3D Quantitative Structure-activity Relationship Models Research Articles

Identification of Non-Nucleoside Inhibitors of the Respiratory Syncytial Virus Polymerase Complex.

Respiratory syncytial virus (RSV) represents a threat to infants, the elderly, and the immunocompromised. RSV entry blockers are in clinical trials, but escape mutations challenge their potential. In search of RSV inhibitors, we have integrated a signature resistance mutation into a recombinant RSV virus and applied the strain to high-throughput screening. Counterscreening of candidates returned 14 confirmed hits with activities in the nano- to low-micromolar range. All blocked RSV polymerase activity in minigenome assays. Compound 1a (GRP-74915) was selected for development based on activity (EC50 = 0.21 μM, selectivity index (SI) 40) and scaffold. Resynthesis confirmed the potency of the compound, which suppressed viral RNA synthesis in infected cells. However, metabolic testing revealed a short half-life in the presence of mouse hepatocyte fractions. Metabolite tracking and chemical elaboration combined with 3D-quantitative structure-activity relationship modeling yielded analogues (i.e., 8n: EC50 = 0.06 μM, SI 500) that establish a platform for the development of a therapeutic candidate.

Pharmacophore-based screening and drug repurposing exemplified on glycogen synthase kinase-3 inhibitors.

The current study was conducted to elaborate a novel pharmacophore model to accurately map selective glycogen synthase kinase-3 (GSK-3) inhibitors, and perform virtual screening and drug repurposing. Pharmacophore modeling was developed using PHASE on a data set of 203 maleimides. Two benchmarking validation data sets with focus on selectivity were assembled using ChEMBL and PubChem GSK-3 confirmatory assays. A drug repurposing experiment linking pharmacophore matching with drug information originating from multiple data sources was performed. A five-point pharmacophore model was built consisting of a hydrogen bond acceptor (A), hydrogen bond donor (D), hydrophobic (H), and two rings (RR). An atom-based 3D quantitative structure-activity relationship (QSAR) model showed good correlative and satisfactory predictive abilities (training set [Formula: see text]; test set: [Formula: see text]; whole data set: stability [Formula: see text]). Virtual screening experiments revealed that selective GSK-3 inhibitors are ranked preferentially by Hypo-1, but fail to retrieve nonselective compounds. The pharmacophore and 3D QSAR models can provide assistance to design novel, potential GSK-3 inhibitors with high potency and selectivity pattern, with potential application for the treatment of GSK-3-driven diseases. A class of purine nucleoside antileukemic drugs was identified as potential inhibitor of GSK-3, suggesting the reassessment of the target range of these drugs.

3D-QSAR studija i razvoj farmakofore agonista serotoninskih 5-HT2A receptora

All tested compounds show agonistic activity onserotonin5-HT2areceptors, which activation causes neuronal excitations, behavioral changes and platelet aggregation. The main aims of this study were to create 3D-QSAR(3D-Quantitative structure-activity relationship)model, analyse 3D-structure of the pharmacophore, validate the 3D-QSARmodel, and propose structural modification for novel 5-HT2aagonists.3D-QSAR modeling was applied to 51 agonists of 5-HT2areceptors. Dominant forms at physiologic pHof the examined compounds were optimized using the PM3 method and used for QSAR modeling. Data set was divided in two groups, training set of38 compounds, and test set of 13 compounds. Training set was used to build 3D-QSAR model, while test set was examined for the model validation. PLS (Partial Least Square Regression)method was used to develop 3D-QSAR model. Statistical parameters of the created and validated 3D-QSAR model,R2= 0.93, Q2=0.72, RMSEE=0.178, RMSEP=0.190 and R2 pred=0.63, indicate good prognostic capacity of the model.The3D-QSAR model was applied to analyse pharmacophore and to predict activity of other agonists of serotonin 5-HT2areceptors. Information obtained from the 3D-QSAR study indicated that presence of hydrogen bond donor and steric hot spot at a distance 14.80-15.20Å (v477:O-TIP), hydrophobic region and hydrogen bond donor at a distance of 2.40-2.86Å (v226:DRY-O), hydrogen bond donor and hydrogen bond acceptor at a distance of 1.60-2.00Å (v389:O-N1) and two hydrophobic regions at a distance 9.20-9.60Å (v23:DRY-DRY) are essential for agonistic activity on 5-HT2aserotonin receptors.

QSAR-Driven Discovery of Novel Chemical Scaffolds Active against Schistosoma mansoni.

