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

ALICE, JUAN I.; SANTIAGO RODRÍGUEZ; ALBERCA, LUCAS N.; BELLERA, CAROLINA L.; TALEVI, ALAN

Congreso; XI Argentine Congress of Bioinformatics and Computational Biology (XI CAB2C); 2021

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.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. 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.