DeepBSP-a Machine Learning Method for Accurate Prediction of Protein-Ligand Docking Structures

Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities

Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.

Recent advances in computational and experimental protein-ligand affinity determination techniques

INTRODUCTION

Modern drug discovery revolves around designing ligands that target the chosen biomolecule, typically proteins. For this, the evaluation of affinities of putative ligands is crucial. This has given rise to a multitude of dedicated computational and experimental methods that are constantly being developed and improved.

AREAS COVERED

In this review, the authors reassess both the industry mainstays and the newest trends among the methods for protein - small-molecule affinity determination. They discuss both computational affinity predictions and experimental techniques, describing their basic principles, main limitations, and advantages. Together, this serves as initial guide to the currently most popular and cutting-edge ligand-binding assays employed in rational drug design.

EXPERT OPINION

The affinity determination methods continue to develop toward miniaturization, high-throughput, and in-cell application. Moreover, the availability of data analysis tools has been constantly increasing. Nevertheless, cross-verification of data using at least two different techniques and careful result interpretation remain of utmost importance.

Water Network-Augmented Two-State Model for Protein-Ligand Binding Affinity Prediction

Water network rearrangement from the ligand-unbound state to the ligand-bound state is known to have significant effects on the protein-ligand binding interactions, but most of the current machine learning-based scoring functions overlook these effects. In this study, we endeavor to construct a comprehensive and realistic deep learning model by incorporating water network information into both ligand-unbound and -bound states. In particular, extended connectivity interaction features were integrated into graph representation, and graph transformer operator was employed to extract features of the ligand-unbound and -bound states. Through these efforts, we developed a water network-augmented two-state model called ECIFGraph::HM-Holo-Apo. Our new model exhibits satisfactory performance in terms of scoring, ranking, docking, screening, and reverse screening power tests on the CASF-2016 benchmark. In addition, it can achieve superior performance in large-scale docking-based virtual screening tests on the DEKOIS2.0 data set. Our study highlights that the use of a water network-augmented two-state model can be an effective strategy to bolster the robustness and applicability of machine learning-based scoring functions, particularly for targets with hydrophilic or solvent-exposed binding pockets.

A new paradigm for applying deep learning to protein-ligand interaction prediction

Protein-ligand interaction prediction presents a significant challenge in drug design. Numerous machine learning and deep learning (DL) models have been developed to accurately identify docking poses of ligands and active compounds against specific targets. However, current models often suffer from inadequate accuracy or lack practical physical significance in their scoring systems. In this research paper, we introduce IGModel, a novel approach that utilizes the geometric information of protein-ligand complexes as input for predicting the root mean square deviation of docking poses and the binding strength (pKd, the negative value of the logarithm of binding affinity) within the same prediction framework. This ensures that the output scores carry intuitive meaning. We extensively evaluate the performance of IGModel on various docking power test sets, including the CASF-2016 benchmark, PDBbind-CrossDocked-Core and DISCO set, consistently achieving state-of-the-art accuracies. Furthermore, we assess IGModel's generalizability and robustness by evaluating it on unbiased test sets and sets containing target structures generated by AlphaFold2. The exceptional performance of IGModel on these sets demonstrates its efficacy. Additionally, we visualize the latent space of protein-ligand interactions encoded by IGModel and conduct interpretability analysis, providing valuable insights. This study presents a novel framework for DL-based prediction of protein-ligand interactions, contributing to the advancement of this field. The IGModel is available at GitHub repository https://github.com/zchwang/IGModel.

GSScore: a novel Graphormer-based shell-like scoring method for protein-ligand docking

Protein-ligand interactions (PLIs) are essential for cellular activities and drug discovery. But due to the complexity and high cost of experimental methods, there is a great demand for computational approaches to recognize PLI patterns, such as protein-ligand docking. In recent years, more and more models based on machine learning have been developed to directly predict the root mean square deviation (RMSD) of a ligand docking pose with reference to its native binding pose. However, new scoring methods are pressingly needed in methodology for more accurate RMSD prediction. We present a new deep learning-based scoring method for RMSD prediction of protein-ligand docking poses based on a Graphormer method and Shell-like graph architecture, named GSScore. To recognize near-native conformations from a set of poses, GSScore takes atoms as nodes and then establishes the docking interface of protein-ligand into multiple bipartite graphs within different shell ranges. Benefiting from the Graphormer and Shell-like graph architecture, GSScore can effectively capture the subtle differences between energetically favorable near-native conformations and unfavorable non-native poses without extra information. GSScore was extensively evaluated on diverse test sets including a subset of PDBBind version 2019, CASF2016 as well as DUD-E, and obtained significant improvements over existing methods in terms of RMSE, $R$ (Pearson correlation coefficient), Spearman correlation coefficient and Docking power.