Schistosomiasis is a neglected tropical disease that affects millions of people worldwide. Thioredoxin glutathione reductase of Schistosoma mansoni (SmTGR) is a validated drug target that plays a crucial role in the redox homeostasis of the parasite. We report the discovery of new chemical scaffolds against S. mansoni using a combi-QSAR approach followed by virtual screening of a commercial database and confirmation of top ranking compounds by in vitro experimental evaluation with automated imaging of schistosomula and adult worms. We constructed 2D and 3D quantitative structure-activity relationship (QSAR) models using a series of oxadiazoles-2-oxides reported in the literature as SmTGR inhibitors and combined the best models in a consensus QSAR model. This model was used for a virtual screening of Hit2Lead set of ChemBridge database and allowed the identification of ten new potential SmTGR inhibitors. Further experimental testing on both shistosomula and adult worms showed that 4-nitro-3,5-bis(1-nitro-1H-pyrazol-4-yl)-1H-pyrazole (LabMol-17) and 3-nitro-4-{[(4-nitro-1,2,5-oxadiazol-3-yl)oxy]methyl}-1,2,5-oxadiazole (LabMol-19), two compounds representing new chemical scaffolds, have high activity in both systems. These compounds will be the subjects for additional testing and, if necessary, modification to serve as new schistosomicidal agents.

Prediction of stability for polychlorinated biphenyls in transformer insulation oil through three-dimensional quantitative structure-activity relationship pharmacophore model and full factor experimental design

Based on the obtained data of half-lives(t1/2) for 31 polychlorinated biphenyl congeners(PCBs), 3D quantitative structure-activity relationship(QSAR) pharmacophore was used to establish a 3D QSAR model to predict the t1/2 values of the remaining 178 PCBs, using the structural parameters as independent variables and lgt1/2 values as the dependent variable. Among this process, the whole data set(31 compounds) was divided into a training set(24 compounds) for model generation and a test set(7 compounds) for model validation. Then, the full factor experimental design was used to research the potential second-order interactional effect between different substituent positions, obtaining the final regulation scheme for PCB. At last, a 3D QSAR pharmacophore model was established to validate the reasonable regulation targeting typical PCB with respect to half-lives and thermostability. As a result, the cross-validation correlation coefficient(q2) obtained by the 3D QSAR model was 0.845(>0.5) and the coefficient of determination(r2) obtained was 0.936(>0.9), indicating that the models were robust and predictive. CoMSIA analyses upon steric, electrostatic and hydrophobic fields were 0.7%, 85.9%, and 13.4%, respectively. The electrostatic field was determined to be a primary factor governing the t1/2. From CoMSIA contour maps, t1/2 increased when substituents possessed electropositive groups at the 2′-, 3-, 3′-, 5- and 5′- positions and electronegative groups at the 3-, 3′-, 5-, 6- and 6′- positions, which could increase the PCB stability in transformer insulation oil. Modification of two typical PCB congeners(PCB-77 and PCB-81) showed that the lgt1/2for three selected modified compounds increased by 13%(average ratio) compared with that of each congener and the thermostability of them were higher, validating the reasonability of the regulatory scheme obtained from the 3D QSAR model. These results are expected to be beneficial in predicting t1/2 values of PCB homologues and derivatives and in providing a theoretical foundation for further elucidation of the stability of PCBs.

3D-QSAR and SVM Prediction of BRAF-V600E and HIV Integrase Inhibitors: A Comparative Study and Characterization of Performance with a New Expected Prediction Performance Metric

The results of directly comparing the prediction accuracy of optimized 3D Quantitative Structure-Activity Relationship (3D-QSAR) models and linear Support Vector Machine (SVM) classifiers to identify small molecule inhibitors of the BRAF-V600E and HIV Integrase targets are reported. Performance comparisons were carried out using 303 compounds (68 active) against BRAF-V600E and 204 compounds (159 active) against HIV Integrase. A SVM prediction accuracy of 95% (BRAF-V600E) and 100% (HIV Integrase) and 3D-QSAR prediction accuracy of 76% (BRAFV600E) and 82% (HIV Integrase) was observed. To help explain the better performance of SVM in the comparison reported here and to help assess the degree to which a SVM or 3D-QSAR model is likely to perform best for other targetligands of interest a new EPP (Expected Predictive Performance) metric is introduced. How EPP can be used to help predict future performance of SVM and 3D-QSAR models by quantifying the degree of similarity between candidate compounds and training data is also demonstrated. Results show that the EPP metric is capable of predicting future prediction accuracy of SVM and 3D-QSAr models within 7% of actual performance.

