Machine Learning of Allosteric Effects: The Analysis of Ligand-Induced Dynamics to Predict Functional Effects in TRAP1

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.

Unsupervised deep learning for molecular dynamics simulations: a novel analysis of protein-ligand interactions in SARS-CoV-2 Mpro

Molecular dynamics (MD) simulations, which are central to drug discovery, offer detailed insights into protein-ligand interactions. However, analyzing large MD datasets remains a challenge. Current machine-learning solutions are predominantly supervised and have data labelling and standardisation issues. In this study, we adopted an unsupervised deep-learning framework, previously benchmarked for rigid proteins, to study the more flexible SARS-CoV-2 main protease (Mpro). We ran MD simulations of Mpro with various ligands and refined the data by focusing on binding-site residues and time frames in stable protein conformations. The optimal descriptor chosen was the distance between the residues and the center of the binding pocket. Using this approach, a local dynamic ensemble was generated and fed into our neural network to compute Wasserstein distances across system pairs, revealing ligand-induced conformational differences in Mpro. Dimensionality reduction yielded an embedding map that correlated ligand-induced dynamics and binding affinity. Notably, the high-affinity compounds showed pronounced effects on the protein's conformations. We also identified the key residues that contributed to these differences. Our findings emphasize the potential of combining unsupervised deep learning with MD simulations to extract valuable information and accelerate drug discovery.

Predicting allosteric pockets in protein biological assemblages

MOTIVATION

Allostery enables changes to the dynamic behavior of a protein at distant positions induced by binding. Here, we present APOP, a new allosteric pocket prediction method, which perturbs the pockets formed in the structure by stiffening pairwise interactions in the elastic network across the pocket, to emulate ligand binding. Ranking the pockets based on the shifts in the global mode frequencies, as well as their mean local hydrophobicities, leads to high prediction success when tested on a dataset of allosteric proteins, composed of both monomers and multimeric assemblages.

RESULTS

Out of the 104 test cases, APOP predicts known allosteric pockets for 92 within the top 3 rank out of multiple pockets available in the protein. In addition, we demonstrate that APOP can also find new alternative allosteric pockets in proteins. Particularly interesting findings are the discovery of previously overlooked large pockets located in the centers of many protein biological assemblages; binding of ligands at these sites would likely be particularly effective in changing the protein's global dynamics.

AVAILABILITY AND IMPLEMENTATION

APOP is freely available as an open-source code (https://github.com/Ambuj-UF/APOP) and as a web server at https://apop.bb.iastate.edu/.

Machine learning and protein allostery

The fundamental biological importance and complexity of allosterically regulated proteins stem from their central role in signal transduction and cellular processes. Recently, machine-learning approaches have been developed and actively deployed to facilitate theoretical and experimental studies of protein dynamics and allosteric mechanisms. In this review, we survey recent developments in applications of machine-learning methods for studies of allosteric mechanisms, prediction of allosteric effects and allostery-related physicochemical properties, and allosteric protein engineering. We also review the applications of machine-learning strategies for characterization of allosteric mechanisms and drug design targeting SARS-CoV-2. Continuous development and task-specific adaptation of machine-learning methods for protein allosteric mechanisms will have an increasingly important role in bridging a wide spectrum of data-intensive experimental and theoretical technologies.

It's ok to be outnumbered - sub-stoichiometric modulation of homomeric protein complexes

An arsenal of molecular tools with increasingly diversified mechanisms of action is being developed by the scientific community to enable biological interrogation and pharmaceutical modulation of targets and pathways of ever increasing complexity. While most small molecules interact with the target of interest in a 1 : 1 relationship, a noteworthy number of recent examples were reported to bind in a sub-stoichiometric manner to a homomeric protein complex. This approach requires molecular understanding of the physiologically relevant protein assemblies and in-depth characterization of the compound's mechanism of action. The recent literature examples summarized here were selected to illustrate methods used to identify and characterize molecules with such mechanisms. The concept of one small molecule targeting a homomeric protein assembly is not new but the subject deserves renewed inspection in light of emerging technologies and increasingly diverse target biology, to ensure relevant in vitro systems are used and valuable compounds with potentially novel sub-stoichiometric mechanisms of action aren't overlooked.

