AI-Accelerated Design of Targeted Covalent Inhibitors for SARS-CoV-2

Unsupervised Learning of Progress Coordinates during Weighted Ensemble Simulations: Application to NTL9 Protein Folding

A major challenge for many rare-event sampling strategies is the identification of progress coordinates that capture the slowest relevant motions. Machine-learning methods that can identify progress coordinates in an unsupervised manner have therefore been of great interest to the simulation community. Here, we developed a general method for identifying progress coordinates "on-the-fly" during weighted ensemble (WE) rare-event sampling via deep learning (DL) of outliers among sampled conformations. Our method identifies outliers in a latent space model of the system's sampled conformations that is periodically trained using a convolutional variational autoencoder. As a proof of principle, we applied our DL-enhanced WE method to simulate the NTL9 protein folding process. To enable rapid tests, our simulations propagated discrete-state synthetic molecular dynamics trajectories using a generative, fine-grained Markov state model. Results revealed that our on-the-fly DL of outliers enhanced the efficiency of WE by >3-fold in estimating the folding rate constant. Our efforts are a significant step forward in the unsupervised learning of slow coordinates during rare event sampling.

Targeted Covalent Modification Strategies for Drugging the Undruggable Targets

The term "undruggable" refers to proteins or other biological targets that have been historically challenging to target with conventional drugs or therapeutic strategies because of their structural, functional, or dynamic properties. Drugging such undruggable targets is essential to develop new therapies for diseases where current treatment options are limited or nonexistent. Thus, investigating methods to achieve such drugging is an important challenge in medicinal chemistry. Among the numerous methodologies for drug discovery, covalent modification of therapeutic targets has emerged as a transformative strategy. The covalent attachment of diverse functional molecules to targets provides a powerful platform for creating highly potent drugs and chemical tools as well the ability to provide valuable information on the structures and dynamics of undruggable targets. In this review, we summarize recent examples of chemical methods for the covalent modification of proteins and other biomolecules for the development of new therapeutics and to overcome drug discovery challenges and highlight how such methods contribute toward the drugging of undruggable targets. In particular, we focus on the use of covalent chemistry methods for the development of covalent drugs, target identification, drug screening, artificial modulation of post-translational modifications, cancer specific chemotherapies, and nucleic acid-based therapeutics.

CACTUS: Chemistry Agent Connecting Tool Usage to Science

Large language models (LLMs) have shown remarkable potential in various domains but often lack the ability to access and reason over domain-specific knowledge and tools. In this article, we introduce Chemistry Agent Connecting Tool-Usage to Science (CACTUS), an LLM-based agent that integrates existing cheminformatics tools to enable accurate and advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Gemma-7b, Falcon-7b, MPT-7b, Llama3-8b, and Mistral-7b, on a benchmark of thousands of chemistry questions. Our results demonstrate that CACTUS significantly outperforms baseline LLMs, with the Gemma-7b, Mistral-7b, and Llama3-8b models achieving the highest accuracy regardless of the prompting strategy used. Moreover, we explore the impact of domain-specific prompting and hardware configurations on model performance, highlighting the importance of prompt engineering and the potential for deploying smaller models on consumer-grade hardware without a significant loss in accuracy. By combining the cognitive capabilities of open-source LLMs with widely used domain-specific tools provided by RDKit, CACTUS can assist researchers in tasks such as molecular property prediction, similarity searching, and drug-likeness assessment.

Artificial intelligence-aiding lab-on-a-chip workforce designed oral [3.1.0] bi and [4.2.0] tricyclic catalytic interceptors inhibiting multiple SARS-CoV-2 protomers assisted by double-shell deep learning

While each massive pandemic has claimed the lives of millions of vulnerable populations over the centuries, one limitation exists: that the Edisonian approach (human-directed with trial errors) relies on repurposing pharmaceuticals, designing drugs, and herbal remedies with the violation of Lipinski's rule of five druglikeness. It may lead to adverse health effects with long-term health multimorbidity. Nevertheless, declining birth rates and aging populations will likely cause a shift in society due to a shortage of a scientific workforce to defend against the next pandemic incursion. The challenge of combating the ongoing post-COVID-19 pandemic has been exacerbated by the lack of gold standard drugs to deactivate multiple SARS-CoV-2 protein targets. Meanwhile, there are three FDA-approved antivirals, Remdesivir, Molnupiravir, and Paxlovid, with moderate clinical efficacy and drug resistance. There is a pressing need for additional antivirals and prepared omics technology to combat the current and future devastating coronavirus pandemics. While there is a limitation of existing contemporary inhibitors to deactivate viral RNA replication with minimal rotational bonds, one strategy is to create Lipinski inhibitors with less than 10 rotational bonds and precise halogen bond placement to destabilize multiple viral protomers. This work describes the efforts to design gold-standard oral inhibitors of bi- and tri-cyclic catalytic interceptors with electrophilic heads using double-shell deep learning. Here, KS1 with and KS2 compounds designed by lab-on-a-chip technology attain 5-fold novel filtered-Lipinski, GHOSE, VEBER, EGAN, and MUEGGE druglikeness. The graph neural network (GNN) relies on module-initiation, expansion, relabeling atom index, and termination (METORITE) iterations, while the deep neural network (DNN) engages pinning, extraction, convolution, pooling, and flattening (PROOF) operations. The cyclic compound's specific halogen atom location enhances the nitrile catalytic head, which deactivates several viral protein targets. Initiating this lab-on-a-chip that is not susceptible to the aging process for creating clinical compounds can leverage a new path to many valuable drugs with speedy oral drug discovery, especially to defend the loss of vulnerable population and prevent multimorbidity that is susceptible to hidden viral persistence in the continuing aging times.

