An Interpretable Convolutional Neural Network Framework for Analyzing Molecular Dynamics Trajectories: a Case Study on Functional States for G-Protein-Coupled Receptors

Leveraging Artificial Intelligence in GPCR Activation Studies: Computational Prediction Methods as Key Drivers of Knowledge

G protein-coupled receptors (GPCRs) are key molecules involved in cellular signaling and are attractive targets for pharmacological intervention. This chapter is designed to explore the range of algorithms used to predict GPCRs' activation states, while also examining the pharmaceutical implications of these predictions. Our primary objective is to show how artificial intelligence (AI) is key in GPCR research to reveal the intricate dynamics of activation and inactivation processes, shedding light on the complex regulatory mechanisms of this vital protein family. We describe several computational strategies that leverage diverse structural data from the Protein Data Bank, molecular dynamic simulations, or ligand-based methods to predict the activation states of GPCRs. We demonstrate how the integration of AI into GPCR research not only enhances our understanding of their dynamic properties but also presents immense potential for driving pharmaceutical research and development, offering promising new avenues in the search for newer, better therapeutic agents.

Deep learning for discriminating non-trivial conformational changes in molecular dynamics simulations of SARS-CoV-2 spike-ACE2

Molecular dynamics (MD) simulations produce a substantial volume of high-dimensional data, and traditional methods for analyzing these data pose significant computational demands. Advances in MD simulation analysis combined with deep learning-based approaches have led to the understanding of specific structural changes observed in MD trajectories, including those induced by mutations. In this study, we model the trajectories resulting from MD simulations of the SARS-CoV-2 spike protein-ACE2, specifically the receptor-binding domain (RBD), as interresidue distance maps, and use deep convolutional neural networks to predict the functional impact of point mutations, related to the virus's infectivity and immunogenicity. Our model was successful in predicting mutant types that increase the affinity of the S protein for human receptors and reduce its immunogenicity, both based on MD trajectories (precision = 0.718; recall = 0.800; [Formula: see text] = 0.757; MCC = 0.488; AUC = 0.800) and their centroids. In an additional analysis, we also obtained a strong positive Pearson's correlation coefficient equal to 0.776, indicating a significant relationship between the average sigmoid probability for the MD trajectories and binding free energy (BFE) changes. Furthermore, we obtained a coefficient of determination of 0.602. Our 2D-RMSD analysis also corroborated predictions for more infectious and immune-evading mutants and revealed fluctuating regions within the receptor-binding motif (RBM), especially in the [Formula: see text] loop. This region presented a significant standard deviation for mutations that enable SARS-CoV-2 to evade the immune response, with RMSD values of 5Å in the simulation. This methodology offers an efficient alternative to identify potential strains of SARS-CoV-2, which may be potentially linked to more infectious and immune-evading mutations. Using clustering and deep learning techniques, our approach leverages information from the ensemble of MD trajectories to recognize a broad spectrum of multiple conformational patterns characteristic of mutant types. This represents a strategic advantage in identifying emerging variants, bypassing the need for long MD simulations. Furthermore, the present work tends to contribute substantially to the field of computational biology and virology, particularly to accelerate the design and optimization of new therapeutic agents and vaccines, offering a proactive stance against the constantly evolving threat of COVID-19 and potential future pandemics.

Identify Regioselective Residues of Ginsenoside Hydrolases by Graph-Based Active Learning from Molecular Dynamics

Identifying the catalytic regioselectivity of enzymes remains a challenge. Compared to experimental trial-and-error approaches, computational methods like molecular dynamics simulations provide valuable insights into enzyme characteristics. However, the massive data generated by these simulations hinder the extraction of knowledge about enzyme catalytic mechanisms without adequate modeling techniques. Here, we propose a computational framework utilizing graph-based active learning from molecular dynamics to identify the regioselectivity of ginsenoside hydrolases (GHs), which selectively catalyze C6 or C20 positions to obtain rare deglycosylated bioactive compounds from Panax plants. Experimental results reveal that the dynamic-aware graph model can excellently distinguish GH regioselectivity with accuracy as high as 96-98% even when different enzyme-substrate systems exhibit similar dynamic behaviors. The active learning strategy equips our model to work robustly while reducing the reliance on dynamic data, indicating its capacity to mine sufficient knowledge from short multi-replica simulations. Moreover, the model's interpretability identified crucial residues and features associated with regioselectivity. Our findings contribute to the understanding of GH catalytic mechanisms and provide direct assistance for rational design to improve regioselectivity. We presented a general computational framework for modeling enzyme catalytic specificity from simulation data, paving the way for further integration of experimental and computational approaches in enzyme optimization and design.