Elucidation of protein-ligand interactions by multiple trajectory analysis methods

The identification of interaction between protein and ligand including binding positions and strength plays a critical role in drug discovery. Molecular docking and molecular dynamics (MD) techniques have been widely applied to predict binding positions and binding affinity. However, there are few works that describe the systematic exploration of the MD trajectory evolution in this context, potentially leaving out important information. To address the problem, we build a framework, Moira (molecular dynamics trajectory analysis), which enables automating the whole process ranging from docking, MD simulations and various analyses as well as visualizations. We utilized Moira to analyze 400 MD simulations in terms of their geometric features (root mean square deviation and protein-ligand interaction profiler) and energetics (molecular mechanics Poisson-Boltzmann surface area) for these trajectories. Finally, we demonstrate the performance of different analysis techniques in distinguishing native poses among four poses.

Molecular Gas-Phase Conformational Ensembles

Accurately determining the global minima of a molecular structure is important in diverse scientific fields, including drug design, materials science, and chemical synthesis. Conformational search engines serve as valuable tools for exploring the extensive conformational space of molecules and for identifying energetically favorable conformations. In this study, we present a comparison of Auto3D, CREST, Balloon, and ETKDG (from RDKit), which are freely available conformational search engines, to evaluate their effectiveness in locating global minima. These engines employ distinct methodologies, including machine learning (ML) potential-based, semiempirical, and force field-based approaches. To validate these methods, we propose the use of collisional cross-section (CCS) values obtained from ion mobility-mass spectrometry studies. We hypothesize that experimental gas-phase CCS values can provide experimental evidence that we likely have the global minimum for a given molecule. To facilitate this effort, we used our gas-phase conformation library (GPCL) which currently consists of the full ensembles of 20 small molecules and can be used by the community to validate any conformational search engine. Further members of the GPCL can be readily created for any molecule of interest using our standard workflow used to compute CCS values, expanding the ability of the GPCL in validation exercises. These innovative validation techniques enhance our understanding of the conformational landscape and provide valuable insights into the performance of conformational generation engines. Our findings shed light on the strengths and limitations of each search engine, enabling informed decisions for their utilization in various scientific fields, where accurate molecular structure determination is crucial for understanding biological activity and designing targeted interventions. By facilitating the identification of reliable conformations, this study significantly contributes to enhancing the efficiency and accuracy of molecular structure determination, with particular focus on metabolite structure elucidation. The findings of this research also provide valuable insights for developing effective workflows for predicting the structures of unknown compounds with high precision.

CarsiDock: a deep learning paradigm for accurate protein-ligand docking and screening based on large-scale pre-training

The expertise accumulated in deep neural network-based structure prediction has been widely transferred to the field of protein-ligand binding pose prediction, thus leading to the emergence of a variety of deep learning-guided docking models for predicting protein-ligand binding poses without relying on heavy sampling. However, their prediction accuracy and applicability are still far from satisfactory, partially due to the lack of protein-ligand binding complex data. To this end, we create a large-scale complex dataset containing ∼9 M protein-ligand docking complexes for pre-training, and propose CarsiDock, the first deep learning-guided docking approach that leverages pre-training of millions of predicted protein-ligand complexes. CarsiDock contains two main stages, i.e., a deep learning model for the prediction of protein-ligand atomic distance matrices, and a translation, rotation and torsion-guided geometry optimization procedure to reconstruct the matrices into a credible binding pose. The pre-training and multiple innovative architectural designs facilitate the dramatically improved docking accuracy of our approach over the baselines in terms of multiple docking scenarios, thereby contributing to its outstanding early recognition performance in several retrospective virtual screening campaigns. Further explorations demonstrate that CarsiDock can not only guarantee the topological reliability of the binding poses but also successfully reproduce the crucial interactions in crystalized structures, highlighting its superior applicability.

zPoseScore model for accurate and robust protein-ligand docking pose scoring in CASP15

We introduce a deep learning-based ligand pose scoring model called zPoseScore for predicting protein-ligand complexes in the 15th Critical Assessment of Protein Structure Prediction (CASP15). Our contributions are threefold: first, we generate six training and evaluation data sets by employing advanced data augmentation and sampling methods. Second, we redesign the "zFormer" module, inspired by AlphaFold2's Evoformer, to efficiently describe protein-ligand interactions. This module enables the extraction of protein-ligand paired features that lead to accurate predictions. Finally, we develop the zPoseScore framework with zFormer for scoring and ranking ligand poses, allowing for atomic-level protein-ligand feature encoding and fusion to output refined ligand poses and ligand per-atom deviations. Our results demonstrate excellent performance on various testing data sets, achieving Pearson's correlation R  = 0.783 and 0.659 for ranking docking decoys generated based on experimental and predicted protein structures of CASF-2016 protein-ligand complexes. Additionally, we obtain an averaged local distance difference test (lDDT pli = 0.558) of AIchemy LIG2 in CASP15 for de novo protein-ligand complex structure predictions. Detailed analysis shows that accurate ligand binding site prediction and side-chain orientation are crucial for achieving better prediction performance. Our proposed model is one of the most accurate protein-ligand pose prediction models and could serve as a valuable tool in small molecule drug discovery.