Rational Design Problematics of Peptide Nucleic Acids as SARS-CoV-2 Inhibitors

The use of viral protein inhibitors has shown to be insufficiently effective in the case of highly variable SARS-CoV-2. In this work, we examined the possibility of designing agents that bind to a highly conserved region of coronavirus (+)RNA. We demonstrated that while the design of antisense RNAs is based on the complementary interaction of nitrogenous bases, it is possible to use semirigid docking methods in the case of unnatural peptide nucleic acids. The transition from N-(2-aminoethyl)glycine chain to a more conformationally rigid piperidine-containing backbone allowed us to significantly increase the affinity of structures to the target RNA.

Inhibitors of SARS-CoV-2 Main Protease (Mpro) as Anti-Coronavirus Agents

The main protease (Mpro) of SARS-CoV-2 is an essential enzyme that plays a critical part in the virus's life cycle, making it a significant target for developing antiviral drugs. The inhibition of SARS-CoV-2 Mpro has emerged as a promising approach for developing therapeutic agents to treat COVID-19. This review explores the structure of the Mpro protein and analyzes the progress made in understanding protein-ligand interactions of Mpro inhibitors. It focuses on binding kinetics, origin, and the chemical structure of these inhibitors. The review provides an in-depth analysis of recent clinical trials involving covalent and non-covalent inhibitors and emerging dual inhibitors targeting SARS-CoV-2 Mpro. By integrating findings from the literature and ongoing clinical trials, this review captures the current state of research into Mpro inhibitors, offering a comprehensive understanding of challenges and directions in their future development as anti-coronavirus agents. This information provides new insights and inspiration for medicinal chemists, paving the way for developing more effective Mpro inhibitors as novel COVID-19 therapies.

Native Mass Spectrometry Dissects the Structural Dynamics of an Allosteric Heterodimer of SARS-CoV-2 Nonstructural Proteins

Structure-based drug design, which relies on precise understanding of the target protein and its interaction with the drug candidate, is dramatically expedited by advances in computational methods for candidate prediction. Yet, the accuracy needs to be improved with more structural data from high throughput experiments, which are challenging to generate, especially for dynamic and weak associations. Herein, we applied native mass spectrometry (native MS) to rapidly characterize ligand binding of an allosteric heterodimeric complex of SARS-CoV-2 nonstructural proteins (nsp) nsp10 and nsp16 (nsp10/16), a complex essential for virus survival in the host and thus a desirable drug target. Native MS showed that the dimer is in equilibrium with monomeric states in solution. Consistent with the literature, well characterized small cosubstrate, RNA substrate, and product bind with high specificity and affinity to the dimer but not the free monomers. Unsuccessfully designed ligands bind indiscriminately to all forms. Using neutral gas collision, the nsp16 monomer with bound cosubstrate can be released from the holo dimer complex, confirming the binding to nsp16 as revealed by the crystal structure. However, we observed an unusual migration of the endogenous zinc ions bound to nsp10 to nsp16 after collisional dissociation. The metal migration can be suppressed by using surface collision with reduced precursor charge states, which presumably resulted in minimal gas-phase structural rearrangement and highlighted the importance of complementary techniques. With minimal sample input (∼μg), native MS can rapidly detect ligand binding affinities and locations in dynamic multisubunit protein complexes, demonstrating the potential of an "all-in-one" native MS assay for rapid structural profiling of protein-to-AI-based compound systems to expedite drug discovery.