PQSAR: The membrane quantitative structure-activity relationships in cheminformatics

The applications of quantitative structure activity relationships (QSAR) are used to establish a correlation between structure and biological response. Similarity searching is one of QSAR major phases. Innovating new strategies for similarity searching is an urgent task in cheminformatics research for three reasons: (i) the increasing size of chemical search space of compound databases; (ii) the importance of similarity measurements to (2D) and (3D) QSAR models; and (iii) similarity searching is a time consuming process in drug discovery. In this study, we introduce theoretical similarity searching strategy based on membrane computing. It solves time consumption problem. We adopt a ranking sorting algorithm with P System to rank probabilities of similarity according to a predefined similarity threshold. That bio-inspired model, simulating biological living cell, presents a high performance parallel processing system, we called it PQSAR. It relies on a set of rules to apply ranking algorithm on probabilities of similarity. The simulated experiments show how the effectiveness of PQSAR method enhanced the performance of similarity searching significantly; and introduced a standard ranking algorithm for similarity searching.

In silico prediction of hERG inhibition.

The voltage-gated potassium channel encoded by hERG carries a delayed rectifying potassium current (IKr) underlying repolarization of the cardiac action potential. Pharmacological blockade of the hERG channel results in slowed repolarization and therefore prolongation of action potential duration and an increase in the QT interval as measured on an electrocardiogram. Those are possible to cause sudden death, leading to the withdrawals of many drugs, which is the reason for hERG screening. Computational in silico prediction models provide a rapid, economic way to screen compounds during early drug discovery. In this review, hERG prediction models are classified as 2D and 3D quantitative structure-activity relationship models, pharmacophore models, classification models, and structure based models (using homology models of hERG).

Structure-odor correlations in homologous series of alkanethiols and attempts to predict odor thresholds by 3D-QSAR studies.

Homologous series of alkane-1-thiols, alkane-2-thiols, alkane-3-thiols, 2-methylalkane-1-thiols, 2-methylalkane-3-thiols, 2-methylalkane-2-thiols, and alkane-1,ω-dithiols were synthesized to study the influence of structural changes on odor qualities and odor thresholds. In particular, the odor thresholds were strongly influenced by steric effects: In all homologous series a minimum was observed for thiols with five to seven carbon atoms, whereas increasing the chain length led to an exponential increase in the odor threshold. Tertiary alkanethiols revealed clearly lower odor thresholds than found for primary or secondary thiols, whereas neither a second mercapto group in the molecule nor an additional methyl substitution lowered the threshold. To investigate the impact of the SH group, odor thresholds and odor qualities of thiols were compared to those of the corresponding alcohols and (methylthio)alkanes. Replacement of the SH group by an OH group as well as S-methylation of the thiols significantly increased the odor thresholds. By using comparative molecular field analysis, a 3D quantitative structure-activity relationship model was created, which was able to simulate the odor thresholds of alkanethiols in good agreement with the experimental results. NMR and mass spectrometric data for 46 sulfur-containing compounds are additionally supplied.

Identification of new non-steroidal TGR5 agonists using virtual screening with combined pharmacophore models

Activation of Takeda G-protein receptor 5 (TGR5) plays a key role in pathways associated with diabetes, metabolic syndrome, and autoimmune disease. Pharmacophore and 3D-quantitative structure–activity relationship modeling were applied to study the structure–activity relationship of TGR5 agonists. The best HypoGen pharmacophore hypothesis Hypo1 with a correlation coefficient of 0.93 consists of one hydrogen-bond acceptor, one aromatic ring and three hydrophobic features, whereas the best phase hypothesis AHHRR.1321 with favorable statistics (q2 = 0.7613, r2 = 0.927) has one hydrogen-bond acceptor, two hydrophobic features and two ring aromatic features. Furthermore, comparing those two models, the preferable AHHRR.1321 was employed as a novel searching tool for chemical databases to conduct virtual screening for new potential lead candidates. Consequently, refined Lipinski ‘rule of five’ and ADME properties were utilized as a filter to reduce less drug-like molecules. Among the hits, 10 non-steroidal compounds with good fitness score and physicochemical properties were identified.

