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

Deciphering the Lexicon of Protein Targets: A Review on Multifaceted Drug Discovery in the Era of Artificial Intelligence

Understanding protein sequence and structure is essential for understanding protein-protein interactions (PPIs), which are essential for many biological processes and diseases. Targeting protein binding hot spots, which regulate signaling and growth, with rational drug design is promising. Rational drug design uses structural data and computational tools to study protein binding sites and protein interfaces to design inhibitors that can change these interactions, thereby potentially leading to therapeutic approaches. Artificial intelligence (AI), such as machine learning (ML) and deep learning (DL), has advanced drug discovery and design by providing computational resources and methods. Quantum chemistry is essential for drug reactivity, toxicology, drug screening, and quantitative structure-activity relationship (QSAR) properties. This review discusses the methodologies and challenges of identifying and characterizing hot spots and binding sites. It also explores the strategies and applications of artificial-intelligence-based rational drug design technologies that target proteins and protein-protein interaction (PPI) binding hot spots. It provides valuable insights for drug design with therapeutic implications. We have also demonstrated the pathological conditions of heat shock protein 27 (HSP27) and matrix metallopoproteinases (MMP2 and MMP9) and designed inhibitors of these proteins using the drug discovery paradigm in a case study on the discovery of drug molecules for cancer treatment. Additionally, the implications of benzothiazole derivatives for anticancer drug design and discovery are deliberated.

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.

DeePNAP: A Deep Learning Method to Predict Protein-Nucleic Acid Binding Affinity from Their Sequences

Predicting the protein-nucleic acid (PNA) binding affinity solely from their sequences is of paramount importance for the experimental design and analysis of PNA interactions (PNAIs). A large number of currently developed models for binding affinity prediction are limited to specific PNAIs while also relying on the sequence and structural information of the PNA complexes for both training and testing, and also as inputs. As the PNA complex structures available are scarce, this significantly limits the diversity and generalizability due to the small training data set. Additionally, a majority of the tools predict a single parameter, such as binding affinity or free energy changes upon mutations, rendering a model less versatile for usage. Hence, we propose DeePNAP, a machine learning-based model built from a vast and heterogeneous data set with 14,401 entries (from both eukaryotes and prokaryotes) from the ProNAB database, consisting of wild-type and mutant PNA complex binding parameters. Our model precisely predicts the binding affinity and free energy changes due to the mutation(s) of PNAIs exclusively from their sequences. While other similar tools extract features from both sequence and structure information, DeePNAP employs sequence-based features to yield high correlation coefficients between the predicted and experimental values with low root mean squared errors for PNA complexes in predicting KD and ΔΔG, implying the generalizability of DeePNAP. Additionally, we have also developed a web interface hosting DeePNAP that can serve as a powerful tool to rapidly predict binding affinities for a myriad of PNAIs with high precision toward developing a deeper understanding of their implications in various biological systems. Web interface: http://14.139.174.41:8080/.

D, Chakravarty M, Jamma T, Yogeeswari P. Targeting hexokinase 2 for oral cancer therapy: structure-based design and validation of lead compounds

The pursuit of small molecule inhibitors targeting hexokinase 2 (HK2) has significantly captivated the field of cancer drug discovery. Nevertheless, the creation of selective inhibitors aimed at specific isoforms of hexokinase (HK) remains a formidable challenge. Here, we present a multiple-pharmacophore modeling approach for designing ligands against HK2 with a marked anti-proliferative effect on FaDu and Cal27 oral cancer cell lines. Molecular dynamics (MD) simulations showed that the prototype ligand exhibited a higher affinity towards HK2. Complementing this, we put forth a sustainable synthetic pathway: an environmentally conscious, single-step process facilitated through a direct amidation of the ester with an amine under transition-metal-free conditions with an excellent yield in ambient temperature, followed by a column chromatography avoided separation technique of the identified lead bioactive compound (H2) that exhibited cell cycle arrest and apoptosis. We observed that the inhibition of HK2 led to the loss of mitochondrial membrane potential and increased mitophagy as a potential mechanism of anticancer action. The lead H2 also reduced the growth of spheroids. Collectively, these results indicated the proof-of-concept for the prototypical lead towards HK2 inhibition with anti-cancer potential.

