Predicting locations of cryptic pockets from single protein structures using the PocketMiner graph neural network

Databases of ligand-binding pockets and protein-ligand interactions

Many research groups and institutions have created a variety of databases curating experimental and predicted data related to protein-ligand binding. The landscape of available databases is dynamic, with new databases emerging and established databases becoming defunct. Here, we review the current state of databases that contain binding pockets and protein-ligand binding interactions. We have compiled a list of such databases, fifty-three of which are currently available for use. We discuss variation in how binding pockets are defined and summarize pocket-finding methods. We organize the fifty-three databases into subgroups based on goals and contents, and describe standard use cases. We also illustrate that pockets within the same protein are characterized differently across different databases. Finally, we assess critical issues of sustainability, accessibility and redundancy.

Comparative CO2 and SiO2 hydratase activity of an enzyme from the siliceous demosponge Suberitesdomuncula

Silicase, an enzyme that catalyzes the hydrolysis of silicon-oxygen bonds, is a crucial player in breaking down silicates into silicic acid, particularly in organisms like aquatic sponges with siliceous skeletons. Despite its significance, our understanding of silicase remains limited. This study comprehensively examines silicase from the demosponge Suberites domuncula, focusing on its kinetics toward CO2 as a substrate, as well as its silicase and esterase activity. It investigates inhibition and activation profiles with a range of inhibitors and activators belonging to various classes. By comparing its esterase activity to human carbonic anhydrase II, we gain insights into its enzymatic properties. Moreover, we investigate silicase's inhibition and activation profiles, providing valuable information for potential applications. We explore the evolutionary relationship of silicase with related enzymes, revealing potential functional roles in biological systems. Additionally, we propose a biochemical mechanism through three-dimensional modeling, shedding light on its catalytic mechanisms and structural features for both silicase activity and CO2 hydration. We highlight nature's utilization of enzymatic expertise in silica metabolism. This study enhances our understanding of silicase and contributes to broader insights into ecosystem functioning and Earth's geochemical cycles, emphasizing the intricate interplay between biology and the environment.

Exploring the Application of SiteMap and Site Finder for Focused Cryptic Pocket Identification

The characterization of cryptic pockets has been elusive, despite substantial efforts. Computational modeling approaches, such as molecular dynamics (MD) simulations, can provide atomic-level details of binding site motions and binding pathways. However, the time scale that MD can achieve at a reasonable cost often limits its application for cryptic pocket identification. Enhanced sampling techniques can improve the efficiency of MD simulations by focused sampling of important regions of the protein, but prior knowledge of the simulated system is required to define the appropriate coordinates. In the case of a novel, unknown cryptic pocket, such information is not available, limiting the application of enhanced sampling techniques for cryptic pocket identification. In this work, we explore the ability of SiteMap and Site Finder, widely used commercial packages for pocket identification, to detect focus points on the protein and further apply other advanced computational methods. The information gained from this analysis enables the use of computational modeling, including enhanced MD sampling techniques, to explore potential cryptic binding pockets suggested by SiteMap and Site Finder. Here, we examined SiteMap and Site Finder results on 136 known cryptic pockets from a combination of the PocketMiner dataset (a recently curated set of cryptic pockets), the Cryptosite Set (a classic set of cryptic pockets), and Natural killer group 2D (NKG2D, a protein target where a cryptic pocket is confirmed). Our findings demonstrate the application of existing, well-studied tools in efficiently mapping potential regions harboring cryptic pockets.

The Malaria Box molecules: a source for targeting the RBD and NTD cryptic pocket of the spike glycoprotein in SARS-CoV-2

CONTEXT

SARS-CoV-2, responsible for COVID-19, has led to over 500 million infections and more than 6 million deaths globally. There have been limited effective treatments available. The study aims to find a drug that can prevent the virus from entering host cells by targeting specific sites on the virus's spike protein.

METHOD

We examined 13,397 compounds from the Malaria Box library against two specific sites on the spike protein: the receptor-binding domain (RBD) and a predicted cryptic pocket. Using virtual screening, molecular docking, molecular dynamics, and MMPBSA techniques, they evaluated the stability of two compounds. TCMDC-124223 showed high stability and binding energy in the RBD, while TCMDC-133766 had better binding energy in the cryptic pocket. The study also identified that the interacting residues are conserved, which is crucial for addressing various virus variants. The findings provide insights into the potential of small molecules as drugs against the spike protein.