Integrated pharmacophore and docking‐based designing of dual inhibitors of aldose reductase (ALR2) and protein tyrosine phosphatase 1B (PTP1B) as novel therapeutics for insulin‐resistant diabetes and its complications

The dual inhibitors against aldose reductase (ALR2) and protein tyrosine phosphatase 1B (PTP1B) may present an anti‐diabetic potency in insulin resistance without risks of serious diabetic complications. Therefore, in the present study, we constructed two separate pharmacophore mapping‐based 3D quantitative structure–activity relationship models for ALR2 (AADRR.11093 with standard deviation 0.663, 0.719, F 22.3, root‐mean‐square error 0.705, 0.647, Pearson‐r 0.802) and PTP1B (AARR.155 with standard deviation 0.146, 0.945, F 82.70, root‐mean‐square error 0.351, 0.621, Pearson‐r 0.831) employing the dataset of 54 flavonoids as ALR2 inhibitors and 46 naphthoquinones as PTP1B inhibitors to identify structural features necessary for the inhibition of both enzymes. These models were subsequently used as 3D query search for hierarchical virtual screening‐based designing using the PHASE database of 1.5 million compounds. Designed dual inhibitors were further subjected to GLIDE XP docking analysis using high‐resolution 3D structures of ALR2 (1US0, at resolution of 0.66 Å) and PTP1B (2F71 at resolution of 1.55 Å) available in the Protein Data Bank to authenticate identified structural features with important binding interactions necessary for dual inhibition. Copyright © 2014 John Wiley & Sons, Ltd.

In vitro antiviral effects and 3D QSAR study of resveratrol derivatives as potent inhibitors of influenza H1N1 neuraminidase.

The anti-influenza virus activities of 50 resveratrol (RV: 3, 5, 4'-trihydroxy-trans-stilbene) derivatives were evaluated using a neuraminidase (NA) activity assay. The results showed that 35 compounds exerted an inhibitory effect on the NA activity of the influenza virus strain A/PR/8/34 (H1N1) with 50% inhibitory concentration (IC50) values ranging from 3.56 to 186.1 μm. Next, the 35 RV derivatives were used to develop 3D quantitative structure-activity relationship (3D QSAR) models for understanding the chemical-biological interactions governing their activities against NA. The comparative molecular field analysis (CoMFA r2=0.973, q2=0.620, qtest2=0.661) and the comparative molecular similarity indices analysis (CoMSIA r2=0.956, q2=0.610, qtest2=0.531) were applied. Afterward, molecular docking was performed to study the molecular interactions between the RV derivatives and NA. Finally, a cytopathic effect (CPE) reduction assay was used to evaluate the antiviral effects of the RV derivatives in vitro. Time-of-addition studies demonstrated that the RV derivatives might have a direct effect on viral particle infectivity. Our results indicate that the RV derivatives are potentially useful antiviral compounds for new drug design and development for influenza treatment.

Computational analysis of quinoline derivatives as potent topoisomerase-II inhibitors

Quantitative structure–activity relationship (QSAR) is an attempt to correlate structural or property descriptors of compounds quantitatively with biological activities. QSARs currently are being applied in many disciplines, with many pertaining to drug design and environmental risk assessment. The 3D QSARs between the structures of 29 quinoline compounds and their topoisomerase-II inhibitor activity have been developed using the comparative molecular field analysis (CoMFA), comparative molecular similarity indices analysis (CoMSIA), and stepwise k nearest neighbor molecular field analysis [(SW) kNN MFA] method, and 3D QSAR models with the considerable prediction ability are obtained. The CoMFA, CoMSIA, and [(SW) kNN MFA] studies resulted in reliable and significant computational models. These models are more significant guide to trace the important chemical features with respect to the design of new potent compounds. The information obtained from the CoMFA, CoMSIA, and [(SW) kNN MFA] contour maps can be utilized for the design and development of new, more potent topoisomerase-II inhibitor.

Editorial (Thematic Issue: Current Status and Perspective on Drug Targets in Tubercle Bacilli and Drug Design of Antituberculous Agents Based on Structure-Activity Relationship)

Editorial (Thematic Issue: Current Status and Perspective on Drug Targets in Tubercle Bacilli and Drug Design of Antituberculous Agents Based on Structure-Activity Relationship)

3D QSAR Studies on Substituted Benzimidazole Derivatives as Angiotensin II-AT<sub>1</sub> Receptor Antagonist

