In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression.

The vast majority of marketed drugs are orally administrated. As such, drug absorption is one of the important drug metabolism and pharmacokinetics parameters that should be assessed in the process of drug discovery and development. A nonlinear quantitative structure-activity relationship (QSAR) model was constructed in this investigation using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to render the extremely complicated relationships between descriptors and intestinal permeability that can take place through various passive diffusion and carrier-mediated active transport routes. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (n = 53, r2 = 0.93, q CV 2 = 0.84, RMSE = 0.17, s = 0.08), test set (n = 13, q2 = 0.75-0.89, RMSE = 0.26, s = 0.14), and even outlier set (n = 8, q2 = 0.78-0.92, RMSE = 0.19, s = 0.09). The built HSVR model consistently met the most stringent criteria when subjected to various statistical assessments. A mock test also assured the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development.

In Silico Prediction of PAMPA Effective Permeability Using a Two-QSAR Approach.

Oral administration is the preferred and predominant route of choice for medication. As such, drug absorption is one of critical drug metabolism and pharmacokinetics (DM/PK) parameters that should be taken into consideration in the process of drug discovery and development. The cell-free in vitro parallel artificial membrane permeability assay (PAMPA) has been adopted as the primary screening to assess the passive diffusion of compounds in the practical applications. A classical quantitative structure-activity relationship (QSAR) model and a machine learning (ML)-based QSAR model were derived using the partial least square (PLS) scheme and hierarchical support vector regression (HSVR) scheme to elucidate the underlying passive diffusion mechanism and to predict the PAMPA effective permeability, respectively, in this study. It was observed that HSVR executed better than PLS as manifested by the predictions of the samples in the training set, test set, and outlier set as well as various statistical assessments. When applied to the mock test, which was designated to mimic real challenges, HSVR also showed better predictive performance. PLS, conversely, cannot cover some mechanistically interpretable relationships between descriptors and permeability. Accordingly, the synergy of predictive HSVR and interpretable PLS models can be greatly useful in facilitating drug discovery and development by predicting passive diffusion.

Insight Analysis of Promiscuous Estrogen Receptor α-Ligand Binding by a Novel Machine Learning Scheme.

Estrogen receptor α (ERα) plays a significant role in occurrence of breast cancer and may cause various adverse side-effects when ERα is an off-target protein. A theoretical model was derived to predict the binding affinity of ERα using the pharmacophore ensemble/support vector machine (PhE/SVM) scheme to consider the promiscuous characteristic of ERα. The estimations by PhE/SVM were discovered to be in good agreement with the observed values for those training molecules ( n = 31, r2 = 0.80, qCV2 = 0.77, RMSE = 0.57, s = 0.58), test molecules ( n = 179, q2 = 0.91-0.96, RMSE = 0.33, s = 0.26) and outliers ( n = 15, q2 = 0.80-0.86, RMSE = 0.56, s = 0.49). When subjected to various statistical validations, the PhE/SVM model consistently fulfilled the strictest criteria. A mock test also asserted its predictivity. When compared with crystal structures, the calculated results are consistent with the reported ERα-ligand co-complex structure, and the plasticity nature of ERα is also disclosed. Consequently, this precise, fast, and robust model can be adopted to predict ERα-ligand binding affinities and to design safer non-ERα-targeted pharmaceuticals in the process of drug discovery and development.

Theoretical Prediction of the Complex P-Glycoprotein Substrate Efflux Based on the Novel Hierarchical Support Vector Regression Scheme.

P-glycoprotein (P-gp), a membrane-bound transporter, can eliminate xenobiotics by transporting them out of the cells or blood⁻brain barrier (BBB) at the expense of ATP hydrolysis. Thus, P-gp mediated efflux plays a pivotal role in altering the absorption and disposition of a wide range of substrates. Nevertheless, the mechanism of P-gp substrate efflux is rather complex since it can take place through active transport and passive permeability in addition to multiple P-gp substrate binding sites. A nonlinear quantitative structure⁻activity relationship (QSAR) model was developed in this study using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to explore the perplexing relationships between descriptors and efflux ratio. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (n = 50, r² = 0.96, qCV2 = 0.94, RMSE = 0.10, s = 0.10) and test set (n = 13, q² = 0.80⁻0.87, RMSE = 0.21, s = 0.22). When subjected to a variety of statistical validations, the developed HSVR model consistently met the most stringent criteria. A mock test also asserted the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development.