Equivariant Flexible Modeling of the Protein-Ligand Binding Pose with Geometric Deep Learning

Flexible modeling of the protein-ligand complex structure is a fundamental challenge for in silico drug development. Recent studies have improved commonly used docking tools by incorporating extra-deep learning-based steps. However, such strategies limit their accuracy and efficiency because they retain massive sampling pressure and lack consideration for flexible biomolecular changes. In this study, we propose FlexPose, a geometric graph network capable of direct flexible modeling of complex structures in Euclidean space without the following conventional sampling and scoring strategies. Our model adopts two key designs: scalar-vector dual feature representation and SE(3)-equivariant network, to manage dynamic structural changes, as well as two strategies: conformation-aware pretraining and weakly supervised learning, to boost model generalizability in unseen chemical space. Benefiting from these paradigms, our model dramatically outperforms all tested popular docking tools and recently advanced deep learning methods, especially in tasks involving protein conformation changes. We further investigate the impact of protein and ligand similarity on the model performance with two conformation-aware strategies. Moreover, FlexPose provides an affinity estimation and model confidence for postanalysis.

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.

Deep Learning with Geometry-Enhanced Molecular Representation for Augmentation of Large-Scale Docking-Based Virtual Screening

Structure-based virtual screening has been a crucial tool in drug discovery for decades. However, as the chemical space expands, the existing structure-based virtual screening techniques based on molecular docking and scoring struggle to handle billion-entry ultralarge libraries due to the high computational cost. To address this challenge, people have resorted to machine learning techniques to enhance structure-based virtual screening for efficiently exploring the vast chemical space. In those cases, compounds are usually treated as sequential strings or two-dimensional topology graphs, limiting their ability to incorporate three-dimensional structural information for downstream tasks. We herein propose a novel deep learning protocol, GEM-Screen, which utilizes the geometry-enhanced molecular representation of the compounds docking to a specific target and is trained on docking scores of a small fraction of a library through an active learning strategy to approximate the docking outcome for yet nontraining entries. This protocol is applied to virtual screening campaigns against the AmpC and D4 targets, demonstrating that GEM-Screen enriches more than 90% of the hit scaffolds for AmpC in the top 4% of model predictions and more than 80% of the hit scaffolds for D4 in the same top-ranking size of library. GEM-Screen can be used in conjunction with traditional docking programs for docking of only the top-ranked compounds to avoid the exhaustive docking of the whole library, thus allowing for discovering top-scoring compounds from billion-entry libraries in a rapid yet accurate fashion.

ViTScore: A Novel Three-Dimensional Vision Transformer Method for Accurate Prediction of Protein-Ligand Docking Poses

Protein-ligand interactions (PLIs) are essential for cellular activities and drug discovery, and due to the complexity and high cost of experimental methods, there is a great demand for computational approaches, such as protein-ligand docking, to decipher PLI patterns. One of the most challenging aspects of protein-ligand docking is to identify near-native conformations from a set of poses, but traditional scoring functions still have limited accuracy. Therefore, new scoring methods are urgently needed for methodological and/or practical implications. We present a novel deep learning-based scoring function for ranking protein-ligand docking poses based on Vision Transformer (ViT), named ViTScore. To recognize near-native poses from a set of poses, ViTScore voxelizes the protein-ligand interactional pocket into a 3D grid labeled by the occupancy contribution of atoms in different physicochemical classes. This allows ViTScore to capture the subtle differences between spatially and energetically favorable near-native poses and unfavorable non-native poses without needing extra information. After that, ViTScore will output the prediction of the root mean square deviation (rmsd) of a docking pose with reference to the native binding pose. ViTScore is extensively evaluated on diverse test sets including PDBbind2019 and CASF2016, and obtains significant improvements over existing methods in terms of RMSE, R and docking power. Moreover, the results demonstrate that ViTScore is a promising scoring function for protein-ligand docking, and it can be used to accurately identify near-native poses from a set of poses. Furthermore, the results suggest that ViTScore is a powerful tool for protein-ligand docking, and it can be used to accurately identify near-native poses from a set of poses. Additionally, ViTScore can be used to identify potential drug targets and to design new drugs with improved efficacy and safety.

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.