This study investigated 3D quantitative structure-activity relationships (QSAR) for a range of substituted benzimidazole derivatives as AngII-AT1 receptor antagonists by comparative molecular field analysis (CoMFA) and comparative molecular similarity indices (CoMSIA). The alignment strategy was used for these compounds by means of Distill function defined in SYBYL X 1.2. The best CoMFA and CoMSIA models were obtained for the training set compounds was statistically significant with leave-one-out (LOO) validation correlation coefficient (q²) of 0.613 and 0.622, cross validated coefficient (r²cv) of 0.617 and 0.607, respectively and conventional coefficient (r²ncv) of 0.886 and 0.859, respectively. Both the models were validated by a test set of 18 compounds giving satisfactory predicted correlation coefficient (r²pred) of 0.714 and 0.549 for CoMFA and CoMSIA models, respectively. Generated 3D QSAR models were used for the prediction of pIC50 of an external dataset of 10 compounds for predictive validation, which gave conventional r² of 0.893 for CoMFA model, and 0.774 for CoMSIA model. We identified some key features in substituted benzimidazole derivatives, such as the importance of lipophilicity and H-bonding at 2- and 5, 6, 7- position of benzimidazole ring, respectively, for good antagonistic activity. CoMFA and CoMSIA models generated in this work provide useful information for the design of new compounds and helped in prediction of antagonistic activity.

Development of docking-based 3D QSAR models for the design of substituted quinoline derivatives as human dihydroorotate dehydrogenase (hDHODH) inhibitors

This study has investigated docking-based 3D quantitative structure–activity relationships (QSARs) for a range of quinoline carboxylic acid derivatives by comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA). A docking study has shown that most of the compounds formed H-bonds with Arg136 and Gln47, which have already been shown to be essential for the binding of ligands at the active site of the hydroorotate dehydrogenase adenovirus (hDHODH). Bioactive conformations of all the molecules obtained from the docking study were used for the 3D QSAR study. The best CoMFA and CoMSIA models were obtained for the training set and were found to be statistically significant, with cross-validated coefficients (q2 ) of 0.672 and 0.613, r2 cv of 0.635 and 0.598 and coefficients of determination (r2 ) of 0.963 and 0.896, respectively. Both models were validated by a test set of 15 compounds, giving satisfactory predicted correlation coefficients (r2 pred) of 0.824 and 0.793 for the CoMFA and CoMSIA models, respectively. From the docking-based 3D QSAR study we designed 34 novel quinoline-based compounds and performed structure-based virtual screening. Finally, in silico pharmacokinetics and toxicities were predicted for 24 of the best docked molecules. The study provides valuable information for the understanding of interactions between hDHODH and the novel compounds.

Pharmacophore modeling and 3D quantitative structure-activity relationship analysis of febrifugine analogues as potent antimalarial agent

Febrifugine and its derivatives are effective against Plasmodium falciparum. Using PHASE algorithm, a five-point pharmacophore model with two hydrogen bond acceptor (A), one positively ionizable (P) and two aromatic rings (R), was developed to derive a predictive ligand-based statistically significant 3D-quantitative structure-activity relationship (QSAR) model (r2 = 0.972, SD = 0.3, F = 173.4, Q2 = 0.712, RMSE = 0.3, Person-R = 0.94, and r2pred = 0.8) to explicate the structural attributes crucial for antimalarial activity. The developed pharmacophore model and 3D QSAR model can be a substantial tool for virtual screening and related antimalarial drug discovery research.

3D MI-DRAGON: New Model for the Reconstruction of US FDA Drug- Target Network and Theoretical-Experimental Studies of Inhibitors of Rasagiline Derivatives for AChE

