An Exploration of the Antiproliferative Potential of Chalcones and Dihydropyrazole Derivatives in Prostate Cancer via Androgen Receptor: Combined QSAR, Machine Learning, and Molecular Docking Techniques

In this study, the antiproliferative activities of some chalcones and dihydro pyrazole derivatives in prostate cancer were investigated via the androgen receptor using the QSAR, machine learning, molecular docking techniques. A total of 30 dichloro substituted chalcones and dihydro pyrazole derivatives were collected from literature and optimized using Density Functional Theory. Genetic Function Approximation was employed for the model development. The model generated was thoroughly validated. Its generalizations and predictive capacities were improved with the Extreme Learning Machine algorithm. Molecular docking and drug-like screening of the compounds were carefully performed. A reduction in the negative coefficient of descriptors and an increase in the positive coefficient of the descriptors favor good bioactivities. An R2 pred value of 0.737 shows a high correlation between the experimental activities and the predicted activities. A correlation coefficient R2, 0.8305 authenticates the predictability of the model. The ELM-Sine model showed an improvement of 66.7% and 8.3% over the QSAR and ELM-Sig models respectively. Molecular docking validated the chalcones and dihydropyrazole derivatives as promising anti-prostate cancer compounds, with pi-pi stacking and hydrogen bond interactions favoring their inhibition of the androgen receptor. The leads are drug-like and novel anti-prostate cancer compounds.