Hypoglycemic Efficacy of Docking Selected Natural Compounds against α-Glucosidase and α-Amylase.

The inhibition of α-glucosidase and α-amylase is a clinical strategy for the treatment of type II diabetes, and herbal medicines have been reported to credibly alleviate hyperglycemia. Our previous study has reported some constituents from plant or herbal sources targeted to α-glucosidase and α-amylase via molecular docking and enzymatic measurement, but the hypoglycemic potencies in cell system and mice have not been validated yet. This study was aimed to elucidate the hypoglycemic efficacy of docking selected compounds in cell assay and oral glucose and starch tolerance tests of mice. All test compounds showed the inhibition of α-glucosidase activity in Caco-2 cells. The decrease of blood sugar levels of test compounds in 30 min and 60 min of mice after OGTT and OSTT, respectively and the decreased glucose levels of test compounds were significantly varied in acarbose. Taken altogether, in vitro and in vivo experiments suggest that selected natural compounds (curcumin, antroquinonol, HCD, docosanol, tetracosanol, rutin, and actinodaphnine) via molecular docking were confirmed as potential candidates of α-glucosidase and α-amylase inhibitors for treating diabetes.

Development of a hierarchical support vector regression-based in silico model for the prediction of the cysteine depletion in DPRA.

Topical and transdermal treatments have been dramatically growing recently and it is crucial to consider skin sensitization during the drug discovery and development process for these administration routes. Various tests, including animal and non-animal approaches, have been devised to assess the potential for skin sensitization. Furthermore, numerous in silico models have been created, providing swift and cost-effective alternatives to traditional methods such as in vivo, in vitro, and in chemico methods for categorizing compounds. In this study, a quantitative structure-activity relationship (QSAR) model was developed using the innovative hierarchical support vector regression (HSVR) scheme. The aim was to quantitatively predict the potential for skin sensitization by analyzing the percent of cysteine depletion in Direct Peptide Reactivity Assay (DPRA). The results demonstrated accurate, consistent, and robust predictions in the training set, test set, and outlier set. Consequently, this model can be employed to estimate skin sensitization potential of novel or virtual compounds.

In Silico Prediction of Skin Permeability Using a Two-QSAR Approach.

Topical and transdermal drug delivery is an effective, safe, and preferred route of drug administration. As such, skin permeability is one of the critical parameters that should be taken into consideration in the process of drug discovery and development. The ex vivo human skin model is considered as the best surrogate to evaluate in vivo skin permeability. This investigation adopted a novel two-QSAR scheme by collectively incorporating machine learning-based hierarchical support vector regression (HSVR) and classical partial least square (PLS) to predict the skin permeability coefficient and to uncover the intrinsic permeation mechanism, respectively, based on ex vivo excised human skin permeability data compiled from the literature. The derived HSVR model functioned better than PLS as represented by the predictive performance in the training set, test set, and outlier set in addition to various statistical estimations. HSVR also delivered consistent performance upon the application of a mock test, which purposely mimicked the real challenges. PLS, contrarily, uncovered the interpretable relevance between selected descriptors and skin permeability. Thus, the synergy between interpretable PLS and predictive HSVR models can be of great use for facilitating drug discovery and development by predicting skin permeability.

Predicting activation of the promiscuous human pregnane X receptor by pharmacophore ensemble/support vector machine approach.

