A new model of flavonoids affinity towards P-glycoprotein: genetic algorithm-support vector machine with features selected by a modified particle swarm optimization algorithm

A Machine Learning-Based Prediction Platform for P-Glycoprotein Modulators and Its Validation by Molecular Docking

P-glycoprotein (P-gp) is an important determinant of multidrug resistance (MDR) because its overexpression is associated with increased efflux of various established chemotherapy drugs in many clinically resistant and refractory tumors. This leads to insufficient therapeutic targeting of tumor populations, representing a major drawback of cancer chemotherapy. Therefore, P-gp is a target for pharmacological inhibitors to overcome MDR. In the present study, we utilized machine learning strategies to establish a model for P-gp modulators to predict whether a given compound would behave as substrate or inhibitor of P-gp. Random forest feature selection algorithm-based leave-one-out random sampling was used. Testing the model with an external validation set revealed high performance scores. A P-gp modulator list of compounds from the ChEMBL database was used to test the performance, and predictions from both substrate and inhibitor classes were selected for the last step of validation with molecular docking. Predicted substrates revealed similar docking poses than that of doxorubicin, and predicted inhibitors revealed similar docking poses than that of the known P-gp inhibitor elacridar, implying the validity of the predictions. We conclude that the machine-learning approach introduced in this investigation may serve as a tool for the rapid detection of P-gp substrates and inhibitors in large chemical libraries.

Synthesis and Acaricidal Activities of Scopoletin Phenolic Ether Derivatives: QSAR, Molecular Docking Study and in Silico ADME Predictions

Thirty phenolic ether derivatives of scopoletin modified at the 7-hydroxy position were synthesized, and their structures were confirmed by IR, ¹H-NMR, 13C-NMR, MS and elemental analysis. Preliminary acaricidal activities of these compounds against female adults of Tetranychus cinnabarinus (Boisduval) were evaluated using the slide-dip method. The results indicated that some of these compounds exhibit more pronounced acaricidal activity than scopoletin, especially compounds 32, 20, 28, 27 and 8 which exhibited about 8.41-, 7.32-, 7.23-, 6.76-, and 6.65-fold higher acaricidal potency. Compound 32 possessed the the most promising acaricidal activity and exhibited about 1.45-fold higher acaricidal potency against T. cinnabarinus than propargite. Statistically significant 2D-QSAR model supports the observed acaricidal activities and reveals that polarizability (HATS5p) was the most important parameter controlling bioactivity. 3D-QSAR (CoMFA: q² = 0.802, r² = 0.993; CoMSIA: q² = 0.735, r² = 0.965) results show that bulky substituents at R₄, R₁, R₂ and R₅ (C₆, C₃, C₄, and C₇) positions, electron positive groups at R₅ (C₇) position, hydrophobic groups at R₁ (C₃) and R₂ (C₄), H-bond donors groups at R₁ (C₃) and R₄ (C₆) will increase their acaricidal activity, which provide a good insight into the molecular features relevant to the acaricidal activity for further designing novel acaricidal agents. Molecular docking demonstrates that these selected derivatives display different bide modes with TcPMCA1 from lead compound and they interact with more key amino acid residues than scopoletin. In silico ADME properties of scopoletin and its phenolic ether derivatives were also analyzed and showed potential to develop as good acaricidal candidates.