Discovery of α-Ketoamide inhibitors of SARS-CoV-2 main protease derived from quaternized P1 groups

Although the SARS-CoV-2 pandemic has ended, multiple sporadic cases still exist, posing a request for more antivirals. The main protease (Mpro) of SARS-CoV-2, a key enzyme for viral replication, is an attractive target for drug development. Here, we report the discovery of a new potent α-ketoamide-containing Mpro inhibitor, N-((R)-1-cyclohexyl-2-(((R)-3-methoxy-1-oxo-1-((1-(2-oxo-2-((thiazol-2-ylmethyl)amino)acetyl)cyclobutyl)amino)propan-2-yl)amino)-2-oxoethyl)-4,4-difluorocyclohexane-1-carboxamide (20j). This compound presented promising enzymatic inhibitory activity against SARS-CoV-2 Mpro with an IC50 value of 19.0 nM, and an excellent antiviral activity in cell-based assay with an EC50 value of 138.1 nM. This novel covalent inhibitor may be used as a lead compound for subsequent drug discovery against SARS-CoV-2.

Non-Canonical Amino Acids in Analyses of Protease Structure and Function

All known organisms encode 20 canonical amino acids by base triplets in the genetic code. The cellular translational machinery produces proteins consisting mainly of these amino acids. Several hundred natural amino acids serve important functions in metabolism, as scaffold molecules, and in signal transduction. New side chains are generated mainly by post-translational modifications, while others have altered backbones, such as the β- or γ-amino acids, or they undergo stereochemical inversion, e.g., in the case of D-amino acids. In addition, the number of non-canonical amino acids has further increased by chemical syntheses. Since many of these non-canonical amino acids confer resistance to proteolytic degradation, they are potential protease inhibitors and tools for specificity profiling studies in substrate optimization and enzyme inhibition. Other applications include in vitro and in vivo studies of enzyme kinetics, molecular interactions and bioimaging, to name a few. Amino acids with bio-orthogonal labels are particularly attractive, enabling various cross-link and click reactions for structure-functional studies. Here, we cover the latest developments in protease research with non-canonical amino acids, which opens up a great potential, e.g., for novel prodrugs activated by proteases or for other pharmaceutical compounds, some of which have already reached the clinical trial stage.

Integrated data-driven and experimental approaches to accelerate lead optimization targeting SARS-CoV-2 main protease

Identification of potential therapeutic candidates can be expedited by integrating computational modeling with domain aware machine learning (ML) models followed by experimental validation in an iterative manner. Generative deep learning models can generate thousands of new candidates, however, their physiochemical and biochemical properties are typically not fully optimized. Using our recently developed deep learning models and a scaffold as a starting point, we generated tens of thousands of compounds for SARS-CoV-2 M^pro that preserve the core scaffold. We utilized and implemented several computational tools such as structural alert and toxicity analysis, high throughput virtual screening, ML-based 3D quantitative structure-activity relationships, multi-parameter optimization, and graph neural networks on generated candidates to predict biological activity and binding affinity in advance. As a result of these combined computational endeavors, eight promising candidates were singled out and put through experimental testing using Native Mass Spectrometry and FRET-based functional assays. Two of the tested compounds with quinazoline-2-thiol and acetylpiperidine core moieties showed IC[Formula: see text] values in the low micromolar range: [Formula: see text] [Formula: see text]M and 3.41±0.0015 [Formula: see text]M, respectively. Molecular dynamics simulations further highlight that binding of these compounds results in allosteric modulations within the chain B and the interface domains of the M^pro. Our integrated approach provides a platform for data driven lead optimization with rapid characterization and experimental validation in a closed loop that could be applied to other potential protein targets.

Triterpene Derivatives as Potential Inhibitors of the RBD Spike Protein from SARS-CoV-2: An In Silico Approach

The appearance of a new coronavirus, SARS-CoV-2, in 2019 kicked off an international public health emergency. Although rapid progress in vaccination has reduced the number of deaths, the development of alternative treatments to overcome the disease is still necessary. It is known that the infection begins with the interaction of the spike glycoprotein (at the virus surface) and the angiotensin-converting enzyme 2 cell receptor (ACE2). Therefore, a straightforward solution for promoting virus inhibition seems to be the search for molecules capable of abolishing such attachment. In this work, we tested 18 triterpene derivatives as potential inhibitors of SARS-CoV-2 against the receptor-binding domain (RBD) of the spike protein by means of molecular docking and molecular dynamics simulations, modeling the RBD S1 subunit from the X-ray structure of the RBD-ACE2 complex (PDB ID: 6M0J). Molecular docking revealed that at least three triterpene derivatives of each type (i.e., oleanolic, moronic and ursolic) present similar interaction energies as the reference molecule, i.e., glycyrrhizic acid. Molecular dynamics suggest that two compounds from oleanolic and ursolic acid, OA5 and UA2, can induce conformational changes capable of disrupting the RBD-ACE2 interaction. Finally, physicochemical and pharmacokinetic properties simulations revealed favorable biological activity as antivirals.