The nuclear receptor human pregnane X receptor (hPXR) is a ligand-regulated transcription factor that responds to a wide range of endogenous and xenobiotic molecules. Upon activation with ligands, hPXR can increase induction levels of metabolic enzymes. Therefore, hPXR plays a critical role in drug metabolism and excretion. Identifying the molecules that activate this protein can be of great help to predict adverse drug interaction, which, nevertheless, cannot be accurately modeled without taking into account its promiscuous nature, namely, highly flexible protein conformation and multiple ligand orientations. An in silico model was developed to predict the activation of hPXR using the novel pharmacophore ensemble/support vector machine (PhE/SVM) scheme. The predictions by the PhE/SVM model are in good agreement with the experimental observations for those molecules in the training set (n = 32, r(2) = 0.86, q(2) = 0.80, RMSE = 0.37, s = 0.21) and test set (n = 120, r(2) = 0.80, RMSE = 0.25, s = 0.19). In addition, this PhE/SVM model performed equally well for those molecules in the outlier set (n = 8, r(2) = 0.91, RMSE = 0.15, s = 0.12) and completely met with those validation criteria generally adopted to gauge the predictivity of a theoretical model. A mock test also verified its predictivity. When compared with crystal structures, the calculated results are consistent with the published hPXR-ligand cocomplex structure and the plasticity nature of hPXR is also revealed. Thus, this accurate, fast, and robust PhE/SVM model can be utilized for predicting the activation of promiscuous hPXR to facilitate drug discovery and development.

In silico Prediction of Skin Sensitization: Quo vadis?

Skin direct contact with chemical or physical substances is predisposed to allergic contact dermatitis (ACD), producing various allergic reactions, namely rash, blister, or itchy, in the contacted skin area. ACD can be triggered by various extremely complicated adverse outcome pathways (AOPs) remains to be causal for biosafety warrant. As such, commercial products such as ointments or cosmetics can fulfill the topically safe requirements in animal and non-animal models including allergy. Europe, nevertheless, has banned animal tests for the safety evaluations of cosmetic ingredients since 2013, followed by other countries. A variety of non-animal in vitro tests addressing different key events of the AOP, the direct peptide reactivity assay (DPRA), KeratinoSens™, LuSens and human cell line activation test h-CLAT and U-SENS™ have been developed and were adopted in OECD test guideline to identify the skin sensitizers. Other methods, such as the SENS-IS are not yet fully validated and regulatorily accepted. A broad spectrum of in silico models, alternatively, to predict skin sensitization have emerged based on various animal and non-animal data using assorted modeling schemes. In this article, we extensively summarize a number of skin sensitization predictive models that can be used in the biopharmaceutics and cosmeceuticals industries as well as their future perspectives, and the underlined challenges are also discussed.

In Silico Approaches to Identify Polyphenol Compounds as α-Glucosidase and α-Amylase Inhibitors against Type-II Diabetes.

Type-II diabetes mellitus (T2DM) results from a combination of genetic and lifestyle factors, and the prevalence of T2DM is increasing worldwide. Clinically, both α-glucosidase and α-amylase enzymes inhibitors can suppress peaks of postprandial glucose with surplus adverse effects, leading to efforts devoted to urgently seeking new anti-diabetes drugs from natural sources for delayed starch digestion. This review attempts to explore 10 families e.g., Bignoniaceae, Ericaceae, Dryopteridaceae, Campanulaceae, Geraniaceae, Euphorbiaceae, Rubiaceae, Acanthaceae, Rutaceae, and Moraceae as medicinal plants, and folk and herb medicines for lowering blood glucose level, or alternative anti-diabetic natural products. Many natural products have been studied in silico, in vitro, and in vivo assays to restrain hyperglycemia. In addition, natural products, and particularly polyphenols, possess diverse structures for exploring them as inhibitors of α-glucosidase and α-amylase. Interestingly, an in silico discovery approach using natural compounds via virtual screening could directly target α-glucosidase and α-amylase enzymes through Monte Carto molecular modeling. Autodock, MOE-Dock, Biovia Discovery Studio, PyMOL, and Accelrys have been used to discover new candidates as inhibitors or activators. While docking score, binding energy (Kcal/mol), the number of hydrogen bonds, or interactions with critical amino acid residues have been taken into concerning the reliability of software for validation of enzymatic analysis, in vitro cell assay and in vivo animal tests are required to obtain leads, hits, and candidates in drug discovery and development.

Development of a Hierarchical Support Vector Regression-Based In Silico Model for Caco-2 Permeability.

