Prediction of the binding affinities of adenosine A2A receptor antagonists based on the heuristic method and support vector machine

Prediction models with multiple machine learning algorithms for POPs: The calculation of PDMS-air partition coefficient from molecular descriptor

Polydimethylsiloxane-air partition coefficient (K_PDMS-air) is a key parameter for passive sampling to measure POPs concentrations. In this study, 13 QSPR models were developed to predict K_PDMS-air, with two descriptor selection methods (MLR and RF) and seven algorithms (MLR, LASSO, ANN, SVM, kNN, RF and GBDT). All models were based on a data set of 244 POPs from 13 different categories. The diverse model evaluation parameters calculated from training and test set were used for internal and external verification. Notably, the R_adj², Q_BOOT² and Q_ext² are 0.995, 0.980 and 0.951 respectively for GBDT model, showing remarkable superiority in fitting, robustness and predictability compared with other models. The discovery that molecular size, branches and types of the bonds were the main internal factors affecting the partition process was revealed by mechanism explanation. Different from the existing QSPR models based on single category compounds, the models developed herein considered multiple classes compounds, so that its application domain was more comprehensive. Therefore, the obtained models can fill the data gap of missing experimental K_PDMS-air values for compounds in the application range, and help researchers better understand the distribution behavior of POPs from the perspective of molecular structure.

Revisiting a receptor-based pharmacophore hypothesis for human A(2A) adenosine receptor antagonists

The application of both structure- and ligand-based design approaches represents to date one of the most useful strategies in the discovery of new drug candidates. In the present paper, we investigated how the application of docking-driven conformational analysis can improve the predictive ability of 3D-QSAR statistical models. With the use of the crystallographic structure in complex with the high affinity antagonist ZM 241385 (4-(2-[7-amino-2-(2-furyl)[1,2,4]-triazolo[2,3-a][1,3,5]triazin-5-ylamino]ethyl)phenol), we revisited a general pharmacophore hypothesis for the human A(2A) adenosine receptor of a set of 751 known antagonists, by applying an integrated ligand- and structure-based approach. Our novel pharmacophore hypothesis has been validated by using an external test set of 29 newly synthesized human adenosine receptor antagonists.

Insight into the binding mode and the structural features of the pyrimidine derivatives as human A2A adenosine receptor antagonists

The interaction of 278 monocyclic and bicyclic pyrimidine derivatives with human A2A adenosine receptor (AR) was investigated by employing molecular dynamics, thermodynamic analysis and three-dimensional quantitative structure-activity relationship (3D-QSAR) approaches. The binding analysis reveals that the pyrimidine derivatives are anchored in TM2, 3, 5, 6 and 7 of A2A AR by the aromatic stacking and hydrogen bonding interactions. The key residues involving Phe168, Glu169, and Asn253 stabilize the monocyclic and bicyclic cores of inhibitors. The thermodynamic analysis by molecular mechanics/Poisson Boltzmann surface area (MM-PBSA) approach also confirms the reasonableness of the binding modes. In addition, the ligand-/receptor-based comparative molecular similarity indices analysis (CoMSIA) models of high statistical significance were generated and the resulting contour maps correlate well with the structural features of the antagonists essential for high A2A AR affinity. A minor/bulky group with negative charge at C2/C6 of pyrimidine ring respectively enhances the activity for all these pyrimidine derivatives. Particularly, the higher electron density of the ring in the bicyclic derivatives, the more potent the antagonists. The obatined results might be helpful in rational design of novel candidate of A2A adenosine receptor antagonist for treatment of Parkinson's disease.