Secondary metabolites of Trichoderma spp. as EGFR tyrosine kinase inhibitors: Evaluation of anticancer efficacy through computational approach

The present study explores the epidermal growth factor receptor (EGFR) tyrosine kinase inhibition efficacy of secondary metabolites in Trichoderma spp. through molecular docking, molecular dynamics (MD) simulation and MM-PBSA approach. The result of molecular docking confirmed that out of 200 metabolites screened, three metabolites such as Harzianelactone A, Pretrichodermamide G and Aspochalasin M, potentially bound with the active binding site of EGFR tyrosine kinase domain(PDB ID: 1M17) with a threshold docking score of ≤- 9.0 kcal/mol when compared with the standard EGFR inhibitor (Erlotinib). The MD simulation was run to investigate the potential for stable complex formation in EGFR tyrosine kinase domain-unbound/lead metabolite (Aspochalasin M)-bound/standard inhibitor (Erlotinib)-bound complex. The MD simulation analysis at 100 ns revealed that Aspochalasin M formed the stable complex with EGFR. Besides, the in silico predication of pharmacokinetic properties further confirmed that Aspochalasin M qualified the drug-likeness rules with no harmful side effects (viz., hERG toxicity, hepatotoxicity and skin sensitization), non-mutagenicity and favourable logBB value. Moreover, the BOILED-Egg model predicted that Aspochalasin M showed a higher gastrointestinal absorption with improved bioavailability when administered orally and removed from the central nervous system (CNS). The results of the computational studies concluded that Aspochalasin M possessed significant efficacy in binding EGFR's active sites compared to the known standard inhibitor (Erlotinib). Therefore, Aspochalasin M can be used as a possible anticancer drug candidate and further in vitro and in vivo experimental validation of Aspochalasin M of Trichoderma spp. are required to determine its anticancer potential.

Considerations Around Structure-Based Drug Discovery for KRAS Using DOCK

Molecular docking is a popular computational tool in drug discovery. Leveraging structural information, docking software predicts binding poses of small molecules to cavities on the surfaces of proteins. Virtual screening for ligand discovery is a useful application of docking software. In this chapter, using the enigmatic KRAS protein as an example system, we endeavor to teach the reader about best practices for performing molecular docking with UCSF DOCK. We discuss methods for virtual screening and docking molecules on KRAS. We present the following six points to optimize our docking setup for prosecuting a virtual screen: protein structure choice, pocket selection, optimization of the scoring function, modification of sampling spheres and sampling procedures, choosing an appropriate portion of chemical space to dock, and the choice of which top scoring molecules to pick for purchase.

From Byte to Bench to Bedside: Molecular Dynamics Simulations and Drug Discovery

Molecular dynamics (MD) simulations and computer-aided drug design (CADD) have advanced substantially over the past two decades, thanks to continuous computer hardware and software improvements. Given these advancements, MD simulations are poised to become even more powerful tools for investigating the dynamic interactions between potential small-molecule drugs and their target proteins, with significant implications for pharmacological research.

Expanding the therapeutic arsenal against cancer: a computational investigation of hybrid xanthone derivatives as selective Topoisomerase 2α ATPase inhibitors

The DNA topoisomerase II (topo II) enzyme plays an important role in the replication, recombination, and repair of DNA. Despite their widespread applications in cancer therapy, new, selective, and potent topo II inhibitors with better pharmaceutical profiles are needed to handle drug resistance and severe adverse effects. In this respect, an array of 36 new anticancer compounds was designed based on a Xanthone core tethered to multifunctional Pyridine-amines and Imidazole scaffold via alkyl chain linkers. An integrated in silico approach was used to understand the structural basis and mechanism of inhibition of the hybrid xanthone derivatives. In this study, we established an initial virtual screening workflow based on pharmacophore mapping, docking, and cancer target association to validate the target selection process. Next, a simulation-based docking was conducted along with pharmacokinetic analysis to filter out the five best compounds (7, 10, 25, 27, and 30) having binding energies within the range of -60.45 to -40.97 kcal/mol. The screened compounds were further subjected to molecular dynamics simulation for 200 ns followed by MM-GBSA and ligand properties analysis to assess the stability and binding affinity to hTOP2α. The top-ranking hits 3,7-bis(3-(2-aminopyridin-3-ylhydroxy)propoxy)-1-hydroxy-9H-xanthen-9-one (ligand 7) and 3,8-bis(3-(2-aminopyridin-3-ylhydroxy)propoxy)-1-hydroxy-9H-xanthen-9-one (ligand 25) were found to have no toxicity, optimum pharmacokinetic and, DFT properties and stable intermolecular interactions with the active site of hTopo IIα protein. In conclusion, further in vitro and in vivo experimental validation of the identified lead molecules is warranted for the discovery of new human Topoisomerase 2 alpha inhibitors.Communicated by Ramaswamy H. Sarma.

Staying Ahead of the Game: How SARS-CoV-2 has Accelerated the Application of Machine Learning in Pandemic Management

In recent years, machine learning (ML) techniques have garnered considerable interest for their potential use in accelerating the rate of drug discovery. With the emergence of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, the utilization of ML has become even more crucial in the search for effective antiviral medications. The pandemic has presented the scientific community with a unique challenge, and the rapid identification of potential treatments has become an urgent priority. Researchers have been able to accelerate the process of identifying drug candidates, repurposing existing drugs, and designing new compounds with desirable properties using machine learning in drug discovery. To train predictive models, ML techniques in drug discovery rely on the analysis of large datasets, including both experimental and clinical data. These models can be used to predict the biological activities, potential side effects, and interactions with specific target proteins of drug candidates. This strategy has proven to be an effective method for identifying potential coronavirus disease 2019 (COVID-19) and other disease treatments. This paper offers a thorough analysis of the various ML techniques implemented to combat COVID-19, including supervised and unsupervised learning, deep learning, and natural language processing. The paper discusses the impact of these techniques on pandemic drug development, including the identification of potential treatments, the understanding of the disease mechanism, and the creation of effective and safe therapeutics. The lessons learned can be applied to future outbreaks and drug discovery initiatives.

