Delta Machine Learning to Improve Scoring-Ranking-Screening Performances of Protein-Ligand Scoring Functions

Augmenting genetic algorithms with machine learning for inverse molecular design

Evolutionary and machine learning methods have been successfully applied to the generation of molecules and materials exhibiting desired properties. The combination of these two paradigms in inverse design tasks can yield powerful methods that explore massive chemical spaces more efficiently, improving the quality of the generated compounds. However, such synergistic approaches are still an incipient area of research and appear underexplored in the literature. This perspective covers different ways of incorporating machine learning approaches into evolutionary learning frameworks, with the overall goal of increasing the optimization efficiency of genetic algorithms. In particular, machine learning surrogate models for faster fitness function evaluation, discriminator models to control population diversity on-the-fly, machine learning based crossover operations, and evolution in latent space are discussed. The further potential of these synergistic approaches in generative tasks is also assessed, outlining promising directions for future developments.

SPRank─A Knowledge-Based Scoring Function for RNA-Ligand Pose Prediction and Virtual Screening

The growing interest in RNA-targeted drugs underscores the need for computational modeling of interactions between RNA molecules and small compounds. Having a reliable scoring function for RNA-ligand interactions is essential for effective computational drug screening. An ideal scoring function should not only predict the native pose for ligand binding but also rank the affinity of the binding for different ligands. However, existing scoring functions are primarily designed to predict the native binding modes for a given RNA-ligand pair and have not been thoroughly assessed for virtual screening purposes. In this paper, we introduce SPRank, a combination of machine-learning and knowledge-based scoring functions developed through a weighted iterative approach, specifically designed to tackle both binding mode prediction and virtual screening challenges. Our approach incorporates third-party docking software, such as rDock and AutoDock Vina, to sample flexible ligands against an ensemble of RNA structures, capturing the conformational flexibility of both the RNA and the ligand. Through rigorous testing, SPRank demonstrates improved performance compared to the tested scoring functions across four test sets comprising 122, 42, 55, and 71 nucleic acid-ligand complexes. Furthermore, SPRank exhibits improved performance in virtual screening tests targeting the HIV-1 TAR ensemble, which highlights its advantage in drug discovery. These results underscore the advantages of SPRank as a potentially promising tool for the RNA-targeted drug design. The source code of SPRank and the data sets are freely accessible at https://github.com/Vfold-RNA/SPRank.

A Repurposed Drug Interferes with Nucleic Acid to Inhibit the Dual Activities of Coronavirus Nsp13

The recent pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) highlighted a critical need to discover more effective antivirals. While therapeutics for SARS-CoV-2 exist, its nonstructural protein 13 (Nsp13) remains a clinically untapped target. Nsp13 is a helicase responsible for unwinding double-stranded RNA during viral replication and is essential for propagation. Like other helicases, Nsp13 has two active sites: a nucleotide binding site that hydrolyzes nucleoside triphosphates (NTPs) and a nucleic acid binding channel that unwinds double-stranded RNA or DNA. Targeting viral helicases with small molecules, as well as the identification of ligand binding pockets, have been ongoing challenges, partly due to the flexible nature of these proteins. Here, we use a virtual screen to identify ligands of Nsp13 from a collection of clinically used drugs. We find that a known ion channel inhibitor, IOWH-032, inhibits the dual ATPase and helicase activities of SARS-CoV-2 Nsp13 at low micromolar concentrations. Kinetic and binding assays, along with computational and mutational analyses, indicate that IOWH-032 interacts with the RNA binding interface, leading to displacement of nucleic acid substrate, but not bound ATP. Evaluation of IOWH-032 with microbial helicases from other superfamilies reveals that it is selective for coronavirus Nsp13. Furthermore, it remains active against mutants representative of observed SARS-CoV-2 variants. Overall, this work provides a new inhibitor for Nsp13 and provides a rationale for a recent observation that IOWH-032 lowers SARS-CoV-2 viral loads in human cells, setting the stage for the discovery of other potent viral helicase modulators.

