Abstract: In the field of pharmaceutical research, identifying promising pharmaceutical compounds is a critical challenge. The observance of Lipinski's Rule of Five (RO5) is a fundamental criterion, but evaluating many compounds manually requires significant resources and time. However, the integration of computational techniques in drug discovery in its early stages has significantly transformed the pharmaceutical industry, enabling further efficient screening and selection of possible drug candidates. Therefore, this study explores RO5 using algorithms of Machine Learning (ML), offering a comprehensive method to predict the druggability of pharmaceutical compounds. The study developed, evaluated, and validated the performance metrics of multiple supervised machine learning models. The best model was used to build an application that can predict and classify potential drug candidates. The findings revealed promising capabilities across all models for drug classification. Among all the explored models, Random Forest (RF), Extreme Gradient Boost (XGBoost), and Decision Tree (DT) classifiers demonstrated exceptional performance, achieving near-perfect accuracy of 99.94%, 99.81% and 99.87% respectively. This highlights the robustness of ensemble learning methods in classifying compounds based on RO5 adherence. The comparative analysis of these models underscores the importance of considering balanced accuracy, precision, F1-score, recall, and Receiver Operating Characteristics-Area Under the Curve (ROC-AUC) score, interpretability, and computational efficiency when choosing between ML algorithms in drug discovery. The DrugCheckMaster application was subsequently developed using the most predictive model and is now available on Render (https://capstone-project-dc7w.onrender.com/). Show less...

Abstract: The present study explored the phytoconstituents and radical scavenging activity of the respective n-hexane and aqueous fractions of Cucurbita maxima (CMHF and CMAF) and Leptadenia hastata (LHHF and LHAF) for potential application in oxidative stress-related ailments. The phytoconstituents were qualitatively determined and characterized using Fourier-transform Infrared (FTIR), while the antioxidant activity was determined in vitro. Alkaloids were present in only the aqueous fractions of C. maxima and L. hastata, while saponins, steroids, and flavonoids were detected in all the fractions. The FTIR revealed the presence of functional groups, including alcohols, sulfonates, alkenes, alkanes, amines, and aromatics in both plant fractions. The LHHF (35.53 ±2.11 ascorbic acid (AA) equivalent µg/mL) exhibited a significantly (p<0.05) higher total reducing power (TRP) than all the other fractions. The CMHF (69.11 ±2.56 AAE µg/mL) demonstrated a significantly (p<0.05) higher total antioxidant capacity (TAC) than all the other fractions. For the ferric thiocyanate (FTC) assay, the highest inhibition was exhibited by LHHF (79.78 ± 3.24%), significantly (p<0.05) higher than AA (26.46 ± 2.12%), CMHF (69.77 ± 3.16%), and CMAF (43.80 ± 2.12%). In the thiobarbituric acid assay, the lowest MDA concentration was exhibited by the CMHF (0.07 ±0.01 nmol/mL), significantly (p<0.05) lower than all the other fractions and ascorbic acid. Conclusively, the n-hexane fraction of both plants presents potential sources of novel antioxidant compounds with significant free radical scavenging and anti-lipid peroxidation activities, applicable in ailments linked to oxidative stress. Show less...