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.

Industrializing AI/ML during the end-to-end drug discovery process

Drug discovery aims to select proper targets and drug candidates to address unmet clinical needs. The end-to-end drug discovery process includes all stages of drug discovery from target identification to drug candidate selection. Recently, several artificial intelligence and machine learning (AI/ML)-based drug discovery companies have attempted to build data-driven platforms spanning the end-to-end drug discovery process. The ability to identify elusive targets essentially leads to the diversification of discovery pipelines, thereby increasing the ability to address unmet needs. Modern ML technologies are complementing traditional computer-aided drug discovery by accelerating candidate optimization in innovative ways. This review summarizes recent developments in AI/ML methods from target identification to molecule optimization, and concludes with an overview of current industrial trends in end-to-end AI/ML platforms.

Dissecting the Enantioselective Neurotoxicity of Isocarbophos: Chiral Insight from Cellular, Molecular, and Computational Investigations

Chiral organophosphorus pollutants are found abundantly in the environment, but the neurotoxicity risks of these asymmetric chemicals to human health have not been fully assessed. Using cellular, molecular, and computational toxicology methods, this story is to explore the static and dynamic toxic actions and its stereoselective differences of chiral isocarbophos toward SH-SY5Y nerve cells mediated by acetylcholinesterase (AChE) and further dissect the microscopic basis of enantioselective neurotoxicity. Cell-based assays indicate that chiral isocarbophos exhibits strong enantioselectivity in the inhibition of the survival rates of SH-SY5Y cells and the intracellular AChE activity, and the cytotoxicity of (S)-isocarbophos is significantly greater than that of (R)-isocarbophos. The inhibitory effects of isocarbophos enantiomers on the intracellular AChE activity are dose-dependent, and the half-maximal inhibitory concentrations (IC₅₀) of (R)-/(S)-isocarbophos are 6.179/1.753 μM, respectively. Molecular experiments explain the results of cellular assays, namely, the stereoselective toxic actions of isocarbophos enantiomers on SH-SY5Y cells are stemmed from the differences in bioaffinities between isocarbophos enantiomers and neuronal AChE. In the meantime, the modes of neurotoxic actions display that the key amino acid residues formed strong noncovalent interactions are obviously different, which are related closely to the molecular structural rigidity of chiral isocarbophos and the conformational dynamics and flexibility of the substrate binding domain in neuronal AChE. Still, we observed that the stable "sandwich-type π-π stacking" fashioned between isocarbophos enantiomers and aromatic Trp-86 and Tyr-337 residues is crucial, which notably reduces the van der Waals' contribution (ΔG_vdW) in the AChE-(S)-isocarbophos complexes and induces the disparities in free energies during the enantioselective neurotoxic conjugations and thus elucidating that (S)-isocarbophos mediated by synaptic AChE has a strong toxic effect on SH-SY5Y neuronal cells. Clearly, this effort can provide experimental insights for evaluating the neurotoxicity risks of human exposure to chiral organophosphates from macroscopic to microscopic levels.

Uncovering water effects in protein-ligand recognition: importance in the second hydration shell and binding kinetics

Developing a ligand with high affinity for a specific protein target is essential for drug design, and water molecules are well known to play a key role in protein-drug recognition. However, predicting the role of particularly ordered water molecules in drug binding remains challenging. Furthermore, hydration free energy contributed from the water network, including the second shell of water molecules, is far from being well studied. In this research we focused on these aspects to accurately and efficiently evaluate water effects in protein-ligand binding affinity. We developed a new strategy using a free-energy calculation method, VM2. We successfully predicted the stable ordered water molecules in a number of protein systems: PDE 10a, HSP90, tryptophan synthase (TRPS), CDK2 and Factor Xa. In some of these, the second shell of water molecules appeared to be critical in protein-ligand binding. We also applied the strategy to largely improve binding free energy calculation using the MM/PBSA method. When applying MM/PBSA alone for two systems, CDK2 and Factor Xa, the computed binding free energy resulted in poor to moderate R² values with experimental data. However, including water free energy correction greatly improved the free energy calculation. Furthermore, our work helped to explain how xk263 is a 1000 times faster binder to HIVp than ritonavir, a potentially useful tool for investigating binding kinetics. Our studies reveal the importance of fully considering water effects in therapeutic developments in pharmaceutical and biotechnology industries and for fundamental research in protein-ligand recognition.

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.

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.