Performance of knowledge-based biological models in higher dimensional chemical space

This study evaluates the improvement of the knowledge-based biological models by incorporating additional advanced molecular descriptors to the existing classical descriptors. It was found that the inclusion of constitutional, topological, and hybrid descriptors in the generation of biological models trained on Mtb (Mycobacterium tuberculosis) bioassay dataset using classifiers like Random Forest, J48, Naive Bayes, and SMO (Sequential Minimal Optimization) have found to enhance the performance of these models.