Hybridizing feature selection and feature learning approaches in QSAR modeling for drug discovery

19 p.-12 fig.-5 tab. Ponzoni, Ignacio et al.Quantitative structure–activity relationship modeling using machine learning techniques constitutes a complex computational problem, where the identification of the most informative molecular descriptors for predicting a specific target property plays a critical role. Two main general approaches can be used for this modeling procedure: feature selection and feature learning. In this paper, a performance comparative study of two state-of-art methods related to these two approaches is carried out. In particular, regression and classification models for three different issues are inferred using both methods under different experimental scenarios: two drug-like properties, such as blood-brainbarrier and human intestinal absorption, and enantiomeric excess, as a measurement of purity used for chiral substances. Beyond the contrastive analysis of feature selection and feature learning methods as competitive approaches, the hybridization of these strategies is also evaluated based on previous results obtained in material sciences. From the experimental results, it can be concluded that there is not a clear winner between both approaches because the performance depends on the characteristics of the compound databases used for modeling. Nevertheless, in several cases, it was observed that the accuracy of the models can be improved by combining both approaches when the molecular descriptor sets provided by feature selection and feature learning contain complementary information.This work was supported by Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET) [Grant number 112-2012-0100471 and PIP 114-2011-0100362], the Secretaría de Ciencia y Tecnología of the Universidad Nacional del Sur (UNS) [Grant numbers 24/N032, 24/ZN26] and MINECO (Spain) [project CTQ2015-66313-R and CTQ2015-66954-P MINECO/FEDER]. Dr. Ponzoni did this work as a visiting researcher at the Centro de Investigaciones Biológicas (CIB-CSIC) at Madrid (Spain). The authors would like to express their acknowledgment to the 6° Programa de Movilidad Docente a Madrid of the Secretaría de Políticas Universitarias (SPU), Ministerio de Educación de la República Argentina, for their economic support given for Dr. Ponzoni’s visit. Víctor Sebastián-Pérez acknowledges a predoctoral fellowship from MINECO [FPU15/01465].Peer reviewe