A Genetic Algorithm for Detection of Relevant Descriptors in ADMET Prediction

CECCHINI, ROCÍO L.; SOTO, AXEL J.; VAZQUEZ, GUSTAVO E.; PONZONI IGNACIO

Río de Janeiro, Brasil

Simposio; Brazilian Symposium on Bioinformatics (BSB 2007); 2006

SBC (Sociedad Brasilera de Computación).

  ACLARACION: POR LIMITACIONES DEL SOFTWARE EVA, Y PREVIA CONSULTA CON EL DEPTO. DE CIC DEL CONICET, CARGUÉ ESTE TRABAJO CON FECHA 2006, PERO EN REALIDAD ESTE ARTÍCULO REALIZADO EN EL 2006 HA SIDO ACEPTADO PERO SU PUBLICACIÓN SERÁ EN EL 2007. ----------------------------------------------------- In this work, a novel approach for descriptor selection aimed to physicochemical property prediction is presented. The capacity of determining the most significant set of descriptors is of great importance due to their contribution for improving ADMET prediction models. The proposed methodology combines a genetic algorithm with decision trees. Experimental analysis was carried out for predicting the octanol-water partition coefficient (logP) using neural networks as prediction method. The performance results showed the good potential of this technique.