AQDnet: Deep Neural Network for Protein-Ligand Docking Simulation

We have developed an innovative system, AI QM Docking Net (AQDnet), which utilizes the three-dimensional structure of protein-ligand complexes to predict binding affinity. This system is novel in two respects: first, it significantly expands the training dataset by generating thousands of diverse ligand configurations for each protein-ligand complex and subsequently determining the binding energy of each configuration through quantum computation. Second, we have devised a method that incorporates the atom-centered symmetry function (ACSF), highly effective in describing molecular energies, for the prediction of protein-ligand interactions. These advancements have enabled us to effectively train a neural network to learn the protein-ligand quantum energy landscape (P-L QEL). Consequently, we have achieved a 92.6% top 1 success rate in the CASF-2016 docking power, placing first among all models assessed in the CASF-2016, thus demonstrating the exceptional docking performance of our model.

Analysis of the First Ion Coordination Sphere: A Toolkit to Analyze the Coordination Sphere of Ions

Rapid and accurate approaches to characterizing the coordination structure of an ion are important for designing ligands and quantifying structure-property trends. Here, we introduce AFICS (Analysis of the First Ion Coordination Sphere), a tool written in Python 3 for analyzing the structural and geometric features of the first coordination sphere of an ion over the course of molecular dynamics simulations. The principal feature of AFICS is its ability to quantify the distortion a coordination geometry undergoes compared to uniform polyhedra. This work applies the toolkit to analyze molecular dynamics simulations of the well-defined coordination structure of aqueous Cr³⁺ along with the more ambiguous structure of aqueous Eu³⁺ chelated to ethylenediaminetetraacetic acid. The tool is targeted for analyzing ions with fluxional or irregular coordination structures (e.g., solution structures of f-block elements) but is generalized such that it may be applied to other systems.

Protein-protein interfaces in molecular glue-induced ternary complexes: classification, characterization, and prediction

Molecular glues are a class of small molecules that stabilize the interactions between proteins. Naturally occurring molecular glues are present in many areas of biology where they serve as central regulators of signaling pathways. Importantly, several clinical compounds act as molecular glue degraders that stabilize interactions between E3 ubiquitin ligases and target proteins, leading to their degradation. Molecular glues hold promise as a new generation of therapeutic agents, including those molecular glue degraders that can redirect the protein degradation machinery in a precise way. However, rational discovery of molecular glues is difficult in part due to the lack of understanding of the protein-protein interactions they stabilize. In this review, we summarize the structures of known molecular glue-induced ternary complexes and the interface properties. Detailed analysis shows different mechanisms of ternary structure formation. Additionally, we also review computational approaches for predicting protein-protein interfaces and highlight the promises and challenges. This information will ultimately help inform future approaches for rational molecular glue discovery.

A fully differentiable ligand pose optimization framework guided by deep learning and a traditional scoring function

The recently reported machine learning- or deep learning-based scoring functions (SFs) have shown exciting performance in predicting protein-ligand binding affinities with fruitful application prospects. However, the differentiation between highly similar ligand conformations, including the native binding pose (the global energy minimum state), remains challenging that could greatly enhance the docking. In this work, we propose a fully differentiable, end-to-end framework for ligand pose optimization based on a hybrid SF called DeepRMSD+Vina combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF. The DeepRMSD+Vina, which combines (1) the root mean square deviation (RMSD) of the docking pose with respect to the native pose and (2) the AutoDock Vina score, is fully differentiable; thus is capable of optimizing the ligand binding pose to the energy-lowest conformation. Evaluated by the CASF-2016 docking power dataset, the DeepRMSD+Vina reaches a success rate of 94.4%, which outperforms most reported SFs to date. We evaluated the ligand conformation optimization framework in practical molecular docking scenarios (redocking and cross-docking tasks), revealing the high potentialities of this framework in drug design and discovery. Structural analysis shows that this framework has the ability to identify key physical interactions in protein-ligand binding, such as hydrogen-bonding. Our work provides a paradigm for optimizing ligand conformations based on deep learning algorithms. The DeepRMSD+Vina model and the optimization framework are available at GitHub repository https://github.com/zchwang/DeepRMSD-Vina_Optimization.

Recent PELE Developments and Applications in Drug Discovery Campaigns

Computer simulation techniques are gaining a central role in molecular pharmacology. Due to several factors, including the significant improvements of traditional molecular modelling, the irruption of machine learning methods, the massive data generation, or the unlimited computational resources through cloud computing, the future of pharmacology seems to go hand in hand with in silico predictions. In this review, we summarize our recent efforts in such a direction, centered on the unconventional Monte Carlo PELE software and on its coupling with machine learning techniques. We also provide new data on combining two recent new techniques, aquaPELE capable of exhaustive water sampling and fragPELE, for fragment growing.