The application of artificial intelligence to accelerate G protein-coupled receptor drug discovery

The application of artificial intelligence (AI) approaches to drug discovery for G protein-coupled receptors (GPCRs) is a rapidly expanding area. Artificial intelligence can be used at multiple stages during the drug discovery process, from aiding our understanding of the fundamental actions of GPCRs to the discovery of new ligand-GPCR interactions or the prediction of clinical responses. Here, we provide an overview of the concepts behind artificial intelligence, including the subfields of machine learning and deep learning. We summarise the published applications of artificial intelligence to different stages of the GPCR drug discovery process. Finally, we reflect on the benefits and limitations of artificial intelligence and share our vision for the exciting potential for further development of applications to aid GPCR drug discovery. In addition to making the drug discovery process "faster, smarter and cheaper," we anticipate that the application of artificial intelligence will create exciting new opportunities for GPCR drug discovery. LINKED ARTICLES: This article is part of a themed issue Therapeutic Targeting of G Protein-Coupled Receptors: hot topics from the Australasian Society of Clinical and Experimental Pharmacologists and Toxicologists 2021 Virtual Annual Scientific Meeting. To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v181.14/issuetoc.

Exploring biased activation characteristics by molecular dynamics simulation and machine learning for the μ-opioid receptor

Biased ligands selectively activating specific downstream signaling pathways (termed as biased activation) exhibit significant therapeutic potential. However, the conformational characteristics revealed are very limited for the biased activation, which is not conducive to biased drug development. Motivated by the issue, we combine extensive accelerated molecular dynamics simulations and an interpretable deep learning model to probe the biased activation features for two complex systems constructed by the inactive μOR and two different biased agonists (G-protein-biased agonist TRV130 and β-arrestin-biased agonist endomorphin2). The results indicate that TRV130 binds deeper into the receptor core compared to endomorphin2, located between W2936.48 and D1142.50, and forms hydrogen bonding with D1142.50, while endomorphin2 binds above W2936.48. The G protein-biased agonist induces greater outward movements of the TM6 intracellular end, forming a typical active conformation, while the β-arrestin-biased agonist leads to a smaller extent of outward movements of TM6. Compared with TRV130, endomorphin2 causes more pronounced inward movements of the TM7 intracellular end and more complex conformational changes of H8 and ICL1. In addition, important residues determining the two different biased activation states were further identified by using an interpretable deep learning classification model, including some common biased activation residues across Class A GPCRs like some key residues on the TM2 extracellular end, ECL2, TM5 intracellular end, TM6 intracellular end, and TM7 intracellular end, and some specific important residues of ICL3 for μOR. The observations will provide valuable information for understanding the biased activation mechanism for GPCRs.

Characterizing conformational states in GPCR structures using machine learning

G protein-coupled receptors (GPCRs) play a pivotal role in signal transduction and represent attractive targets for drug development. Recent advances in structural biology have provided insights into GPCR conformational states, which are critical for understanding their signaling pathways and facilitating structure-based drug discovery. In this study, we introduce a machine learning approach for conformational state annotation of GPCRs. We represent GPCR conformations as high-dimensional feature vectors, incorporating information about amino acid residue pairs involved in the activation pathway. Using a dataset of GPCR conformations in inactive and active states obtained through molecular dynamics simulations, we trained machine learning models to distinguish between inactive-like and active-like conformations. The developed model provides interpretable predictions and can be used for the large-scale analysis of molecular dynamics trajectories of GPCRs.

Machine Learning-Guided Protein Engineering

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.

Open-Source Machine Learning in Computational Chemistry

The field of computational chemistry has seen a significant increase in the integration of machine learning concepts and algorithms. In this Perspective, we surveyed 179 open-source software projects, with corresponding peer-reviewed papers published within the last 5 years, to better understand the topics within the field being investigated by machine learning approaches. For each project, we provide a short description, the link to the code, the accompanying license type, and whether the training data and resulting models are made publicly available. Based on those deposited in GitHub repositories, the most popular employed Python libraries are identified. We hope that this survey will serve as a resource to learn about machine learning or specific architectures thereof by identifying accessible codes with accompanying papers on a topic basis. To this end, we also include computational chemistry open-source software for generating training data and fundamental Python libraries for machine learning. Based on our observations and considering the three pillars of collaborative machine learning work, open data, open source (code), and open models, we provide some suggestions to the community.

