RED: A Set of Molecular Descriptors Based on Renyi Entropy

New molecular descriptors, RED (Renyi entropy descriptors), based on the generalized entropies introduced by Renyi are presented. Topological descriptors based oil molecular features have proven to be useful for describing molecular profiles. Renyi entropy is used as a variability measure to contract a feature-pair distribution composing the descriptor vector. The performance of RED descriptors was tested for the analysis of different sets of molecular distances, virtual screening, and pharmacological profiling. A free parameter of the Renyi entropy has been optimized for all the considered applications.