Drug absorption is one of the critical factors that should be taken into account in the process of drug discovery and development. The human colon carcinoma cell layer (Caco-2) model has been frequently used as a surrogate to preliminarily investigate the intestinal absorption. In this study, a quantitative structure-activity relationship (QSAR) model was generated using the innovative machine learning-based hierarchical support vector regression (HSVR) scheme to depict the exceedingly confounding passive diffusion and transporter-mediated active transport. The HSVR model displayed good agreement with the experimental values of the training samples, test samples, and outlier samples. The predictivity of HSVR was further validated by a mock test and verified by various stringent statistical criteria. Consequently, this HSVR model can be employed to forecast the Caco-2 permeability to assist drug discovery and development.

Mangosteen xanthone γ-mangostin exerts lowering blood glucose effect with potentiating insulin sensitivity through the mediation of AMPK/PPARγ.

Diabetes mellitus (DM) is concomitant with significant morbidity and mortality and its prevalence is accumulative in worldwide. The conventional antidiabetic agents are known to mitigate the symptoms of diabetes; however, they may also cause side and adverse effects. There is an imperative necessity to conduct preclinical and clinical trials for the discovery of alternative therapeutic agents that can overcome the drawbacks of current synthetic antidiabetic drugs. This study aimed to investigate the efficacy of lowering blood glucose and underlined mechanism of γ-mangostin, mangosteen (Garcinia mangostana) xanthones. The results showed γ-Mangostin had a antihyperglycemic ability in short (2 h)- and long-term (28 days) administrations to diet-induced diabetic mice. The long-term administration of γ-mangostin attenuated fasting blood glucose of diabetic mice and exhibited no hepatotoxicity and nephrotoxicity. Moreover, AMPK, PPARγ, α-amylase, and α-glucosidase were found to be the potential targets for simulating binds with γ-mangostin after molecular docking. To validate the docking results, the inhibitory potency of γ-mangostin againstα-amylase/α-glucosidase was higher than Acarbose via enzymatic assay. Interestingly, an allosteric relationship between γ-mangostin and insulin was also found in the glucose uptake of VSMC, FL83B, C2C12, and 3T3-L1 cells. Taken together, the results showed that γ-mangostin exerts anti-hyperglycemic activity through promoting glucose uptake and reducing saccharide digestion by inhibition of α-amylase/α-glucosidase with insulin sensitization, suggesting that γ-mangostin could be a new clue for drug discovery and development to treat diabetes.

Natural compounds as potential adjuvants to cancer therapy: Preclinical evidence.

Traditional chemotherapy is being considered due to hindrances caused by systemic toxicity. Currently, the administration of multiple chemotherapeutic drugs with different biochemical/molecular targets, known as combination chemotherapy, has attained numerous benefits like efficacy enhancement and amelioration of adverse effects that has been broadly applied to various cancer types. Additionally, seeking natural-based alternatives with less toxicity has become more important. Experimental evidence suggests that herbal extracts such as Solanum nigrum and Claviceps purpurea and isolated herbal compounds (e.g., curcumin, resveratrol, and matairesinol) combined with antitumoral drugs have the potential to attenuate resistance against cancer therapy and to exert chemoprotective actions. Plant products are not free of risks: Herb adverse effects, including herb-drug interactions, should be carefully considered. LINKED ARTICLES: This article is part of a themed section on The Pharmacology of Nutraceuticals. To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v177.6/issuetoc.

Prediction of human cytochrome P450 2B6-substrate interactions using hierarchical support vector regression approach.

The human cytochrome P450 2B6 can metabolize a number of clinical drugs. Inhibition of CYP2B6 by coadministered multiple drugs may lead to drug-drug interactions and undesired drug toxicity. The aim of this investigation is to develop an in silico model to predict the interactions between P450 2B6 and novel inhibitors using a novel hierarchical support vector regression (HSVR) approach, which simultaneously takes into account the coverage of applicability domain (AD) and the level of predictivity. Thirty-seven molecules were deliberately selected and rigorously scrutinized from the literature data, of which 26 and 11 molecules were treated as the training set and the test set to generate the models and to validate the generated models, respectively. The generated HSVR model gave rise to an r2 value of 0.97 for observed versus predicted pK(m) values for the training set, a q2 value of 0.93 by the 10-fold cross-validation, and an r2 value of 0.82 for the test set. Additionally, the predicted results show that the HSVR model outperformed the individual local models, the global model, and the consensus model. Thus, this HSVR model provides an accurate tool for the prediction of human cytochrome P450 2B6-substrate interactions and can be utilized as a primary filter to eliminate the potential selective inhibitor of CYP2B6.