Targeting protein conformations with small molecules to control protein complexes

Dynamic protein complexes function in all cellular processes, from signaling to transcription, using distinct conformations that regulate their activity. Conformational switching of proteins can turn on or off their activity through protein-protein interactions, catalytic function, cellular localization, or membrane interaction. Recent advances in structural, computational, and chemical methodologies have enabled the discovery of small-molecule activators and inhibitors of conformationally dynamic proteins by using a more rational design than a serendipitous screening approach. Here, we discuss such recent examples, focusing on the mechanism of protein conformational switching and its regulation by small molecules. We emphasize the rational approaches to control protein oligomerization with small molecules that offer exciting opportunities for investigation of novel biological mechanisms and drug discovery.

Systematic Improvement of the Performance of Machine Learning Scoring Functions by Incorporating Features of Protein-Bound Water Molecules

Water molecules at the ligand-protein interfaces play crucial roles in the binding of the ligands, but the behavior of protein-bound water is largely ignored in many currently used machine learning (ML)-based scoring functions (SFs). In an attempt to improve the prediction performance of existing ML-based SFs, we estimated the water distribution with a HydraMap (HM) method and then incorporated the features extracted from protein-bound waters obtained in this way into three ML-based SFs: RF-Score, ECIF, and PLEC. It was found that a combination of HM-based features can consistently improve the performance of all three SFs, including their scoring, ranking, and docking power. HydraMap-based features show consistently good performance with both crystal structures and docked structures, demonstrating their robustness for SFs. Overall, HM-based features, which are a statistical representation of hydration sites at protein-ligand interfaces, are expected to improve the prediction performance for diverse SFs.

Boosting Protein-Ligand Binding Pose Prediction and Virtual Screening Based on Residue-Atom Distance Likelihood Potential and Graph Transformer

The past few years have witnessed enormous progress toward applying machine learning approaches to the development of protein-ligand scoring functions. However, the robust performance and wide applicability of scoring functions remain a big challenge for increasing the success rate of docking-based virtual screening. Herein, a novel scoring function named RTMScore was developed by introducing a tailored residue-based graph representation strategy and several graph transformer layers for the learning of protein and ligand representations, followed by a mixture density network to obtain residue-atom distance likelihood potential. Our approach was resolutely validated on the CASF-2016 benchmark, and the results indicate that RTMScore can outperform almost all of the other state-of-the-art methods in terms of both the docking and screening powers. Further evaluation confirms the robustness of our approach that can not only retain its docking power on cross-docked poses but also achieve improved performance as a rescoring tool in larger-scale virtual screening.

XLPFE: A Simple and Effective Machine Learning Scoring Function for Protein-Ligand Scoring and Ranking

Prediction of protein-ligand binding affinities is a central issue in structure-based computer-aided drug design. In recent years, much effort has been devoted to the prediction of the binding affinity in protein-ligand complexes using machine learning (ML). Due to the remarkable ability of ML methods in nonlinear fitting, ML-based scoring functions (SFs) can deliver much improved performance on a selected test set, such as the comparative assessment of scoring functions (CASF), when compared to the classical SFs. However, the performance of ML-based SFs heavily relies on the overall similarity of the training set and the test set. To improve the performance and transferability of an SF, we have tried to combine various features including energy terms from X-score and AutoDock Vina, the properties of ligands, and the statistical sequence-related information from either the binding site or the full protein. In conjunction with extreme trees (ET), an ML model, we have developed XLPFE, a new SF. Compared with other tested methods such as X-score, AutoDock Vina, ΔvinaXGB, PSH-ML, or CNN-score, XLPFE achieves consistently better scoring and ranking power for various types of protein-ligand complex structures beyond the CASF, suggesting that XLPFE has superior transferability. In particular, XLPFE performs better with metalloenzymes. With its faster speed, improved accuracy, and better transferability, XLPFE could be usefully applied to a diverse range of protein-ligand complexes.

Scoring Functions for Protein-Ligand Binding Affinity Prediction using Structure-Based Deep Learning: A Review

The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel-Ligand Docking

The identification of promising lead compounds showing pharmacological activities toward a biological target is essential in early stage drug discovery. With the recent increase in available small-molecule databases, virtual high-throughput screening using physics-based molecular docking has emerged as an essential tool in assisting fast and cost-efficient lead discovery and optimization. However, the best scored docking poses are often suboptimal, resulting in incorrect screening and chemical property calculation. We address the pose classification problem by leveraging data-driven machine learning approaches to identify correct docking poses from AutoDock Vina and Glide screens. To enable effective classification of docking poses, we present two convolutional neural network approaches: a three-dimensional convolutional neural network (3D-CNN) and an attention-based point cloud network (PCN) trained on the PDBbind refined set. We demonstrate the effectiveness of our proposed classifiers on multiple evaluation data sets including the standard PDBbind CASF-2016 benchmark data set and various compound libraries with structurally different protein targets including an ion channel data set extracted from Protein Data Bank (PDB) and an in-house KCa3.1 inhibitor data set. Our experiments show that excluding false positive docking poses using the proposed classifiers improves virtual high-throughput screening to identify novel molecules against each target protein compared to the initial screen based on the docking scores.