Geometry Optimization Algorithms in Conjunction with the Machine Learning Potential ANI-2x Facilitate the Structure-Based Virtual Screening and Binding Mode Prediction

Structure-based virtual screening utilizes molecular docking to explore and analyze ligand-macromolecule interactions, crucial for identifying and developing potential drug candidates. Although there is availability of several widely used docking programs, the accurate prediction of binding affinity and binding mode still presents challenges. In this study, we introduced a novel protocol that combines our in-house geometry optimization algorithm, the conjugate gradient with backtracking line search (CG-BS), which is capable of restraining and constraining rotatable torsional angles and other geometric parameters with a highly accurate machine learning potential, ANI-2x, renowned for its precise molecular energy predictions reassembling the wB97X/6-31G(d) model. By integrating this protocol with binding pose prediction using the Glide, we conducted additional structural optimization and potential energy prediction on 11 small molecule-macromolecule and 12 peptide-macromolecule systems. We observed that ANI-2x/CG-BS greatly improved the docking power, not only optimizing binding poses more effectively, particularly when the RMSD of the predicted binding pose by Glide exceeded around 5 Å, but also achieving a 26% higher success rate in identifying those native-like binding poses at the top rank compared to Glide docking. As for the scoring and ranking powers, ANI-2x/CG-BS demonstrated an enhanced performance in predicting and ranking hundreds or thousands of ligands over Glide docking. For example, Pearson's and Spearman's correlation coefficients remarkedly increased from 0.24 and 0.14 with Glide docking to 0.85 and 0.69, respectively, with the addition of ANI-2x/CG-BS for optimizing and ranking small molecules binding to the bacterial ribosomal aminoacyl-tRNA receptor. These results suggest that ANI-2x/CG-BS holds considerable potential for being integrated into virtual screening pipelines due to its enhanced docking performance.

Gender potentially affects early postoperative hyponatremia in pituitary adenoma: XGBoost-based predictive modeling

Purpose

The occurrence of hyponatremia is a prevalent complication following transnasal transsphenoidal surgery for pituitary adenoma surgery, which adversely affects patient prognosis, hospitalization duration, and rehospitalization risk. The primary objective of this study is to strengthen the correlation between clinical factors associated with pituitary adenoma and postoperative hyponatremia. Additionally, the study aims to develop a predictive model for postoperative hyponatremia in patients with pituitary adenoma, with the ultimate goal of establishing a basis for reducing the occurrence of postoperative hyponatremia following surgical interventions.

Methods

The chi-square test or Fisher test was employed for nominal data, while the t-test or Mann-Whitney test was utilized for continuous data analysis. In cases where the data exhibited statistical differences, binary logistic analysis was conducted to examine the risk and protective factors associated with postoperative hyponatremia. XGBoost was employed to construct predictive models for hyponatremia in this study. The patients were partitioned into training and test sets, and the most suitable parameters were determined through five-fold cross-validation and subsequently utilized for training on the training set. The discriminatory capability was assessed on the internal validation set.

Results and conclusions

Out of the total 280 patients included in this investigation, 82 patients experienced early postoperative hyponatremia. Among these individuals, male gender (P = 0.02, odds ratio = 1.98) was identified as a risk factor for early postoperative hyponatremia, while preoperative chloride levels (P = 0.021, odds ratio = 0.866) and surgery time (P = 0.039, odds ratio = 0.990) were identified as protective factors against postoperative hyponatremia. The XGBoost model exhibited a sensitivity of 94.2%, a specificity of 61.5%, a positive predictive value of 51.6%, a negative predictive value of 96%, and identified male gender, preoperative sodium, and preoperative cortisol as the most significant predictors. Our findings indicate that gender may have influence in the development of early postoperative hyponatremia in patients with pituitary adenomas.

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.

Enhancing Generalizability in Protein-Ligand Binding Affinity Prediction with Multimodal Contrastive Learning

Improving the generalization ability of scoring functions remains a major challenge in protein-ligand binding affinity prediction. Many machine learning methods are limited by their reliance on single-modal representations, hindering a comprehensive understanding of protein-ligand interactions. We introduce a graph-neural-network-based scoring function that utilizes a triplet contrastive learning loss to improve protein-ligand representations. In this model, three-dimensional complex representations and the fusion of two-dimensional ligand and coarse-grained pocket representations converge while distancing from decoy representations in latent space. After rigorous validation on multiple external data sets, our model exhibits commendable generalization capabilities compared to those of other deep learning-based scoring functions, marking it as a promising tool in the realm of drug discovery. In the future, our training framework can be extended to other biophysical- and biochemical-related problems such as protein-protein interaction and protein mutation prediction.

Drugging the entire human proteome: Are we there yet?

Each of the ∼20,000 proteins in the human proteome is a potential target for compounds that bind to it and modify its function. The 3D structures of most of these proteins are now available. Here, we discuss the prospects for using these structures to perform proteome-wide virtual HTS (VHTS). We compare physics-based (docking) and AI VHTS approaches, some of which are now being applied with large databases of compounds to thousands of targets. Although preliminary proteome-wide screens are now within our grasp, further methodological developments are expected to improve the accuracy of the results.