The perceptions of natural compounds against dipeptidyl peptidase 4 in diabetes: from in silico to in vivo.

Dipeptidyl peptidase IV (DPP-4), an incretin glucagon-like peptide-1 (GLP-1) degrading enzyme, contains two forms and it can exert various physiological functions particular in controlling blood glucose through the action of GLP-1. In diabetic use, the DPP-4 inhibitor can block the DDP-4 to attenuate GLP-1 degradation and prolong GLP-1 its action and sensitize insulin activity for the purpose of lowering blood glucose. Nonetheless the adverse effects of DPP-4 inhibitors severely hinder their clinical applications, and notably there is a clinical demand for novel DPP-4 inhibitors from various sources including chemical synthesis, herbs, and plants with fewer side effects. In this review, we highlight various strategies, namely computational biology (in silico), in vitro enzymatic and cell assays, and in vivo animal tests, for seeking natural DPP-4 inhibitors from botanic sources including herbs and plants. The pros and cons of all approaches for new inhibitor candidates or hits will be under discussion.

Prediction of cytochrome P450 2B6-substrate interactions using pharmacophore ensemble/support vector machine (PhE/SVM) approach.

An in silico model for predicting human cytochrome P450 2B6-substrate interactions was generated based on a novel scheme, which was initially devised to predict the hERG liability (reported in Leong, M. K., Chem. Res. Toxicol., 2007, 20, 217.) using pharmacophore ensemble/support vector machine to take into account the protein conformational flexibility while interacting with structurally diverse substrates. This is of critical importance yet never being addressed by any analogue-based molecular modeling studies before. Thirty-seven molecules were chosen from the literature and scrutinized for structural integrity and data consistency, of which 26 were treated as the training set to generate models, which were subject to validation by the other 11 molecules as the test set. The predicted pK(m) values by the final PhE/SVM model were in good agreement with observed values. In addition, this in silico model produced an r(2) of 0.84 and a 10-fold cross-validation q(2) of 0.66 for the training set and an r(2) of 0.87 for the test set, asserting the fact that this PhE/SVM model is an accurate model to predict the human P450 2B6-substrates interactions and can be used as a robust prediction tool to facilitate drug discovery.

Potential natural mTOR inhibitors screened by in silico approach and suppress hepatic stellate cells activation.

The mammalian target of rapamycin (mTOR), an atypical serine/threonine kinase, plays a central role in the regulation of cell proliferation, growth, differentiation, migration, and survival. In this study, the 3-D structure of the mTOR (PDB ID: 2FAP) was used for the docking of 47 natural compounds and compared with pharmacophore model of 14 known mTOR inhibitors to identify the novel and specific natural inhibitor. The top four compounds, rutin, curcumin, antroquinonol, and benzyl cinnamate, have been selected based on their PLP score and further validated with hepatic stellate cells NHSC and THSC. Curcumin and antroquinonol significantly inhibited NHSC and THSC cells proliferation in a dose-dependent manner, whereas rutin and benzyl cinnamate showed less alteration of cell viability. Rutin inhibited the phosphorylation of mTOR (p-mTOR) and p-p70 S6 K in NHSC and THSC cells by Western blotting. Additionally, p-p70 S6 K protein was significantly decreased by incubation with benzyl cinnamate and curcumin in THSC cells. Taken together, this result suggests that rutin is a potential mTOR inhibitor in screen hits of molecular docking to hamper the activation of HSC and further applications in the treatment of liver fibrosis.

Prodigiosin-Emerged PI3K/Beclin-1-Independent Pathway Elicits Autophagic Cell Death in Doxorubicin-Sensitive and -Resistant Lung Cancer.

