companies, but also researchers, have directed their efforts toward overcoming this threat. The use of artificial intelligence (AI) has recently surged internationally and has been applied to diverse aspects of many problems. The benefits of using AI are now widely accepted, and many studies have shown great success in medical research on tasks, such as the classification, detection, and prediction of disease, or even patient outcome. In fact, AI technology has been actively employed in various ways in COVID-19 research, and several clinical applications of AI-equipped medical devices for the diagnosis of COVID-19 have already been reported. Hence, in this review, we summarize the latest studies that focus on medical imaging analysis, drug discovery, and therapeutics such as vaccine development and public health decision-making using AI. This survey clarifies the advantages of using AI in the fight against COVID-19 and provides future directions for tackling the COVID-19 pandemic using AI techniques.