Dowker complex based machine learning (DCML) models for protein-ligand binding affinity prediction

With the great advancements in experimental data, computational power and learning algorithms, artificial intelligence (AI) based drug design has begun to gain momentum recently. AI-based drug design has great promise to revolutionize pharmaceutical industries by significantly reducing the time and cost in drug discovery processes. However, a major issue remains for all AI-based learning model that is efficient molecular representations. Here we propose Dowker complex (DC) based molecular interaction representations and Riemann Zeta function based molecular featurization, for the first time. Molecular interactions between proteins and ligands (or others) are modeled as Dowker complexes. A multiscale representation is generated by using a filtration process, during which a series of DCs are generated at different scales. Combinatorial (Hodge) Laplacian matrices are constructed from these DCs, and the Riemann zeta functions from their spectral information can be used as molecular descriptors. To validate our models, we consider protein-ligand binding affinity prediction. Our DC-based machine learning (DCML) models, in particular, DC-based gradient boosting tree (DC-GBT), are tested on three most-commonly used datasets, i.e., including PDBbind-2007, PDBbind-2013 and PDBbind-2016, and extensively compared with other existing state-of-the-art models. It has been found that our DC-based descriptors can achieve the state-of-the-art results and have better performance than all machine learning models with traditional molecular descriptors. Our Dowker complex based machine learning models can be used in other tasks in AI-based drug design and molecular data analysis.

With the ever-increasing accumulation of chemical and biomolecular data, data-driven artificial intelligence (AI) models will usher in an era of faster, cheaper and more-efficient drug design and drug discovery. However, unlike image, text, video, audio data, molecular data from chemistry and biology, have much complicated three-dimensional structures, as well as physical and chemical properties. Efficient molecular representations and descriptors are key to the success of machine learning models in drug design. Here, we propose Dowker complex based molecular representation and Riemann Zeta function based molecular featurization, for the first time. To characterize the complicated molecular structures and interactions at the atomic level, Dowker complexes are constructed. Based on them, intrinsic mathematical invariants are derived and used as molecular descriptors, which can be further combined with machine learning and deep learning models. Our model has achieved state-of-the-art results in protein-ligand binding affinity prediction, demonstrating its great potential for other drug design and discovery problems.

Improving protein-ligand docking and screening accuracies by incorporating a scoring function correction term

Scoring functions are important components in molecular docking for structure-based drug discovery. Traditional scoring functions, generally empirical- or force field-based, are robust and have proven to be useful for identifying hits and lead optimizations. Although multiple highly accurate deep learning- or machine learning-based scoring functions have been developed, their direct applications for docking and screening are limited. We describe a novel strategy to develop a reliable protein–ligand scoring function by augmenting the traditional scoring function Vina score using a correction term (OnionNet-SFCT). The correction term is developed based on an AdaBoost random forest model, utilizing multiple layers of contacts formed between protein residues and ligand atoms. In addition to the Vina score, the model considerably enhances the AutoDock Vina prediction abilities for docking and screening tasks based on different benchmarks (such as cross-docking dataset, CASF-2016, DUD-E and DUD-AD). Furthermore, our model could be combined with multiple docking applications to increase pose selection accuracies and screening abilities, indicating its wide usage for structure-based drug discoveries. Furthermore, in a reverse practice, the combined scoring strategy successfully identified multiple known receptors of a plant hormone. To summarize, the results show that the combination of data-driven model (OnionNet-SFCT) and empirical scoring function (Vina score) is a good scoring strategy that could be useful for structure-based drug discoveries and potentially target fishing in future.