Integrating Artificial Intelligence for Drug Discovery in the Context of Revolutionizing Drug Delivery

Drug development is expensive, time-consuming, and has a high failure rate. In recent years, artificial intelligence (AI) has emerged as a transformative tool in drug discovery, offering innovative solutions to complex challenges in the pharmaceutical industry. This manuscript covers the multifaceted role of AI in drug discovery, encompassing AI-assisted drug delivery design, the discovery of new drugs, and the development of novel AI techniques. We explore various AI methodologies, including machine learning and deep learning, and their applications in target identification, virtual screening, and drug design. This paper also discusses the historical development of AI in medicine, emphasizing its profound impact on healthcare. Furthermore, it addresses AI's role in the repositioning of existing drugs and the identification of drug combinations, underscoring its potential in revolutionizing drug delivery systems. The manuscript provides a comprehensive overview of the AI programs and platforms currently used in drug discovery, illustrating the technological advancements and future directions of this field. This study not only presents the current state of AI in drug discovery but also anticipates its future trajectory, highlighting the challenges and opportunities that lie ahead.

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.

Amalgamated Pharmacoinformatics Study to Investigate the Mechanism of Xiao Jianzhong Tang against Chronic Atrophic Gastritis

BACKGROUND

Traditional Chinese medicine (TCM) Xiao Jianzhong Tang (XJZ) has a favorable efficacy in the treatment of chronic atrophic gastritis (CAG). However, its pharmacological mechanism has not been fully explained.

OBJECTIVE

The purpose of this study was to find the potential mechanism of XJZ in the treatment of CAG using pharmacocoinformatics approaches.

METHODS

Network pharmacology was used to screen out the key compounds and key targets, MODELLER and GNNRefine were used to repair and refine proteins, Autodock vina was employed to perform molecular docking, Δ Lin_F9XGB was used to score the docking results, and Gromacs was used to perform molecular dynamics simulations (MD).

RESULTS

Kaempferol, licochalcone A, and naringenin, were obtained as key compounds, while AKT1, MAPK1, MAPK14, RELA, STAT1, and STAT3 were acquired as key targets. Among docking results, 12 complexes scored greater than five. They were run for 50ns MD. The free binding energy of AKT1-licochalcone A and MAPK1-licochalcone A was less than -15 kcal/mol and AKT1-naringenin and STAT3-licochalcone A was less than -9 kcal/mol. These complexes were crucial in XJZ treating CAG.

CONCLUSION

Our findings suggest that licochalcone A could act on AKT1, MAPK1, and STAT3, and naringenin could act on AKT1 to play the potential therapeutic effect on CAG. The work also provides a powerful approach to interpreting the complex mechanism of TCM through the amalgamation of network pharmacology, deep learning-based protein refinement, molecular docking, machine learning-based binding affinity estimation, MD simulations, and MM-PBSA-based estimation of binding free energy.

Protein engineering in the computational age: An open source framework for exploring mutational landscapes in silico

The field of protein engineering has seen tremendous expansion in the last decade, with researchers developing novel proteins with specialised functionalities for a range of uses, from drug discovery to industrial biotechnology. The emergence of computational tools and high-throughput screening technology has substantially sped up the process of protein engineering. However, much of the expertise required to engage in such projects is still concentrated in the hands of a few specialised individuals, including computational biologists and structural biochemists. The international Genetically Engineered Machine (iGEM) competition represents a platform for undergraduate students to innovate in synthetic biology. Yet, due to their complexity, arduous protein engineering projects are hindered by the resources available and strict timelines of the competition. The authors highlight how the 2022 iGEM Team, 'Sporadicate', set out to develop InFinity 1.0, a computational framework for increased accessibility to effective protein engineering, hoping to increase awareness and accessibility to novel in silico tools.

Template-guided method for protein-ligand complex structure prediction: Application to CASP15 protein-ligand studies

Critical Assessment of Structure Prediction 15 (CASP15) added a new category of ligand prediction to promote the development of protein/RNA-ligand modeling methods, which have become important tools in modern drug discovery. A total of 22 targets were released, including 18 protein-ligand targets and 4 RNA-ligand targets. We applied our recently developed template-guided method to the protein-ligand complex structure predictions. The method combined a physicochemical, molecular docking method, and a bioinformatics-based ligand similarity method. The Protein Data Bank was scanned for template structures containing the target protein, homologous proteins, or proteins sharing a similar fold with the target protein. The binding modes of the co-bound ligands in the template structures were used to guide the complex structure prediction for the target. The CASP assessment results show that the overall performance of our method was ranked second when the top predicted model was considered for each target. Here, we analyzed our predictions in detail, and discussed the challenges including protein conformational changes, large and flexible ligands, and multiple diverse ligands in a binding pocket.