Enhancing Conformational Sampling for Intrinsically Disordered and Ordered Proteins by Variational Autoencoder

Intrinsically disordered proteins (IDPs) account for more than 50% of the human proteome and are closely associated with tumors, cardiovascular diseases, and neurodegeneration, which have no fixed three-dimensional structure under physiological conditions. Due to the characteristic of conformational diversity, conventional experimental methods of structural biology, such as NMR, X-ray diffraction, and CryoEM, are unable to capture conformational ensembles. Molecular dynamics (MD) simulation can sample the dynamic conformations at the atomic level, which has become an effective method for studying the structure and function of IDPs. However, the high computational cost prevents MD simulations from being widely used for IDPs conformational sampling. In recent years, significant progress has been made in artificial intelligence, which makes it possible to solve the conformational reconstruction problem of IDP with fewer computational resources. Here, based on short MD simulations of different IDPs systems, we use variational autoencoders (VAEs) to achieve the generative reconstruction of IDPs structures and include a wider range of sampled conformations from longer simulations. Compared with the generative autoencoder (AEs), VAEs add an inference layer between the encoder and decoder in the latent space, which can cover the conformational landscape of IDPs more comprehensively and achieve the effect of enhanced sampling. Through experimental verification, the Cα RMSD between VAE-generated and MD simulation sampling conformations in the 5 IDPs test systems was significantly lower than that of AE. The Spearman correlation coefficient on the structure was higher than that of AE. VAE can also achieve excellent performance regarding structured proteins. In summary, VAEs can be used to effectively sample protein structures.

Integrating Machine Learning in the Coarse-Grained Molecular Simulation of Polymers

Machine learning (ML) is having an increasing impact on the physical sciences, engineering, and technology and its integration into molecular simulation frameworks holds great potential to expand their scope of applicability to complex materials and facilitate fundamental knowledge and reliable property predictions, contributing to the development of efficient materials design routes. The application of ML in materials informatics in general, and polymer informatics in particular, has led to interesting results, however great untapped potential lies in the integration of ML techniques into the multiscale molecular simulation methods for the study of macromolecular systems, specifically in the context of Coarse Grained (CG) simulations. In this Perspective, we aim at presenting the pioneering recent research efforts in this direction and discussing how these new ML-based techniques can contribute to critical aspects of the development of multiscale molecular simulation methods for bulk complex chemical systems, especially polymers. Prerequisites for the implementation of such ML-integrated methods and open challenges that need to be met toward the development of general systematic ML-based coarse graining schemes for polymers are discussed.

Layer-Wise Relevance Analysis for Motif Recognition in the Activation Pathway of the β2-Adrenergic GPCR Receptor

G-protein-coupled receptors (GPCRs) are cell membrane proteins of relevance as therapeutic targets, and are associated to the development of treatments for illnesses such as diabetes, Alzheimer's, or even cancer. Therefore, comprehending the underlying mechanisms of the receptor functional properties is of particular interest in pharmacoproteomics and in disease therapy at large. Their interaction with ligands elicits multiple molecular rearrangements all along their structure, inducing activation pathways that distinctly influence the cell response. In this work, we studied GPCR signaling pathways from molecular dynamics simulations as they provide rich information about the dynamic nature of the receptors. We focused on studying the molecular properties of the receptors using deep-learning-based methods. In particular, we designed and trained a one-dimensional convolution neural network and illustrated its use in a classification of conformational states: active, intermediate, or inactive, of the β2-adrenergic receptor when bound to the full agonist BI-167107. Through a novel explainability-oriented investigation of the prediction results, we were able to identify and assess the contribution of individual motifs (residues) influencing a particular activation pathway. Consequently, we contribute a methodology that assists in the elucidation of the underlying mechanisms of receptor activation-deactivation.

Spectral Encoder to Extract the Features of Near-Infrared Spectra for Multivariate Calibration

An autoencoder architecture was adopted for near-infrared (NIR) spectral analysis by extracting the common features in the spectra. Three autoencoder-based networks with different purposes were constructed. First, a spectral encoder was established by training the network with a set of spectra as the input. The features of the spectra can be encoded by the nodes in the bottleneck layer, which in turn can be used to build a sparse and robust model. Second, taking the spectra of one instrument as the input and that of another instrument as the reference output, the common features in both spectra can be obtained in the bottleneck layer. Therefore, in the prediction step, the spectral features of the second can be predicted by taking the reverse of the decoder as the encoder. Furthermore, transfer learning was used to build the model for the spectra of more instruments by fine-tuning the trained network. NIR datasets of plant, wheat, and pharmaceutical tablets measured on multiple instruments were used to test the method. The multi-linear regression (MLR) model with the encoded features was found to have a similar or slightly better performance in prediction compared with the partial least-squares (PLS) model.