Allostery: Allosteric Cancer Drivers and Innovative Allosteric Drugs

Here, we discuss the principles of allosteric activating mutations, propagation downstream of the signals that they prompt, and allosteric drugs, with examples from the Ras signaling network. We focus on Abl kinase where mutations shift the landscape toward the active, imatinib binding-incompetent conformation, likely resulting in the high affinity ATP outcompeting drug binding. Recent pharmacological innovation extends to allosteric inhibitor (GNF-5)-linked PROTAC, targeting Bcr-Abl1 myristoylation site, and broadly, allosteric heterobifunctional degraders that destroy targets, rather than inhibiting them. Designed chemical linkers in bifunctional degraders can connect the allosteric ligand that binds the target protein and the E3 ubiquitin ligase warhead anchor. The physical properties and favored conformational state of the engineered linker can precisely coordinate the distance and orientation between the target and the recruited E3. Allosteric PROTACs, noncompetitive molecular glues, and bitopic ligands, with covalent links of allosteric ligands and orthosteric warheads, increase the effective local concentration of productively oriented and placed ligands. Through covalent chemical or peptide linkers, allosteric drugs can collaborate with competitive drugs, degrader anchors, or other molecules of choice, driving innovative drug discovery.

Protein Function Analysis through Machine Learning

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein–ligand binding, including allosteric effects, protein–protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

Determination of Molecule Category of Ligands Targeting the Ligand-Binding Pocket of Nuclear Receptors with Structural Elucidation and Machine Learning

The mechanism of transcriptional activation/repression of the nuclear receptors (NRs) involves two main conformations of the NR protein, namely, the active (agonistic) and inactive (antagonistic) conformations. Binding of agonists or antagonists to the ligand-binding pocket (LBP) of NRs can regulate the downstream signaling pathways with different physiological effects. However, it is still hard to determine the molecular type of a LBP-bound ligand because both the agonists and antagonists bind to the same position of the protein. Therefore, it is necessary to develop precise and efficient methods to facilitate the discrimination of agonists and antagonists targeting the LBP of NRs. Here, combining structural and energetic analyses with machine-learning (ML) algorithms, we constructed a series of structure-based ML models to determine the molecular category of the LBP-bound ligands. We show that the proposed models work robustly and with high accuracy (ACC > 0.9) for determining the category of molecules derived from docking-based and crystallized poses. Furthermore, the models are also capable of determining the molecular category of ligands with dual opposite functions on different NRs (i.e., working as an agonist in one NR target, whereas functioning as an antagonist in another) with reasonable accuracy. The proposed method is expected to facilitate the determination of the molecular properties of ligands targeting the LBP of NRs with structural interpretation.

From single-omics to interactomics: How can ligand-induced perturbations modulate single-cell phenotypes?

Cells suffer from perturbations by different stimuli, which, consequently, rise to individual alterations in their profile and function that may end up affecting the tissue as a whole. This is no different if we consider the effect of a therapeutic agent on a biological system. As cells are exposed to external ligands their profile can change at different single-omics levels. Detecting how these changes take place through different sequencing technologies is key to a better understanding of the effects of therapeutic agents. Single-cell RNA-sequencing stands out as one of the most common approaches for cell profiling and perturbation analysis. As a result, single-cell transcriptomics data can be integrated with other omics data sources, such as proteomics and epigenomics data, to clarify the perturbation effects and mechanism at the cell level. Appropriate computational tools are key to process and integrate the available information. This chapter focuses on the recent advances on ligand-induced perturbation and single-cell omics computational tools and algorithms, their current limitations, and how the deluge of data can be used to improve the current process of drug research and development.

Differences in ligand-induced protein dynamics extracted from an unsupervised deep learning approach correlate with protein-ligand binding affinities

Prediction of protein–ligand binding affinity is a major goal in drug discovery. Generally, free energy gap is calculated between two states (e.g., ligand binding and unbinding). The energy gap implicitly includes the effects of changes in protein dynamics induced by ligand binding. However, the relationship between protein dynamics and binding affinity remains unclear. Here, we propose a method that represents ligand-binding-induced protein behavioral change with a simple feature that can be used to predict protein–ligand affinity. From unbiased molecular simulation data, an unsupervised deep learning method measures the differences in protein dynamics at a ligand-binding site depending on the bound ligands. A dimension reduction method extracts a dynamic feature that strongly correlates to the binding affinities. Moreover, the residues that play important roles in protein–ligand interactions are specified based on their contribution to the differences. These results indicate the potential for binding dynamics-based drug discovery.