Leveraging Bidirectional Nature of Allostery To Inhibit Protein-Protein Interactions (PPIs): A Case Study of PCSK9-LDLR Interaction

The protein PCSK9 (proprotein convertase subtilisin/Kexin type 9) negatively regulates the recycling of LDLR (low-density lipoprotein receptor), leading to an elevated plasma level of LDL. Inhibition of PCSK9-LDLR interaction has emerged as a promising therapeutic strategy to manage hypercholesterolemia. However, the large interaction surface area between PCSK9 and LDLR makes it challenging to identify a small molecule competitive inhibitor. An alternative strategy would be to identify distal cryptic sites as targets for allosteric inhibitors that can remotely modulate PCSK9-LDLR interaction. Using several microseconds long molecular dynamics (MD) simulations, we demonstrate that on binding with LDLR, there is a significant conformational change (population shift) in a distal loop (residues 211-222) region of PCSK9. Consistent with the bidirectional nature of allostery, we establish a clear correlation between the loop conformation and the binding affinity with LDLR. Using a thermodynamic argument, we establish that the loop conformations predominantly present in the apo state of PCSK9 would have lower LDLR binding affinity, and they would be potential targets for designing allosteric inhibitors. We elucidate the molecular origin of the allosteric coupling between this loop and the LDLR binding interface in terms of the population shift in a set of salt bridges and hydrogen bonds. Overall, our work provides a general strategy toward identifying allosteric hotspots: compare the conformational ensemble of the receptor between the apo and bound states of the protein and identify distal conformational changes, if any. The inhibitors should be designed to bind and stabilize the apo-specific conformations.

AHoJ-DB: A PDB-wide assignment of apo & holo relationships based on individual protein-ligand interactions

A single protein structure is rarely sufficient to capture the conformational variability of a protein. Both bound and unbound (holo and apo) forms of a protein are essential for understanding its geometry and making meaningful comparisons. Nevertheless, docking or drug design studies often still consider only single protein structures in their holo form, which are for the most part rigid. With the recent explosion in the field of structural biology, large, curated datasets are urgently needed. Here, we use a previously developed application (AHoJ) to perform a comprehensive search for apo-holo pairs for 468,293 biologically relevant protein-ligand interactions across 27,983 proteins. In each search, the binding pocket is captured and mapped across existing structures within the same UniProt, and the mapped pockets are annotated as apo or holo, based on the presence or absence of ligands. We assemble the results into a database, AHoJ-DB (www.apoholo.cz/db), that captures the variability of proteins with identical sequences, thereby exposing the agents responsible for the observed differences in geometry. We report several metrics for each annotated pocket, and we also include binding pockets that form at the interface of multiple chains. Analysis of the database shows that about 24% of the binding sites occur at the interface of two or more chains and that less than 50% of the total binding sites processed have an apo form in the PDB. These results can be used to train and evaluate predictors, discover potentially druggable proteins, and reveal protein- and ligand-specific relationships that were previously obscured by intermittent or partial data. Availability: http://apoholo.cz/db.

Toward physics-based precision medicine: Exploiting protein dynamics to design new therapeutics and interpret variants

The goal of precision medicine is to utilize our knowledge of the molecular causes of disease to better diagnose and treat patients. However, there is a substantial mismatch between the small number of food and drug administration (FDA)-approved drugs and annotated coding variants compared to the needs of precision medicine. This review introduces the concept of physics-based precision medicine, a scalable framework that promises to improve our understanding of sequence-function relationships and accelerate drug discovery. We show that accounting for the ensemble of structures a protein adopts in solution with computer simulations overcomes many of the limitations imposed by assuming a single protein structure. We highlight studies of protein dynamics and recent methods for the analysis of structural ensembles. These studies demonstrate that differences in conformational distributions predict functional differences within protein families and between variants. Thanks to new computational tools that are providing unprecedented access to protein structural ensembles, this insight may enable accurate predictions of variant pathogenicity for entire libraries of variants. We further show that explicitly accounting for protein ensembles, with methods like alchemical free energy calculations or docking to Markov state models, can uncover novel lead compounds. To conclude, we demonstrate that cryptic pockets, or cavities absent in experimental structures, provide an avenue to target proteins that are currently considered undruggable. Taken together, our review provides a roadmap for the field of protein science to accelerate precision medicine.