The number of neurodegenerative diseases has been increasing in recent years. Many of the drug candidates to be used in the treatment of neurodegenerative diseases present specific 3D structural features. An important protein in this sense is the acetylcholinesterase (AChE), which is the target of many Alzheimer's dementia drugs. Consequently, the prediction of Drug-Protein Interactions (DPIs/nDPIs) between new drug candidates and specific 3D structure and targets is of major importance. To this end, we can use Quantitative Structure-Activity Relationships (QSAR) models to carry out a rational DPIs prediction. Unfortunately, many previous QSAR models developed to predict DPIs take into consideration only 2D structural information and codify the activity against only one target. To solve this problem we can develop some 3D multi-target QSAR (3D mt-QSAR) models. In this study, using the 3D MI-DRAGON technique, we have introduced a new predictor for DPIs based on two different well-known software. We have used the MARCH-INSIDE (MI) and DRAGON software to calculate 3D structural parameters for drugs and targets respectively. Both classes of 3D parameters were used as input to train Artificial Neuronal Network (ANN) algorithms using as benchmark dataset the complex network (CN) made up of all DPIs between US FDA approved drugs and their targets. The entire dataset was downloaded from the DrugBank database. The best 3D mt-QSAR predictor found was an ANN of Multi-Layer Perceptron-type (MLP) with profile MLP 37:37-24-1:1. This MLP classifies correctly 274 out of 321 DPIs (Sensitivity = 85.35%) and 1041 out of 1190 nDPIs (Specificity = 87.48%), corresponding to training Accuracy = 87.03%. We have validated the model with external predicting series with Sensitivity = 84.16% (542/644 DPIs; Specificity = 87.51% (2039/2330 nDPIs) and Accuracy = 86.78%. The new CNs of DPIs reconstructed from US FDA can be used to explore large DPI databases in order to discover both new drugs and/or targets. We have carried out some theoretical-experimental studies to illustrate the practical use of 3D MI-DRAGON. First, we have reported the prediction and pharmacological assay of 22 different rasagiline derivatives with possible AChE inhibitory activity. In this work, we have reviewed different computational studies on Drug- Protein models. First, we have reviewed 10 studies on DP computational models. Next, we have reviewed 2D QSAR, 3D QSAR, CoMFA, CoMSIA and Docking with different compounds to find Drug-Protein QSAR models. Last, we have developped a 3D multi-target QSAR (3D mt-QSAR) models for the prediction of the activity of new compounds against different targets or the discovery of new targets.

Computational Studies of Novel Chymase Inhibitors Against Cardiovascular and Allergic Diseases: Mechanism and Inhibition

To provide a new idea for drug design, a computational investigation is performed on chymase and its novel 1,4-diazepane-2,5-diones inhibitors that explores the crucial molecular features contributing to binding specificity. Molecular docking studies of inhibitors within the active site of chymase were carried out to rationalize the inhibitory properties of these compounds and understand their inhibition mechanism. The density functional theory method was used to optimize molecular structures with the subsequent analysis of highest occupied molecular orbital, lowest unoccupied molecular orbital, and molecular electrostatic potential maps, which revealed that negative potentials near 1,4-diazepane-2,5-diones ring are essential for effective binding of inhibitors at active site of enzyme. The Bayesian model with receiver operating curve statistic of 0.82 also identified arylsulfonyl and aminocarbonyl as the molecular features favoring and not favoring inhibition of chymase, respectively. Moreover, genetic function approximation was applied to construct 3D quantitative structure-activity relationships models. Two models (genetic function approximation model 1 r(2) = 0.812 and genetic function approximation model 2 r(2) = 0.783) performed better in terms of correlation coefficients and cross-validation analysis. In general, this study is used as example to illustrate how combinational use of 2D/3D quantitative structure-activity relationships modeling techniques, molecular docking, frontier molecular orbital density fields (highest occupied molecular orbital and lowest unoccupied molecular orbital), and molecular electrostatic potential analysis may be useful to gain an insight into the binding mechanism between enzyme and its inhibitors.

3D-QSAR studies on UDP-glucuronosyltransferase 2B7 substrates using the pharmacophore and VolSurf approaches

UDP-glucuronosyltransferase 2B7 (UGT2B7) is an important enzyme responsible for clearance of many drugs. Here, we report two 3D quantitative structure-activity relationship (QSAR) models for UGT2B7 using the pharmacophore and VolSurf approach, respectively.The dataset included 53 structurally diverse UGT2B7 substrates, 36 of which were used for the training set and 17 of which for the external test set. Pharmacophore-based 3D-QSAR model (or hypothesis) was developed using the Discovery Studio program. A user-defined “glucuronidation site” feature was forcefully included in a pharmacophore hypothesis. VolSurf-based 3D-QSAR model was generated using the VolSurf program. This involves calculation of VolSurf descriptors, variable selection with the FFD algorithm, and partial least squares (PLS) analyses.The best pharmacophore model (r2 = 0.736) consists of one glucuronidation site, one hydrogen bond acceptor, and three hydrophobic regions. Using this model, Km values for 14 of 17 test substrates were predicted within one log unit. The yielded VolSurf (PLS) model with two components shows statistical significance in both fitting and internal predicting (r2 = 0.866, q2 = 0.728). Further, the Km values for all test substrates were predicted within one log unit. In addition, the VolSurf model reveals an overlay of chemical features influencing the enzyme-substrate binding. Those include molecular size and shape, integy moments, capacity factors, best volumes of DRY probe, H-bonding, and log P.In conclusion, the pharmacophore and VolSurf approaches are successfully utilized to establish predictive models for UGT2B7. The derived models should be an efficient tool for high throughput prediction of UGT2B7 metabolism.