Advancing Plant-Based Anti-Cancer Drug Discovery through Hybrid Ensemble Models

Chemotherapy is a powerful tool in the fight against cancer, but it is not without its risks. Damage to healthy tissues that aren't specifically targeted, drug resistance, and disease recurrence are all possible complications. The remarkable chemical and functional diversity of phytocompounds has made them an important resource for medicinal research, and many of these molecules have helped develop new cancer medicines. As a possible new cancer treatment, phytocompounds are being studied by researchers and pharmaceutical companies across the globe. This study presents a three-stage hybrid ELM model for the discovery of anti-cancer drugs derived from plants. The phases are preprocessing, feature extraction, and model training. PCA is used to derive features once the dataset is cleaned using min-max normalisation. This model takes advantage of the best features of boosting and bagging ensemble methods by combining them. The experimental results show that compared to conventional models, the hybrid ELM model achieves a remarkable accuracy of 95.91%. The benefits of ensemble learning approaches are demonstrated in this study, and machine learning can be used to discover anti-cancer medications derived from plants. Improving the model's predictive power and expanding dataset sizes should be the primary focusses of future studies.