Engineering extracellular electron transfer pathways of electroactive microorganisms by synthetic biology for energy and chemicals production

The excessive consumption of fossil fuels causes massive emission of CO2, leading to climate deterioration and environmental pollution. The development of substitutes and sustainable energy sources to replace fossil fuels has become a worldwide priority. Bio-electrochemical systems (BESs), employing redox reactions of electroactive microorganisms (EAMs) on electrodes to achieve a meritorious combination of biocatalysis and electrocatalysis, provide a green and sustainable alternative approach for bioremediation, CO2 fixation, and energy and chemicals production. EAMs, including exoelectrogens and electrotrophs, perform extracellular electron transfer (EET) (i.e., outward and inward EET), respectively, to exchange energy with the environment, whose rate determines the efficiency and performance of BESs. Therefore, we review the synthetic biology strategies developed in the last decade for engineering EAMs to enhance the EET rate in cell-electrode interfaces for facilitating the production of electricity energy and value-added chemicals, which include (1) progress in genetic manipulation and editing tools to achieve the efficient regulation of gene expression, knockout, and knockdown of EAMs; (2) synthetic biological engineering strategies to enhance the outward EET of exoelectrogens to anodes for electricity power production and anodic electro-fermentation (AEF) for chemicals production, including (i) broadening and strengthening substrate utilization, (ii) increasing the intracellular releasable reducing equivalents, (iii) optimizing c-type cytochrome (c-Cyts) expression and maturation, (iv) enhancing conductive nanowire biosynthesis and modification, (v) promoting electron shuttle biosynthesis, secretion, and immobilization, (vi) engineering global regulators to promote EET rate, (vii) facilitating biofilm formation, and (viii) constructing cell-material hybrids; (3) the mechanisms of inward EET, CO2 fixation pathway, and engineering strategies for improving the inward EET of electrotrophic cells for CO2 reduction and chemical production, including (i) programming metabolic pathways of electrotrophs, (ii) rewiring bioelectrical circuits for enhancing inward EET, and (iii) constructing microbial (photo)electrosynthesis by cell-material hybridization; (4) perspectives on future challenges and opportunities for engineering EET to develop highly efficient BESs for sustainable energy and chemical production. We expect that this review will provide a theoretical basis for the future development of BESs in energy harvesting, CO2 fixation, and chemical synthesis.

Protein dynamics underlying allosteric regulation

Allostery is the mechanism by which information and control are propagated in biomolecules. It regulates ligand binding, chemical reactions, and conformational changes. An increasing level of experimental resolution and control over allosteric mechanisms promises a deeper understanding of the molecular basis for life and powerful new therapeutics. In this review, we survey the literature for an up-to-date biological and theoretical understanding of protein allostery. By delineating five ways in which the energy landscape or the kinetics of a system may change to give rise to allostery, we aim to help the reader grasp its physical origins. To illustrate this framework, we examine three systems that display these forms of allostery: allosteric inhibitors of beta-lactamases, thermosensation of TRP channels, and the role of kinetic allostery in the function of kinases. Finally, we summarize the growing power of computational tools available to investigate the different forms of allostery presented in this review.

A journey from molecule to physiology and in silico tools for drug discovery targeting the transient receptor potential vanilloid type 1 (TRPV1) channel

The heat and capsaicin receptor TRPV1 channel is widely expressed in nerve terminals of dorsal root ganglia (DRGs) and trigeminal ganglia innervating the body and face, respectively, as well as in other tissues and organs including central nervous system. The TRPV1 channel is a versatile receptor that detects harmful heat, pain, and various internal and external ligands. Hence, it operates as a polymodal sensory channel. Many pathological conditions including neuroinflammation, cancer, psychiatric disorders, and pathological pain, are linked to the abnormal functioning of the TRPV1 in peripheral tissues. Intense biomedical research is underway to discover compounds that can modulate the channel and provide pain relief. The molecular mechanisms underlying temperature sensing remain largely unknown, although they are closely linked to pain transduction. Prolonged exposure to capsaicin generates analgesia, hence numerous capsaicin analogs have been developed to discover efficient analgesics for pain relief. The emergence of in silico tools offered significant techniques for molecular modeling and machine learning algorithms to indentify druggable sites in the channel and for repositioning of current drugs aimed at TRPV1. Here we recapitulate the physiological and pathophysiological functions of the TRPV1 channel, including structural models obtained through cryo-EM, pharmacological compounds tested on TRPV1, and the in silico tools for drug discovery and repositioning.

