Improving the binding affinity estimations of protein-ligand complexes using machine-learning facilitated force field method

Identification of potent anti-fibrinolytic compounds against plasminogen and tissue-type plasminogen activator employing in silico approaches

The zymogen protease Plasminogen (Plg) and its active form plasmin (Plm) carry out important functions in the blood clot disintegration (breakdown of fibrin fibers) process. Inhibition of plasmin effectively reduces fibrinolysis to circumvent heavy bleeding. Currently, available Plm inhibitor tranexamic acid (TXA) used for treating severe hemorrhages is associated with an increased incidence of seizures which in turn were traced to gamma-aminobutyric acid antagonistic activity (GABAa) in addition to having multiple side effects. Fibrinolysis can be suppressed by targeting the three important protein domains: the kringle-2 domain of tissue plasminogen activator, the kringle-1 domain of plasminogen, and the serine protease domain of plasminogen. In the present study, one million molecules were screened from the ZINC database. These ligands were docked to their respective protein targets using Autodock Vina, Schrödinger Glide, and ParDOCK/BAPPL+. Thereafter, the drug-likeness properties of the ligands were evaluated using Discovery Studio 3.5. Subsequently, we subjected the protein-ligand complexes to molecular dynamics simulation of 200 ns in GROMACS. The identified ligands P76(ZINC09970930), C97(ZINC14888376), and U97(ZINC11839443) for each protein target are found to impart higher stability and greater compactness to the protein-ligand complexes. Principal component analysis (PCA) implicates, that the identified ligands occupy smaller phase space, form stable clusters, and provide greater rigidity to the protein-ligand complexes. Molecular Mechanics Poisson-Boltzmann Surface Area (MMPBSA) analysis reveals that P76, C97, and U97 exhibit better binding free energy (ΔG) when compared to that of the standard ligands. Thus, our findings can be useful for the development of promising anti-fibrinolytic agents.Communicated by Ramaswamy H. Sarma.

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.

Artificial intelligence in virtual screening: models versus experiments

A typical drug discovery project involves identifying active compounds with significant binding potential for selected disease-specific targets. Experimental high-throughput screening (HTS) is a traditional approach to drug discovery, but is expensive and time-consuming when dealing with huge chemical libraries with billions of compounds. The search space can be narrowed down with the use of reliable computational screening approaches. In this review, we focus on various machine-learning (ML) and deep-learning (DL)-based scoring functions developed for solving classification and ranking problems in drug discovery. We highlight studies in which ML and DL models were successfully deployed to identify lead compounds for which the experimental validations are available from bioassay studies.

Machine Learning Approaches for Metalloproteins

Metalloproteins are a family of proteins characterized by metal ion binding, whereby the presence of these ions confers key catalytic and ligand-binding properties. Due to their ubiquity among biological systems, researchers have made immense efforts to predict the structural and functional roles of metalloproteins. Ultimately, having a comprehensive understanding of metalloproteins will lead to tangible applications, such as designing potent inhibitors in drug discovery. Recently, there has been an acceleration in the number of studies applying machine learning to predict metalloprotein properties, primarily driven by the advent of more sophisticated machine learning algorithms. This review covers how machine learning tools have consolidated and expanded our comprehension of various aspects of metalloproteins (structure, function, stability, ligand-binding interactions, and inhibitors). Future avenues of exploration are also discussed.

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.

Structural Predictive Model of Presenilin-2 Protein and Analysis of Structural Effects of Familial Alzheimer's Disease Mutations

