Computational models to assign biopharmaceutics drug disposition classification from molecular structure

Purpose. We applied in silico methods to automatically classify drugs according to the Biopharmaceutics Drug Disposition Classification System (BDDCS). Materials and Methods. Models were developed using machine learning methods including recursive partitioning (RP), random forest (RF) and support vector machine (SVM) algorithms with ChemDraw, clogP, polar surface area, VolSurf and MolConnZ descriptors. The dataset consisted of 165 training and 56 test set molecules. Results. RF model 3, RP model 1, and SVM model 1 can correctly predict 73.1, 63.6 and 78.6% test compounds in classes 1, 2 and 3, respectively. Both RP and SVM models can be used for class 4 prediction. The inclusion of consensus analysis resulted in improved test set predictions for class 2 and 4 drugs. Conclusions. The models can be used to predict BDDCS class for new compounds from molecular structure using readily available molecular descriptors and software, representing an area where in silico approaches could aid the pharmaceutical industry in speeding drugs to the patient and reducing costs. This could have significant applications in drug discovery to identify molecules that may have future developability issues.