Improving structure-based protein-ligand affinity prediction by graph representation learning and ensemble learning

Predicting protein-ligand binding affinity presents a viable solution for accelerating the discovery of new lead compounds. The recent widespread application of machine learning approaches, especially graph neural networks, has brought new advancements in this field. However, some existing structure-based methods treat protein macromolecules and ligand small molecules in the same way and ignore the data heterogeneity, potentially leading to incomplete exploration of the biochemical information of ligands. In this work, we propose LGN, a graph neural network-based fusion model with extra ligand feature extraction to effectively capture local features and global features within the protein-ligand complex, and make use of interaction fingerprints. By combining the ligand-based features and interaction fingerprints, LGN achieves Pearson correlation coefficients of up to 0.842 on the PDBbind 2016 core set, compared to 0.807 when using the features of complex graphs alone. Finally, we verify the rationalization and generalization of our model through comprehensive experiments. We also compare our model with state-of-the-art baseline methods, which validates the superiority of our model. To reduce the impact of data similarity, we increase the robustness of the model by incorporating ensemble learning.

Genomics 2 Proteins portal: A resource and discovery tool for linking genetic screening outputs to protein sequences and structures

Recent advances in AI-based methods have revolutionized the field of structural biology. Concomitantly, high-throughput sequencing and functional genomics technologies have enabled the detection and generation of variants at an unprecedented scale. However, efficient tools and resources are needed to link these two disparate data types - to "map" variants onto protein structures, to better understand how the variation causes disease and thereby design therapeutics. Here we present the Genomics 2 Proteins Portal (G2P; g2p.broadinstitute.org/): a human proteome-wide resource that maps 19,996,443 genetic variants onto 42,413 protein sequences and 77,923 structures, with a comprehensive set of structural and functional features. Additionally, the G2P portal generalizes the capability of linking genomics to proteins beyond databases by allowing users to interactively upload protein residue-wise annotations (variants, scores, etc.) as well as the protein structure to establish the connection. The portal serves as an easy-to-use discovery tool for researchers and scientists to hypothesize the structure-function relationship between natural or synthetic variations and their molecular phenotype.

A Structure-Based Allosteric Modulator Design Paradigm

Importance: Allosteric drugs bound to topologically distal allosteric sites hold a substantial promise in modulating therapeutic targets deemed undruggable at their orthosteric sites. Traditionally, allosteric modulator discovery has predominantly relied on serendipitous high-throughput screening. Nevertheless, the landscape has undergone a transformative shift due to recent advancements in our understanding of allosteric modulation mechanisms, coupled with a significant increase in the accessibility of allosteric structural data. These factors have extensively promoted the development of various computational methodologies, especially for machine-learning approaches, to guide the rational design of structure-based allosteric modulators. Highlights: We here presented a comprehensive structure-based allosteric modulator design paradigm encompassing 3 critical stages: drug target acquisition, allosteric binding site, and modulator discovery. The recent advances in computational methods in each stage are encapsulated. Furthermore, we delve into analyzing the successes and obstacles encountered in the rational design of allosteric modulators. Conclusion: The structure-based allosteric modulator design paradigm holds immense potential for the rational design of allosteric modulators. We hope that this review would heighten awareness of the use of structure-based computational methodologies in advancing the field of allosteric drug discovery.