AtomNet PoseRanker: Enriching Ligand Pose Quality for Dynamic Proteins in Virtual High-Throughput Screens

Structure-based, virtual High-Throughput Screening (vHTS) methods for predicting ligand activity in drug discovery are important when there are no or relatively few known compounds that interact with a therapeutic target of interest. State-of-the-art computational vHTS necessarily relies on effective methods for pose sampling and docking and generating an accurate affinity score from the docked poses. However, proteins are dynamic; in vivo ligands bind to a conformational ensemble. In silico docking to the single conformation represented by a crystal structure can adversely affect the pose quality. Here, we introduce AtomNet PoseRanker (ANPR), a graph convolutional network trained to identify and rerank crystal-like ligand poses from a sampled ensemble of protein conformations and ligand poses. In contrast to conventional vHTS methods that incorporate receptor flexibility, a deep learning approach can internalize valid cognate and noncognate binding modes corresponding to distinct receptor conformations, thereby learning to infer and account for receptor flexibility even on single conformations. ANPR significantly enriched pose quality in docking to cognate and noncognate receptors of the PDBbind v2019 data set. Improved pose rankings that better represent experimentally observed ligand binding modes improve hit rates in vHTS campaigns and thereby advance computational drug discovery, especially for novel therapeutic targets or novel binding sites.

Reliable Prediction of the Protein-Ligand Binding Affinity Using a Charge Penetration Corrected AMOEBA Force Field: A Case Study of Drug Resistance Mutations in Abl Kinase

Protein mutations that directly impair drug binding are related to therapeutic resistance, and accurate prediction of their impact on drug binding would benefit drug design and clinical practice. Here, we have developed a scoring strategy that predicts the effect of the mutations on the protein-ligand binding affinity. In view of the critical importance of electrostatics in protein-ligand interactions, the charge penetration corrected AMOEBA force field (AMOEBA_CP model) was employed to improve the accuracy of the calculated electrostatic energy. We calculated the electrostatic energy using an energy decomposition analysis scheme based on the generalized Kohn-Sham (GKS-EDA). The AMOEBA_CP model was validated by a protein-fragment-ligand complex data set (Abl236) constructed from the co-crystal structures of the cancer target Abl kinase with six inhibitors. To predict ligand binding affinity changes upon protein mutation of Abl kinase, we used sampling protocol with multistep simulated annealing to search conformations of mutant proteins. The scoring strategy based on AMOEBA_CP model has achieved considerable performance in predicting resistance for 8 kinase inhibitors across 144 clinically identified point mutations. Overall, this study illustrates that the AMOEBA_CP model, which accurately treats electrostatics through penetration correction, enables the accurate prediction of the mutation-induced variation of protein-ligand binding affinity.

Big data and artificial intelligence (AI) methodologies for computer-aided drug design (CADD)

There have been numerous advances in the development of computational and statistical methods and applications of big data and artificial intelligence (AI) techniques for computer-aided drug design (CADD). Drug design is a costly and laborious process considering the biological complexity of diseases. To effectively and efficiently design and develop a new drug, CADD can be used to apply cutting-edge techniques to various limitations in the drug design field. Data pre-processing approaches, which clean the raw data for consistent and reproducible applications of big data and AI methods are introduced. We include the current status of the applicability of big data and AI methods to drug design areas such as the identification of binding sites in target proteins, structure-based virtual screening (SBVS), and absorption, distribution, metabolism, excretion and toxicity (ADMET) property prediction. Data pre-processing and applications of big data and AI methods enable the accurate and comprehensive analysis of massive biomedical data and the development of predictive models in the field of drug design. Understanding and analyzing biological, chemical, or pharmaceutical architectures of biomedical entities related to drug design will provide beneficial information in the biomedical big data era.

Applications of machine learning in computer-aided drug discovery

Machine learning (ML) has revolutionised the field of structure-based drug design (SBDD) in recent years. During the training stage, ML techniques typically analyse large amounts of experimentally determined data to create predictive models in order to inform the drug discovery process. Deep learning (DL) is a subfield of ML, that relies on multiple layers of a neural network to extract significantly more complex patterns from experimental data, and has recently become a popular choice in SBDD. This review provides a thorough summary of the recent DL trends in SBDD with a particular focus on de novo drug design, binding site prediction, and binding affinity prediction of small molecules.

Active Site Sequence Representations of Human Kinases Outperform Full Sequence Representations for Affinity Prediction and Inhibitor Generation: 3D Effects in a 1D Model

Recent advances in deep learning have enabled the development of large-scale multimodal models for virtual screening and de novo molecular design. The human kinome with its abundant sequence and inhibitor data presents an attractive opportunity to develop proteochemometric models that exploit the size and internal diversity of this family of targets. Here, we challenge a standard practice in sequence-based affinity prediction models: instead of leveraging the full primary structure of proteins, each target is represented by a sequence of 29 discontiguous residues defining the ATP binding site. In kinase-ligand binding affinity prediction, our results show that the reduced active site sequence representation is not only computationally more efficient but consistently yields significantly higher performance than the full primary structure. This trend persists across different models, data sets, and performance metrics and holds true when predicting pIC₅₀ for both unseen ligands and kinases. Our interpretability analysis reveals a potential explanation for the superiority of the active site models: whereas only mild statistical effects about the extraction of three-dimensional (3D) interaction sites take place in the full sequence models, the active site models are equipped with an implicit but strong inductive bias about the 3D structure stemming from the discontiguity of the active sites. Moreover, in direct comparisons, our models perform similarly or better than previous state-of-the-art approaches in affinity prediction. We then investigate a de novo molecular design task and find that the active site provides benefits in the computational efficiency, but otherwise, both kinase representations yield similar optimized affinities (for both SMILES- and SELFIES-based molecular generators). Our work challenges the assumption that the full primary structure is indispensable for modeling human kinases.

