A comparative analysis of the ensemble methods for drug design

Quantitative structure-activity relationship (QSAR) is a computer modeling technique for identifying relationships between the structural properties of chemical compounds and biological activity. QSAR necessary drug discovery, but it has many limitations. Ensemble-based machine learning approaches have been used to overcome limitations generate reliable predictions. Ensemble creates set diverse models combines them. In our comparative analysis, each ensemble algorithm was paired with basic algorithms, algorithms were also investigated separately. this configuration, 57 developed compared on 4 different datasets. Thus, complex method proposed that builds diversified integrates The individual did not show impressive results as unified model, considered most important predictor when combined. We assessed whether ensembles always give better than algorithms. Python code written get experimental in article uploaded Github (https://github.com/rifqat/Comparative-Analysis).