Computing allostery: from the understanding of biomolecular regulation and the discovery of cryptic sites to molecular design

The concept of allostery has become a central tenet in the study of biological systems. In parallel, the discovery of allosteric drugs is generating new opportunities to selectively modulate difficult targets involved in pathologic mechanisms. Molecular simulations can provide atomistically detailed insight into the processes involved in allosteric regulation and signaling, and at the same time, they have the potential to unveil regulatory hotspots or cryptic sites that are not immediately evident from the analysis of static structures. In this context, computational approaches should be able to connect the study of allosteric regulation at different scales to the possibility of leveraging this knowledge to expand the chemical space of new, active drugs. Here, we will discuss recent advances in the study of allosteric regulation via computational methods and connect the mechanistic knowledge generated to the possibility of designing new small molecules that can tweak the functions of their receptors.

Integrated Molecular Modeling and Machine Learning for Drug Design

Modern therapeutic development often involves several stages that are interconnected, and multiple iterations are usually required to bring a new drug to the market. Computational approaches have increasingly become an indispensable part of helping reduce the time and cost of the research and development of new drugs. In this Perspective, we summarize our recent efforts on integrating molecular modeling and machine learning to develop computational tools for modulator design, including a pocket-guided rational design approach based on AlphaSpace to target protein-protein interactions, delta machine learning scoring functions for protein-ligand docking as well as virtual screening, and state-of-the-art deep learning models to predict calculated and experimental molecular properties based on molecular mechanics optimized geometries. Meanwhile, we discuss remaining challenges and promising directions for further development and use a retrospective example of FDA approved kinase inhibitor Erlotinib to demonstrate the use of these newly developed computational tools.

Exploring Conformational Landscapes and Cryptic Binding Pockets in Distinct Functional States of the SARS-CoV-2 Omicron BA.1 and BA.2 Trimers: Mutation-Induced Modulation of Protein Dynamics and Network-Guided Prediction of Variant-Specific Allosteric Binding Sites

A significant body of experimental structures of SARS-CoV-2 spike trimers for the BA.1 and BA.2 variants revealed a considerable plasticity of the spike protein and the emergence of druggable binding pockets. Understanding the interplay of conformational dynamics changes induced by the Omicron variants and the identification of cryptic dynamic binding pockets in the S protein is of paramount importance as exploring broad-spectrum antiviral agents to combat the emerging variants is imperative. In the current study, we explore conformational landscapes and characterize the universe of binding pockets in multiple open and closed functional spike states of the BA.1 and BA.2 Omicron variants. By using a combination of atomistic simulations, a dynamics network analysis, and an allostery-guided network screening of binding pockets in the conformational ensembles of the BA.1 and BA.2 spike conformations, we identified all experimentally known allosteric sites and discovered significant variant-specific differences in the distribution of binding sites in the BA.1 and BA.2 trimers. This study provided a structural characterization of the predicted cryptic pockets and captured the experimentally known allosteric sites, revealing the critical role of conformational plasticity in modulating the distribution and cross-talk between functional binding sites. We found that mutational and dynamic changes in the BA.1 variant can induce the remodeling and stabilization of a known druggable pocket in the N-terminal domain, while this pocket is drastically altered and may no longer be available for ligand binding in the BA.2 variant. Our results predicted the experimentally known allosteric site in the receptor-binding domain that remains stable and ranks as the most favorable site in the conformational ensembles of the BA.2 variant but could become fragmented and less probable in BA.1 conformations. We also uncovered several cryptic pockets formed at the inter-domain and inter-protomer interface, including functional regions of the S2 subunit and stem helix region, which are consistent with the known role of pocket residues in modulating conformational transitions and antibody recognition. The results of this study are particularly significant for understanding the dynamic and network features of the universe of available binding pockets in spike proteins, as well as the effects of the Omicron-variant-specific modulation of preferential druggable pockets. The exploration of predicted druggable sites can present a new and previously underappreciated opportunity for therapeutic interventions for Omicron variants through the conformation-selective and variant-specific targeting of functional sites involved in allosteric changes.

Reconstructing the cytokine view for the multi-view prediction of COVID-19 mortality

BACKGROUND

Coronavirus disease 2019 (COVID-19) is a rapidly developing and sometimes lethal pulmonary disease. Accurately predicting COVID-19 mortality will facilitate optimal patient treatment and medical resource deployment, but the clinical practice still needs to address it. Both complete blood counts and cytokine levels were observed to be modified by COVID-19 infection. This study aimed to use inexpensive and easily accessible complete blood counts to build an accurate COVID-19 mortality prediction model. The cytokine fluctuations reflect the inflammatory storm induced by COVID-19, but their levels are not as commonly accessible as complete blood counts. Therefore, this study explored the possibility of predicting cytokine levels based on complete blood counts.