Differences in ligand-induced protein dynamics extracted as a single feature from a deep learning-based analysis of MD simulations correlate with ligand binding affinity.

From Data to Knowledge: Systematic Review of Tools for Automatic Analysis of Molecular Dynamics Output

An increasing number of crystal structures available on one side, and the boost of computational power available for computer-aided drug design tasks on the other, have caused that the structure-based drug design tools are intensively used in the drug development pipelines. Docking and molecular dynamics simulations, key representatives of the structure-based approaches, provide detailed information about the potential interaction of a ligand with a target receptor. However, at the same time, they require a three-dimensional structure of a protein and a relatively high amount of computational resources. Nowadays, as both docking and molecular dynamics are much more extensively used, the amount of data output from these procedures is also growing. Therefore, there are also more and more approaches that facilitate the analysis and interpretation of the results of structure-based tools. In this review, we will comprehensively summarize approaches for handling molecular dynamics simulations output. It will cover both statistical and machine-learning-based tools, as well as various forms of depiction of molecular dynamics output.

New perspectives in cancer drug development: computational advances with an eye to design

Computational chemistry has come of age in drug discovery. Indeed, most pharmaceutical development programs rely on computer-based data and results at some point. Herein, we discuss recent applications of advanced simulation techniques to difficult challenges in drug discovery. These entail the characterization of allosteric mechanisms and the identification of allosteric sites or cryptic pockets determined by protein motions, which are not immediately evident in the experimental structure of the target; the study of ligand binding mechanisms and their kinetic profiles; and the evaluation of drug-target affinities. We analyze different approaches to tackle challenging and emerging biological targets. Finally, we discuss the possible perspectives of future application of computation in drug discovery.

Design and Synthesis of TRAP1 Selective Inhibitors: H-Bonding with Asn171 Residue in TRAP1 Increases Paralog Selectivity

Tumor necrosis factor receptor-associated protein 1 (TRAP1) is overexpressed in the mitochondria of various cancer cells, reprograms cellular metabolism to enable cancer cells to adapt to harsh tumor environments. As inactivation of TRAP1 induces massive apoptosis in cancer cells in vitro and in vivo, the development of TRAP1-selective inhibitors has become an attractive approach. A series of purine-8-one and pyrrolo[2,3-d]pyrimidine derivatives was developed based on TRAP1 structure and identified to be highly selective in vitro for TRAP1 over the paralogous enzymes, Hsp90α and Grp94. The TRAP1-selective inhibition strategy via utilization of the Asn171 residue of the ATP-lid was investigated using X-ray crystallography and molecular dynamics simulation studies. Among various synthesized potent TRAP1 inhibitors, 5f possessed a 65-fold selectivity over Hsp90α and a 13-fold selectivity over Grp94. Additionally, 6f had a half-maximal inhibitory concentration (IC₅₀) of 63.5 nM for TRAP1, with a 78-fold and 30-fold selectivity over Hsp90α and Grp94, respectively.

Targeting the mitochondrial chaperone TRAP1: strategies and therapeutic perspectives

TRAP1, the mitochondrial isoform of heat shock protein (Hsp)90 chaperones, is a key regulator of metabolism and organelle homeostasis in diverse pathological states. While selective TRAP1 targeting is an attractive goal, classical active-site-directed strategies have proved difficult, due to high active site conservation among Hsp90 paralogs. Here, we discuss advances in developing TRAP1-directed strategies, from lead modification with mitochondria delivery groups to the computational discovery of allosteric sites and ligands. Specifically, we address the unique opportunities that targeting TRAP1 opens up in tackling fundamental questions on its biology and in unveiling new therapeutic approaches. Finally, we show how crucial to this endeavor is our ability to predict the activities of TRAP1-selective allosteric ligands and to optimize target engagement to avoid side effects.

Machine Learning Prediction of Allosteric Drug Activity from Molecular Dynamics

Allosteric drugs have been attracting increasing interest over the past few years. In this context, it is common practice to use high-throughput screening for the discovery of non-natural allosteric drugs. While the discovery stage is supported by a growing amount of biological information and increasing computing power, major challenges still remain in selecting allosteric ligands and predicting their effect on the target protein's function. Indeed, allosteric compounds can act both as inhibitors and activators of biological responses. Computational approaches to the problem have focused on variations on the theme of molecular docking coupled to molecular dynamics with the aim of recovering information on the (long-range) modulation typical of allosteric proteins.