Alzheimer's disease manifests itself in brain tissue by neuronal death, due to aggregation of β-amyloid, produced by senile plaques, and hyperphosphorylation of the tau protein, which produces neurofibrillary tangles. One of the genetic markers of the disease is the gene that translates the presenilin-2 protein, which has mutations that favor the appearance of the disease and has no reported crystallographic structure. In view of this, protein modeling is performed using prediction and structural refinement tools followed by an energetic and stereochemical characterization for its validation. For the simulation, four reported mutations are chosen, which are Met239Ile, Met239Val, Ser130Leu, and Thr122Arg, all associated with various functional responses. From a theoretical analysis, a preliminary bioinformatic study is made to find the phosphorylation patterns in the protein and the hydropathic index according to the polarity and chemical environment. Molecular visualization was carried out with the Chimera 1.14 software, and the theoretical calculation with the hybrid quantum mechanics/molecular mechanics system from the semi-empirical method, with Spartan18 software and an AustinModel1 basis. These relationships allow for studying the system from a structural approach with the determination of small distance changes, potential surfaces, electrostatic maps, and angle changes, which favor the comparison between wild-type and mutant systems. With the results obtained, it is expected to complement experimental data reported in the literature from models that would allow us to understand the effects of the selected mutations.

Recent trends in artificial intelligence-driven identification and development of anti-neurodegenerative therapeutic agents

Neurological disorders affect various aspects of life. Finding drugs for the central nervous system is a very challenging and complex task due to the involvement of the blood-brain barrier, P-glycoprotein, and the drug's high attrition rates. The availability of big data present in online databases and resources has enabled the emergence of artificial intelligence techniques including machine learning to analyze, process the data, and predict the unknown data with high efficiency. The use of these modern techniques has revolutionized the whole drug development paradigm, with an unprecedented acceleration in the central nervous system drug discovery programs. Also, the new deep learning architectures proposed in many recent works have given a better understanding of how artificial intelligence can tackle big complex problems that arose due to central nervous system disorders. Therefore, the present review provides comprehensive and up-to-date information on machine learning/artificial intelligence-triggered effort in the brain care domain. In addition, a brief overview is presented on machine learning algorithms and their uses in structure-based drug design, ligand-based drug design, ADMET prediction, de novo drug design, and drug repurposing. Lastly, we conclude by discussing the major challenges and limitations posed and how they can be tackled in the future by using these modern machine learning/artificial intelligence approaches.

Protein Predictive Modeling and Simulation of Mutations of Presenilin-1 Familial Alzheimer's Disease on the Orthosteric Site

Alzheimer's disease pathology is characterized by β-amyloid plaques and neurofibrillary tangles. Amyloid precursor protein is processed by β and γ secretase, resulting in the production of β-amyloid peptides with a length ranging from 38 to 43 amino acids. Presenilin 1 (PS1) is the catalytic unit of γ-secretase, and more than 200 PS1 pathogenic mutations have been identified as causative for Alzheimer's disease. A complete monocrystal structure of PS1 has not been determined so far due to the presence of two flexible domains. We have developed a complete structural model of PS1 using a computational approach with structure prediction software. Missing fragments Met1-Glut72 and Ser290-Glu375 were modeled and validated by their energetic and stereochemical characteristics. Then, with the complete structure of PS1, we defined that these fragments do not have a direct effect in the structure of the pore. Next, we used our hypothetical model for the analysis of the functional effects of PS1 mutations Ala246GLu, Leu248Pro, Leu248Arg, Leu250Val, Tyr256Ser, Ala260Val, and Val261Phe, localized in the catalytic pore. For this, we used a quantum mechanics/molecular mechanics (QM/MM) hybrid method, evaluating modifications in the topology, potential surface density, and electrostatic potential map of mutated PS1 proteins. We found that each mutation exerts changes resulting in structural modifications of the active site and in the shape of the pore. We suggest this as a valid approach for functional studies of PS1 in view of the possible impact in substrate processing and for the design of targeted therapeutic strategies.

Docking Paradigm in Drug Design

Docking is in demand for the rational computer aided structure based drug design. A review of docking methods and programs is presented. Different types of docking programs are described. They include docking of non-covalent small ligands, protein-protein docking, supercomputer docking, quantum docking, the new generation of docking programs and the application of docking for covalent inhibitors discovery. Taking into account the threat of COVID-19, we present here a short review of docking applications to the discovery of inhibitors of SARS-CoV and SARS-CoV-2 target proteins, including our own result of the search for inhibitors of SARS-CoV-2 main protease using docking and quantum chemical post-processing. The conclusion is made that docking is extremely important in the fight against COVID-19 during the process of development of antivirus drugs having a direct action on SARS-CoV-2 target proteins.