METHODS

We used complete blood counts to predict cytokine levels. The predictive model includes an autoencoder, principal component analysis, and linear regression models. We used classifiers such as support vector machine and feature selection models such as adaptive boost to predict the mortality of COVID-19 patients.

RESULTS

Complete blood counts and original cytokine levels reached the COVID-19 mortality classification area under the curve (AUC) values of 0.9678 and 0.9111, respectively, and the cytokine levels predicted by the feature set alone reached the classification AUC value of 0.9844. The predicted cytokine levels were more significantly associated with COVID-19 mortality than the original values.

CONCLUSIONS

Integrating the predicted cytokine levels and complete blood counts improved a COVID-19 mortality prediction model using complete blood counts only. Both the cytokine level prediction models and the COVID-19 mortality prediction models are publicly available at http://www.healthinformaticslab.org/supp/resources.php .

Targeted Protein Degradation: Advances, Challenges, and Prospects for Computational Methods

The therapeutic approach of targeted protein degradation (TPD) is gaining momentum due to its potentially superior effects compared with protein inhibition. Recent advancements in the biotech and pharmaceutical sectors have led to the development of compounds that are currently in human trials, with some showing promising clinical results. However, the use of computational tools in TPD is still limited, as it has distinct characteristics compared with traditional computational drug design methods. TPD involves creating a ternary structure (protein-degrader-ligase) responsible for the biological function, such as ubiquitination and subsequent proteasomal degradation, which depends on the spatial orientation of the protein of interest (POI) relative to E2-loaded ubiquitin. Modeling this structure necessitates a unique blend of tools initially developed for small molecules (e.g., docking) and biologics (e.g., protein-protein interaction modeling). Additionally, degrader molecules, particularly heterobifunctional degraders, are generally larger than conventional small molecule drugs, leading to challenges in determining drug-like properties like solubility and permeability. Furthermore, the catalytic nature of TPD makes occupancy-based modeling insufficient. TPD consists of multiple interconnected yet distinct steps, such as POI binding, E3 ligase binding, ternary structure interactions, ubiquitination, and degradation, along with traditional small molecule properties. A comprehensive set of tools is needed to address the dynamic nature of the induced proximity ternary complex and its implications for ubiquitination. In this Perspective, we discuss the current state of computational tools for TPD. We start by describing the series of steps involved in the degradation process and the experimental methods used to characterize them. Then, we delve into a detailed analysis of the computational tools employed in TPD. We also present an integrative approach that has proven successful for degrader design and its impact on project decisions. Finally, we examine the future prospects of computational methods in TPD and the areas with the greatest potential for impact.

W254 in furin functions as a molecular gate promoting anti-viral drug binding: Elucidation of putative drug tunneling and docking by non-equilibrium molecular dynamics

Furins are serine endoproteases that process precursor proteins into their biologically active forms, and they play essential roles in normal metabolism and disease presentation, including promoting expression of bacterial virulence factors and viral pathogenesis. Thus, furins represent vital targets for development of antimicrobial and antiviral therapeutics. Recent experimental evidence indicated that dichlorophenyl (DCP)-pyridine "BOS" drugs (e.g., BOS-318) competitively inhibit human furin by an induced-fit mechanism in which tryptophan W254 in the furin catalytic cleft (FCC) functions as a molecular gate, rotating nearly 180o through a steep energy barrier about its chi-1 dihedral to an "open" orientation, exposing a buried (i.e., cryptic) hydrophobic pocket 1. Once exposed, the non-polar DCP group of BOS-318, and similar halo-phenyl groups of analogs, enter the cryptic pocket, stabilizing drug binding. Here, we demonstrate flexible-receptor docking of BOS-318 (and various analogs) was unable to emulate the induced-fit motif, even when tryptophan was replaced with less bulky phenylalanine or glycine. While either substitution allowed access to the hydrophobic pocket for most ligands tested, optimal binding was observed only for W254, inferring a stabilizing effect of the indole sidechain. Furthermore, non-equilibrium steered molecular dynamics (sMD) in which the bound drugs (or their fragments) were extracted from the FCC did not cause closure of the open W254 gate, consistent with the thermodynamic stability of the open or closed W254 orientations. Finally, interactive molecular dynamics (iMD) revealed two putative conduits of drug entry and binding into the FCC, each coupled with W254 dihedral rotation and opening of the cryptic pocket. The iMD simulations further revealed ligand entry and binding in the FCC is likely driven in part by energy fluxes stemming from disruption and re-formation of ligand and protein solvation shells during drug migration from the solution phase into the FCC.