Prodigiosin (PG) belongs to a family of prodiginines isolated from gram-negative bacteria. It is a water insoluble red pigment and a potent proapoptotic compound. This study elucidates the anti-tumor activity and underlying mechanism of PG in doxorubicin-sensitive (Dox-S) and doxorubicin-resistant (Dox-R) lung cancer cells. The cytotoxicity and cell death characteristics of PG in two cells were measured by MTT assay, cell cycle analysis, and apoptosis/autophagic marker analysis. Then, the potential mechanism of PG-induced cell death was evaluated through the phosphatidylinositol-4,5-bisphosphate 3-kinase-p85/Protein kinase B /mammalian target of rapamycin (PI3K-p85/Akt/mTOR) and Beclin-1/phosphatidylinositol-4,5-bisphosphate 3-kinase-Class III (Beclin-1/PI3K-Class III) signaling. Finally, in vivo efficacy was examined by intratracheal inoculation and treatment. There was similar cytotoxicity with PG in both Dox-S and Dox-R cells, where the half maximal inhibitory concentrations (IC50) were all in 10 µM. Based on a non-significant increase in the sub-G1 phase with an increase of microtubule-associated proteins 1A/1B light chain 3B-phosphatidylethanolamine conjugate (LC3-II), the cell death of both cells was categorized to achieve autophagy. Interestingly, an increase in cleaved-poly ADP ribose polymerase (cleaved-PARP) also showed the existence of an apoptosis-sensitive subpopulation. In both Dox-S and Dox-R cells, PI3K-p85/Akt/mTOR signaling pathways were reduced, which inhibited autophagy initiation. However, Beclin-1/PI3K-Class III downregulation implicated non-canonical autophagy pathways were involved in PG-induced autophagy. At completion of the PG regimen, tumors accumulated in the mice trachea and were attenuated by PG treatment, which indicated the efficacy of PG for both Dox-S and Dox-R lung cancer. All the above results concluded that PG is a potential chemotherapeutic agent for lung cancer regimens regardless of doxorubicin resistance.

In silico prediction of the mutagenicity of nitroaromatic compounds using a novel two-QSAR approach.

Certain drugs are nitroaromatic compounds, which are potentially toxic. As such, it is of practical importance to assess and predict their mutagenic potency in the process of drug discovery. A classical quantitative structure-activity relationship (QSAR) model was developed using the linear partial least square (PLS) scheme to understand the underline mutagenic mechanism and a non-classical QSAR model was derived using the machine learning-based hierarchical support vector regression (HSVR) to predict the mutagenicity of nitroaromatic compounds based on a series of mutagenicity data (TA98-S9). It was observed that HSVR performed better than PLS as manifested by the predictions of the samples in the training set, test set, and outlier set as well as various statistical validations. A mock test designated to mimic real challenges also confirmed the better performance of HSVR. Furthermore, HSVR exhibited superiority in predictivity, generalization capabilities, consistent performance, and robustness when compared with various published predictive models. PLS, conversely, revealed some mechanistically interpretable relationships between descriptors and mutagenicity. Thus, this two-QSAR approach using the predictive HSVR and interpretable PLS models in a synergistic fashion can be adopted to facilitate drug discovery and development by designing safer drug candidates with nitroaromatic moiety.

Prediction of N-Methyl-D-Aspartate Receptor GluN1-Ligand Binding Affinity by a Novel SVM-Pose/SVM-Score Combinatorial Ensemble Docking Scheme.

The glycine-binding site of the N-methyl-D-aspartate receptor (NMDAR) subunit GluN1 is a potential pharmacological target for neurodegenerative disorders. A novel combinatorial ensemble docking scheme using ligand and protein conformation ensembles and customized support vector machine (SVM)-based models to select the docked pose and to predict the docking score was generated for predicting the NMDAR GluN1-ligand binding affinity. The predicted root mean square deviation (RMSD) values in pose by SVM-Pose models were found to be in good agreement with the observed values (n = 30, r2 = 0.928-0.988, = 0.894-0.954, RMSE = 0.002-0.412, s = 0.001-0.214), and the predicted pKi values by SVM-Score were found to be in good agreement with the observed values for the training samples (n = 24, r2 = 0.967, = 0.899, RMSE = 0.295, s = 0.170) and test samples (n = 13, q2 = 0.894, RMSE = 0.437, s = 0.202). When subjected to various statistical validations, the developed SVM-Pose and SVM-Score models consistently met the most stringent criteria. A mock test asserted the predictivity of this novel docking scheme. Collectively, this accurate novel combinatorial ensemble docking scheme can be used to predict the NMDAR GluN1-ligand binding affinity for facilitating drug discovery.