Prediction of Binding Free Energy of Protein-Ligand Complexes with a Hybrid Molecular Mechanics/Generalized Born Surface Area and Machine Learning Method

Accurate prediction of protein-ligand binding free energies is important in enzyme engineering and drug discovery. The molecular mechanics/generalized Born surface area (MM/GBSA) approach is widely used to estimate ligand-binding affinities, but its performance heavily relies on the accuracy of its energy components. A hybrid strategy combining MM/GBSA and machine learning (ML) has been developed to predict the binding free energies of protein-ligand systems. Based on the MM/GBSA energy terms and several features associated with protein-ligand interactions, our ML-based scoring function, GXLE, shows much better performance than MM/GBSA without entropy. In particular, the good transferability of the GXLE model is highlighted by its good performance in ranking power for prediction of the binding affinity of different ligands for either the docked structures or crystal structures. The GXLE scoring function and its code are freely available and can be used to correct the binding free energies computed by MM/GBSA.

LCP: Simple Representation of Docking Poses for Machine Learning: A Case Study on Xanthine Oxidase Inhibitors

In this paper, we propose a simple descriptor called the ligand coordinate profile (LCP) for describing docking poses. The LCP descriptor is generated from the coordinates of the polar hydrogen and heavy atoms of the docked ligand. We hypothesize that the prediction of binding poses can be enhanced through the combination of machine learning methods with the LCP descriptor. Two docking programs were used to predict ligand docking against xanthine oxidase. Four machine learning methods-k-nearest neighbors, random forest, support vector machine, and LightGBM-were used to determine whether machine learning-based models could be used to accurately identify the correct binding poses. Regardless of the machine learning method employed, the LCP descriptor demonstrated improved performance compared to the existing descriptor. The results of the leave-one-pdb-out approach revealed that the influence of the pose descriptor was also significant, as demonstrated through cross-validation. When evaluated using top-N metrics, the machine learning models were generally more effective than the docking programs. In addition, the LCP-based models outperformed those based on the existing descriptor. The results obtained in this study suggest that our proposed binding pose descriptor is effective for improving the docking accuracy of xanthine oxidase inhibitors.

Enhancing preclinical drug discovery with artificial intelligence

Artificial intelligence (AI) is becoming an integral part of drug discovery. It has the potential to deliver across the drug discovery and development value chain, starting from target identification and reaching through clinical development. In this review, we provide an overview of current AI technologies and a glimpse of how AI is reimagining preclinical drug discovery by highlighting examples where AI has made a real impact. Considering the excitement and hyperbole surrounding AI in drug discovery, we aim to present a realistic view by discussing both opportunities and challenges in adopting AI in drug discovery.

The impact of cross-docked poses on performance of machine learning classifier for protein-ligand binding pose prediction

Structure-based drug design depends on the detailed knowledge of the three-dimensional (3D) structures of protein-ligand binding complexes, but accurate prediction of ligand-binding poses is still a major challenge for molecular docking due to deficiency of scoring functions (SFs) and ignorance of protein flexibility upon ligand binding. In this study, based on a cross-docking dataset dedicatedly constructed from the PDBbind database, we developed several XGBoost-trained classifiers to discriminate the near-native binding poses from decoys, and systematically assessed their performance with/without the involvement of the cross-docked poses in the training/test sets. The calculation results illustrate that using Extended Connectivity Interaction Features (ECIF), Vina energy terms and docking pose ranks as the features can achieve the best performance, according to the validation through the random splitting or refined-core splitting and the testing on the re-docked or cross-docked poses. Besides, it is found that, despite the significant decrease of the performance for the threefold clustered cross-validation, the inclusion of the Vina energy terms can effectively ensure the lower limit of the performance of the models and thus improve their generalization capability. Furthermore, our calculation results also highlight the importance of the incorporation of the cross-docked poses into the training of the SFs with wide application domain and high robustness for binding pose prediction. The source code and the newly-developed cross-docking datasets can be freely available at https://github.com/sc8668/ml_pose_prediction and https://zenodo.org/record/5525936 , respectively, under an open-source license. We believe that our study may provide valuable guidance for the development and assessment of new machine learning-based SFs (MLSFs) for the predictions of protein-ligand binding poses.