From Deep Mutational Mapping of Allosteric Protein Landscapes to Deep Learning of Allostery and Hidden Allosteric Sites: Zooming in on "Allosteric Intersection" of Biochemical and Big Data Approaches

The recent advances in artificial intelligence (AI) and machine learning have driven the design of new expert systems and automated workflows that are able to model complex chemical and biological phenomena. In recent years, machine learning approaches have been developed and actively deployed to facilitate computational and experimental studies of protein dynamics and allosteric mechanisms. In this review, we discuss in detail new developments along two major directions of allosteric research through the lens of data-intensive biochemical approaches and AI-based computational methods. Despite considerable progress in applications of AI methods for protein structure and dynamics studies, the intersection between allosteric regulation, the emerging structural biology technologies and AI approaches remains largely unexplored, calling for the development of AI-augmented integrative structural biology. In this review, we focus on the latest remarkable progress in deep high-throughput mining and comprehensive mapping of allosteric protein landscapes and allosteric regulatory mechanisms as well as on the new developments in AI methods for prediction and characterization of allosteric binding sites on the proteome level. We also discuss new AI-augmented structural biology approaches that expand our knowledge of the universe of protein dynamics and allostery. We conclude with an outlook and highlight the importance of developing an open science infrastructure for machine learning studies of allosteric regulation and validation of computational approaches using integrative studies of allosteric mechanisms. The development of community-accessible tools that uniquely leverage the existing experimental and simulation knowledgebase to enable interrogation of the allosteric functions can provide a much-needed boost to further innovation and integration of experimental and computational technologies empowered by booming AI field.

Discovery of a cryptic pocket in the AI-predicted structure of PPM1D phosphatase explains the binding site and potency of its allosteric inhibitors

Virtual screening is a widely used tool for drug discovery, but its predictive power can vary dramatically depending on how much structural data is available. In the best case, crystal structures of a ligand-bound protein can help find more potent ligands. However, virtual screens tend to be less predictive when only ligand-free crystal structures are available, and even less predictive if a homology model or other predicted structure must be used. Here, we explore the possibility that this situation can be improved by better accounting for protein dynamics, as simulations started from a single structure have a reasonable chance of sampling nearby structures that are more compatible with ligand binding. As a specific example, we consider the cancer drug target PPM1D/Wip1 phosphatase, a protein that lacks crystal structures. High-throughput screens have led to the discovery of several allosteric inhibitors of PPM1D, but their binding mode remains unknown. To enable further drug discovery efforts, we assessed the predictive power of an AlphaFold-predicted structure of PPM1D and a Markov state model (MSM) built from molecular dynamics simulations initiated from that structure. Our simulations reveal a cryptic pocket at the interface between two important structural elements, the flap and hinge regions. Using deep learning to predict the pose quality of each docked compound for the active site and cryptic pocket suggests that the inhibitors strongly prefer binding to the cryptic pocket, consistent with their allosteric effect. The predicted affinities for the dynamically uncovered cryptic pocket also recapitulate the relative potencies of the compounds (τ _b =0.70) better than the predicted affinities for the static AlphaFold-predicted structure (τ _b =0.42). Taken together, these results suggest that targeting the cryptic pocket is a good strategy for drugging PPM1D and, more generally, that conformations selected from simulation can improve virtual screening when limited structural data is available.