An overview of recent advances and challenges in predicting compound-protein interaction (CPI)

Compound-protein interactions (CPIs) are critical in drug discovery for identifying therapeutic targets, drug side effects, and repurposing existing drugs. Machine learning (ML) algorithms have emerged as powerful tools for CPI prediction, offering notable advantages in cost-effectiveness and efficiency. This review provides an overview of recent advances in both structure-based and non-structure-based CPI prediction ML models, highlighting their performance and achievements. It also offers insights into CPI prediction-related datasets and evaluation benchmarks. Lastly, the article presents a comprehensive assessment of the current landscape of CPI prediction, elucidating the challenges faced and outlining emerging trends to advance the field.

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.

Iterative Knowledge-Based Scoring Function for Protein-Ligand Interactions by Considering Binding Affinity Information

Scoring functions for protein-ligand interactions play a critical role in structure-based drug design. Owing to the good balance between general applicability and computational efficiency, knowledge-based scoring functions have obtained significant advancements and achieved many successes. Nevertheless, knowledge-based scoring functions face a challenge in utilizing the experimental affinity data and thus may not perform well in binding affinity prediction. Addressing the challenge, we have proposed an improved version of the iterative knowledge-based scoring function ITScore by considering binding affinity information, which is referred to as ITScoreAff, based on a large training set of 6216 protein-ligand complexes with both structures and affinity data. ITScoreAff was extensively evaluated and compared with ITScore, 33 traditional, and 6 machine learning scoring functions in terms of docking power, ranking power, and screening power on the independent CASF-2016 benchmark. It was shown that ITScoreAff obtained an overall better performance than the other 40 scoring functions and gave an average success rate of 85.3% in docking power, a correlation coefficient of 0.723 in scoring power, and an average rank correlation coefficient of 0.668 in ranking power. In addition, ITScoreAff also achieved the overall best screening power when the top 10% of the ranked database were considered. These results demonstrated the robustness of ITScoreAff and its improvement over existing scoring functions.

Ligand binding affinity prediction with fusion of graph neural networks and 3D structure-based complex graph

Accurate prediction of protein-ligand binding affinity is pivotal for drug design and discovery. Here, we proposed a novel deep fusion graph neural networks framework named FGNN to learn the protein-ligand interactions from the 3D structures of protein-ligand complexes. Unlike 1D sequences for proteins or 2D graphs for ligands, the 3D graph of protein-ligand complex enables the more accurate representations of the protein-ligand interactions. Benchmark studies have shown that our fusion models FGNN can achieve more accurate prediction of binding affinity than any individual algorithm. The advantages of fusion strategies have been demonstrated in terms of expressive power of data, learning efficiency and model interpretability. Our fusion models show satisfactory performances on diverse data sets, demonstrating their generalization ability. Given the good performances in both binding affinity prediction and virtual screening, our fusion models are expected to be practically applied for drug screening and design. Our work highlights the potential of the fusion graph neural network algorithm in solving complex prediction problems in computational biology and chemistry. The fusion graph neural networks (FGNN) model is freely available in https://github.com/LinaDongXMU/FGNN.

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.

A generalized protein-ligand scoring framework with balanced scoring, docking, ranking and screening powers

Applying machine learning algorithms to protein-ligand scoring functions has aroused widespread attention in recent years due to the high predictive accuracy and affordable computational cost. Nevertheless, most machine learning-based scoring functions are only applicable to a specific task, e.g., binding affinity prediction, binding pose prediction or virtual screening, suggesting that the development of a scoring function with balanced performance in all critical tasks remains a grand challenge. To this end, we propose a novel parameterization strategy by introducing an adjustable binding affinity term that represents the correlation between the predicted outcomes and experimental data into the training of mixture density network. The resulting residue-atom distance likelihood potential not only retains the superior docking and screening power over all the other state-of-the-art approaches, but also achieves a remarkable improvement in scoring and ranking performance. We emphatically explore the impacts of several key elements on prediction accuracy as well as the task preference, and demonstrate that the performance of scoring/ranking and docking/screening tasks of a certain model could be well balanced through an appropriate manner. Overall, our study highlights the potential utility of our innovative parameterization strategy as well as the resulting scoring framework in future structure-based drug design.

