ADME properties evaluation in drug discovery: in silico prediction of blood-brain partitioning.

The absorption, distribution, metabolism and excretion properties are important for drugs, and prediction of these properties in advance will save the cost of drug discovery substantially. The ability to penetrate the blood-brain barrier is critical for drugs targeting central nervous system, which is represented by the ratio of its concentration in brain and in blood. Herein, a quantitative structure-property relationship study was carried out to predict blood-brain partitioning coefficient (logBB) of a data set consisting of 287 compounds. Four different methods including support vector machine, multivariate linear regression, multivariate adaptive regression splines and random forest were employed to build prediction models with 116 molecular descriptors selected by Boruta algorithm. The RF model had best performance in training set ([Formula: see text] = 0.938), test set ([Formula: see text] = 0.840) and tenfold cross-validation ([Formula: see text] = 0.788). Finally, we found that the polar surface area and octanol-water partition coefficient have the greatest influence on blood-brain partitioning. Results suggest that the proposed model is a useful and practical tool to predict the logBB values of drug candidates.

QSAR modeling and in silico design of small-molecule inhibitors targeting the interaction between E3 ligase VHL and HIF-1α.

Protein-protein interactions (PPIs) have attracted much attention recently because of their preponderant role in most biological processes. The prevention of the interaction between E3 ligase VHL and HIF-1[Formula: see text] may improve tolerance to hypoxia and ameliorate the prognosis of many diseases. To obtain novel potent inhibitors of VHL/HIF-1[Formula: see text] interaction, a series of hydroxyproline-based inhibitors were investigated for structural optimization using a combination of QSAR modeling and molecular docking. Here, 2D- and 3D-QSAR models were developed by genetic function approximation (GFA) and comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA) methods, respectively. The top-ranked models with strict validation revealed satisfactory statistical parameters (CoMFA with [Formula: see text], 0.637; [Formula: see text], 0.955; [Formula: see text], 0.944; CoMSIA with [Formula: see text], 0.649; [Formula: see text], 0.954; [Formula: see text], 0.911; GFA with [Formula: see text], 0.721; [Formula: see text], 0.801; [Formula: see text], 0.861). The selected five 2D-QSAR descriptors were in good accordance with the 3D-QSAR results, and contour maps gave the visualization of feature requirements for inhibitory activity. A new diverse molecular database was created by molecular fragment replacement and BREED techniques for subsequent virtual screening. Eventually, 31 novel hydroxyproline derivatives stood out as potential VHL/HIF-1[Formula: see text] inhibitors with favorable predictions by the CoMFA, CoMSIA and GFA models. The reliability of this protocol suggests that it could also be applied to the exploration of lead optimization of other PPI targets.

Identification of Covalent Binding Sites Targeting Cysteines Based on Computational Approaches.

Covalent drugs have attracted increasing attention in recent years due to good inhibitory activity and selectivity. Targeting noncatalytic cysteines with irreversible inhibitors is a powerful approach for enhancing pharmacological potency and selectivity because cysteines can form covalent bonds with inhibitors through their nucleophilic thiol groups. However, most human kinases have multiple noncatalytic cysteines within the active site; to accurately predict which cysteine is most likely to form covalent bonds is of great importance but remains a challenge when designing irreversible inhibitors. In this work, FTMap was first applied to check its ability in predicting covalent binding site defined as the region where covalent bonds are formed between cysteines and irreversible inhibitors. Results show that it has excellent performance in detecting the hot spots within the binding pocket, and its hydrogen bond interaction frequency analysis could give us some interesting instructions for identification of covalent binding cysteines. Furthermore, we proposed a simple but useful covalent fragment probing approach and showed that it successfully predicted the covalent binding site of seven targets. By adopting a distance-based method, we observed that the closer the nucleophiles of covalent warheads are to the thiol group of a cysteine, the higher the possibility that a cysteine is prone to form a covalent bond. We believe that the combination of FTMap and our distance-based covalent fragment probing method can become a useful tool in detecting the covalent binding site of these targets.

A combined drug discovery strategy based on machine learning and molecular docking.

Data mining methods based on machine learning play an increasingly important role in drug design and discovery. In the current work, eight machine learning methods including decision trees, k-Nearest neighbor, support vector machines, random forests, extremely randomized trees, AdaBoost, gradient boosting trees, and XGBoost were evaluated comprehensively through a case study of ACC inhibitor data sets. Internal and external data sets were employed for cross-validation of the eight machine learning methods. Results showed that the extremely randomized trees model performed best and was adopted as the first step of virtual screening. Together with structure-based virtual screening in the second step, this combined strategy obtained desirable results. This work indicates that the combination of machine learning methods with traditional structure-based virtual screening can effectively strengthen the ability in finding potential hits from large compound database for a given target.

Virtual Screening Strategy Combined Bayesian Classification Model, Molecular Docking for Acetyl-CoA Carboxylases Inhibitors.

INTRODUCTION: Acetyl-CoA Carboxylases (ACC) have been an important target for the therapy of metabolic syndrome, such as obesity, hepatic steatosis, insulin resistance, dyslipidemia, non-alcoholic fatty liver disease (NAFLD), non-alcoholic steatohepatitis (NASH), type 2 diabetes (T2DM), and some other diseases. METHODS: In this study, virtual screening strategy combined with Bayesian categorization modeling, molecular docking and binding site analysis with protein ligand interaction fingerprint (PLIF) was adopted to validate some potent ACC inhibitors. First, the best Bayesian model with an excellent value of Area Under Curve (AUC) value (training set AUC: 0.972, test set AUC: 0.955) was used to screen compounds of validation library. Then the compounds screened by best Bayesian model were further screened by molecule docking again. RESULTS: Finally, the hit compounds evaluated with four percentages (1%, 2%, 5%, 10%) were verified to reveal enrichment rates for the compounds. The combination of the ligandbased Bayesian model and structure-based virtual screening resulted in the identification of top four compounds which exhibited excellent IC 50 values against ACC in top 1% of the validation library. CONCLUSION: In summary, the whole strategy is of high efficiency, and would be helpful for the discovery of ACC inhibitors and some other target inhibitors.

In silico Prediction of Inhibitory Constant of Thrombin Inhibitors Using Machine Learning.

BACKGROUND: Thrombin is the central protease of the vertebrate blood coagulation cascade, which is closely related to cardiovascular diseases. The inhibitory constant Ki is the most significant property of thrombin inhibitors. METHOD: This study was carried out to predict Ki values of thrombin inhibitors based on a large data set by using machine learning methods. Taking advantage of finding non-intuitive regularities on high-dimensional datasets, machine learning can be used to build effective predictive models. A total of 6554 descriptors for each compound were collected and an efficient descriptor selection method was chosen to find the appropriate descriptors. Four different methods including multiple linear regression (MLR), K Nearest Neighbors (KNN), Gradient Boosting Regression Tree (GBRT) and Support Vector Machine (SVM) were implemented to build prediction models with these selected descriptors. RESULTS: The SVM model was the best one among these methods with R2=0.84, MSE=0.55 for the training set and R2=0.83, MSE=0.56 for the test set. Several validation methods such as yrandomization test and applicability domain evaluation, were adopted to assess the robustness and generalization ability of the model. The final model shows excellent stability and predictive ability and can be employed for rapid estimation of the inhibitory constant, which is full of help for designing novel thrombin inhibitors.