DrugPred: A Structure-Based Approach To Predict Protein Druggability Developed Using an Extensive Nonredundant Data Set

Abstract

Judging if a protein is able to bind orally available molecules with high affinity, i.e. if a protein is druggable, is an important step in target assessment. In order to derive a structure-based method to predict protein druggability, a comprehensive, nonredundant data set containing crystal structures of 71 druggable and 44 less druggable proteins was compiled by literature search and data mining. This data set was subsequently used to train a structure-based druggability predictor (DrugPred) using partial least-squares projection to latent structures discriminant analysis (PLS-DA). DrugPred performed well in discriminating druggable from less druggable binding sites for both internal and external predictions. The method is robust against conformational changes in the binding site and outperforms previously published methods. The superior performance of DrugPred is likely due to the size and composition of the training set which, in contrast to most previously developed methods, only contains cavities that have evolved to bind a natural ligand.

Intrinsically Disordered Proteins as Drug Targets

“…To that extent, usual CAAD techniques can be useful to estimate the druggability and the effects of small molecules on IDP interactions. 10,34,71,72 These methods analyze the cavities over static structures coming from experiments or simulations such as DrugPred, 73 Cavity 74 or fpocket, 75 or coupled to MD simulations and calculate the druggability "on-the -fly", such as the recently developed JEDI. 76 Zhang and coworkers 44 have studied the ligand-binding cavities of diverse IDPs comparing some of their properties with those of ordered proteins.…”

Untitled

“…To that extent, usual CAAD techniques can be useful to estimate the druggability and the effects of small molecules on IDP interactions [10,34,71,72]. These methods analyze the cavities over static structures coming from experiments or simulations such as DrugPred [73], Cavity [74] or fpocket [75], or coupled to MD simulations and calculate the druggability "on-the -fly", such as the recently developed JEDI [76].…”

Virtual screening: An in silico tool for interlacing the chemical universe with the proteome

“…In general terms, druggability can be inferred from homologous proteins whose druggabilities are known [177]. In one study, using both a non-redundant set of druggable and a less druggable set containing 71 druggable and 44 less-druggable targets [178], it was possible to classify all protein targets into druggable or less druggable ones without serious training [174]: Oxidoreductases appeared more frequently as being druggable, while hydrolases, lyases and isomerases were more frequently less druggable.…”