Accelerating Cryptic Pocket Discovery Using AlphaFold

Cryptic pockets, or pockets absent in ligand-free, experimentally determined structures, hold great potential as drug targets. However, cryptic pocket openings are often beyond the reach of conventional biomolecular simulations because certain cryptic pocket openings involve slow motions. Here, we investigate whether AlphaFold can be used to accelerate cryptic pocket discovery either by generating structures with open pockets directly or generating structures with partially open pockets that can be used as starting points for simulations. We use AlphaFold to generate ensembles for 10 known cryptic pocket examples, including five that were deposited after AlphaFold's training data were extracted from the PDB. We find that in 6 out of 10 cases AlphaFold samples the open state. For plasmepsin II, an aspartic protease from the causative agent of malaria, AlphaFold only captures a partial pocket opening. As a result, we ran simulations from an ensemble of AlphaFold-generated structures and show that this strategy samples cryptic pocket opening, even though an equivalent amount of simulations launched from a ligand-free experimental structure fails to do so. Markov state models (MSMs) constructed from the AlphaFold-seeded simulations quickly yield a free energy landscape of cryptic pocket opening that is in good agreement with the same landscape generated with well-tempered metadynamics. Taken together, our results demonstrate that AlphaFold has a useful role to play in cryptic pocket discovery but that many cryptic pockets may remain difficult to sample using AlphaFold alone.

Drug specificity and affinity are encoded in the probability of cryptic pocket opening in myosin motor domains

The design of compounds that can discriminate between closely related target proteins remains a central challenge in drug discovery. Specific therapeutics targeting the highly conserved myosin motor family are urgently needed as mutations in at least six of its members cause numerous diseases. Allosteric modulators, like the myosin-II inhibitor blebbistatin, are a promising means to achieve specificity. However, it remains unclear why blebbistatin inhibits myosin-II motors with different potencies given that it binds at a highly conserved pocket that is always closed in blebbistatin-free experimental structures. We hypothesized that the probability of pocket opening is an important determinant of the potency of compounds like blebbistatin. To test this hypothesis, we used Markov state models (MSMs) built from over 2 ms of aggregate molecular dynamics simulations with explicit solvent. We find that blebbistatin's binding pocket readily opens in simulations of blebbistatin-sensitive myosin isoforms. Comparing these conformational ensembles reveals that the probability of pocket opening correctly identifies which isoforms are most sensitive to blebbistatin inhibition and that docking against MSMs quantitatively predicts blebbistatin binding affinities (R²=0.82). In a blind prediction for an isoform (Myh7b) whose blebbistatin sensitivity was unknown, we find good agreement between predicted and measured IC50s (0.67 μM vs. 0.36 μM). Therefore, we expect this framework to be useful for the development of novel specific drugs across numerous protein targets.

Discovery of a cryptic pocket in the AI-predicted structure of PPM1D phosphatase explains the binding site and potency of its allosteric inhibitors

Virtual screening is a widely used tool for drug discovery, but its predictive power can vary dramatically depending on how much structural data is available. In the best case, crystal structures of a ligand-bound protein can help find more potent ligands. However, virtual screens tend to be less predictive when only ligand-free crystal structures are available, and even less predictive if a homology model or other predicted structure must be used. Here, we explore the possibility that this situation can be improved by better accounting for protein dynamics, as simulations started from a single structure have a reasonable chance of sampling nearby structures that are more compatible with ligand binding. As a specific example, we consider the cancer drug target PPM1D/Wip1 phosphatase, a protein that lacks crystal structures. High-throughput screens have led to the discovery of several allosteric inhibitors of PPM1D, but their binding mode remains unknown. To enable further drug discovery efforts, we assessed the predictive power of an AlphaFold-predicted structure of PPM1D and a Markov state model (MSM) built from molecular dynamics simulations initiated from that structure. Our simulations reveal a cryptic pocket at the interface between two important structural elements, the flap and hinge regions. Using deep learning to predict the pose quality of each docked compound for the active site and cryptic pocket suggests that the inhibitors strongly prefer binding to the cryptic pocket, consistent with their allosteric effect. The predicted affinities for the dynamically uncovered cryptic pocket also recapitulate the relative potencies of the compounds (τ_b = 0.70) better than the predicted affinities for the static AlphaFold-predicted structure (τ_b = 0.42). Taken together, these results suggest that targeting the cryptic pocket is a good strategy for drugging PPM1D and, more generally, that conformations selected from simulation can improve virtual screening when limited structural data is available.