Druggability assessment algorithm based on Composition, Transition and Distribution descriptors and publicly available predictive tools

Abstract

Background: In the framework target-guided drug discovery it is important to be able to assess the druggability of the proposed drug target prior to the implementation of a drug discovery project. Druggability is a concept coined by Hopkins and Groom to refer to the ability of a protein to be modulated by small, drug-like molecules. Results: A dataset of 222 proteins druggable and undruggable was compiled, and it was split into a training set for model building and an independent test set for model validation. The training set was then used to infer linear classifiers capable of prospectively discriminating druggable from non-druggable targets. Two algorithms were built and validated for such task. The first one uses CTD (Composition, Transition and Distribution) descriptors, while the second combines CTD descriptors with already reported and validated online druggability assessment tools. 14 druggability predictors were derived from online tools and 147 CTD descriptors were computed using the PyProtein module from PyBioMed library. Using a combination of feature bagging and forward stepwise feature selection, 1000 linear models were built using either a combination of online tools plus CTD or CTD descriptors alone . The best individual model for CTD descriptors displayed an accuracy of 0.803, a precision of 0.738 and recall of 0.939 on the test set, while the best individual model emerging from the combination of CTD descriptors and online tools showed an accuracy of 0.871, a precision of 0.800 and a recall of 0.848. Conclusions: Any target-focused, rational drug discovery initiative starts with the choice and validation of an adequate drug target. Drug target validation implies, among other studies, guaranteeing that the chosen target is druggable. Here, we have reported an algorithm based on CTD descriptors and druggability descriptors derived from online tools, capable of differentiating, with remarkable accuracy druggable from non-druggable proteins in a fast and cost-efficient manner.