Conserved Sites and Recognition Mechanisms of T1R1 and T2R14 Receptors Revealed by Ensemble Docking and Molecular Descriptors and Fingerprints Combined with Machine Learning

Taste peptides, as an important component of protein-rich foodstuffs, potentiate the nutrition and taste of food. Thereinto, umami- and bitter-taste peptides have been ex tensively reported, while their taste mechanisms remain unclear. Meanwhile, the identification of taste peptides is still a time-consuming and costly task. In this study, 489 peptides with umami/bitter taste from TPDB (http://tastepeptides-meta.com/) were collected and used to train the classification models based on docking analysis, molecular descriptors (MDs), and molecular fingerprints (FPs). A consensus model, taste peptide docking machine (TPDM), was generated based on five learning algorithms (linear regression, random forest, gaussian naive bayes, gradient boosting tree, and stochastic gradient descent) and four molecular representation schemes. Model interpretive analysis showed that MDs (VSA_EState, MinEstateIndex, MolLogP) and FPs (598, 322, 952) had the greatest impact on the umami/bitter prediction of peptides. Based on the consensus docking results, we obtained the key recognition modes of umami/bitter receptors (T1Rs/T2Rs): (1) residues 107S-109S, 148S-154T, 247F-249A mainly form hydrogen bonding contacts and (2) residues 153A-158L, 163L, 181Q, 218D, 247F-249A in T1R1 and 56D, 106P, 107V, 152V-156F, 173K-180F in T2R14 constituted their hydrogen bond pockets. The model is available at http://www.tastepeptides-meta.com/yyds.

New avenues in artificial-intelligence-assisted drug discovery

Over the past decade, the amount of biomedical data available has grown at unprecedented rates. Increased automation technology and larger data volumes have encouraged the use of machine learning (ML) or artificial intelligence (AI) techniques for mining such data and extracting useful patterns. Because the identification of chemical entities with desired biological activity is a crucial task in drug discovery, AI technologies have the potential to accelerate this process and support decision making. In addition, the advent of deep learning (DL) has shown great promise in addressing diverse problems in drug discovery, such as de novo molecular design. Herein, we will appraise the current state-of-the-art in AI-assisted drug discovery, discussing the recent applications covering generative models for chemical structure generation, scoring functions to improve binding affinity and pose prediction, and molecular dynamics to assist in the parametrization, featurization and generalization tasks. Finally, we will discuss current hurdles and the strategies to overcome them, as well as potential future directions.

Structural Analysis, Multi-Conformation Virtual Screening and Molecular Simulation to Identify Potential Inhibitors Targeting pS273R Proteases of African Swine Fever Virus

The African Swine Fever virus (ASFV) causes an infectious viral disease in pigs of all ages. The development of antiviral drugs primarily aimed at inhibition of proteases required for the proteolysis of viral polyproteins. In this study, the conformation of the pS273R protease in physiological states were investigated, virtually screened the multi-protein conformation of pS273R target proteins, combined various molecular docking scoring functions, and identified five potential drugs from the Food and Drug Administration drug library that may inhibit pS273R. Subsequent validation of the dynamic interactions of pS273R with the five putative inhibitors was achieved using molecular dynamics simulations and binding free energy calculations using the molecular mechanics/Poison-Boltzmann (Generalized Born) (MM/PB(GB)SA) surface area. These findings demonstrate that the arm domain and Thr159-Lys167 loop region of pS273R are significantly more flexible compared to the core structural domain, and the Thr159-Lys167 loop region can serve as a "gatekeeper" in the substrate channel. Leucovorin, Carboprost, Protirelin, Flavin Mononucleotide, and Lovastatin Acid all have Gibbs binding free energies with pS273R that were less than -20 Kcal/mol according to the MM/PBSA analyses. In contrast to pS273R in the free energy landscape, the inhibitor and drug complexes of pS273R showed distinct structural group distributions. These five drugs may be used as potential inhibitors of pS273R and may serve as future drug candidates for treating ASFV.

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.

Protein-Ligand Docking in the Machine-Learning Era

Molecular docking plays a significant role in early-stage drug discovery, from structure-based virtual screening (VS) to hit-to-lead optimization, and its capability and predictive power is critically dependent on the protein-ligand scoring function. In this review, we give a broad overview of recent scoring function development, as well as the docking-based applications in drug discovery. We outline the strategies and resources available for structure-based VS and discuss the assessment and development of classical and machine learning protein-ligand scoring functions. In particular, we highlight the recent progress of machine learning scoring function ranging from descriptor-based models to deep learning approaches. We also discuss the general workflow and docking protocols of structure-based VS, such as structure preparation, binding site detection, docking strategies, and post-docking filter/re-scoring, as well as a case study on the large-scale docking-based VS test on the LIT-PCBA data set.