A wrapper-based feature selection method for ADMET prediction using evolutionary computing

Authors:
Axel J. Soto;Rocío L. Cecchini;Gustavo E. Vazquez;Ignacio Ponzoni
Affiliations:
Lab. de Investigación y Desarrollo en Comp. Científica, Dept. de Ciencias e Ingeniería de la Comp., Univ. Nacional del Sur, Argentina and Planta Piloto de Ingeniería Univ. Naci ...;Laboratorio de Investigación y Desarrollo en Computación Científica, Departamento de Ciencias e Ingeniería de la Computación, Universidad Nacional del Sur, Bahía Blan ...;Laboratorio de Investigación y Desarrollo en Computación Científica, Departamento de Ciencias e Ingeniería de la Computación, Universidad Nacional del Sur, Bahía Blan ...;Lab. de Investigación y Desarrollo en Comp. Científica, Dept. de Ciencias e Ingeniería de la Comp., Univ. Nacional del Sur, Argentina and Planta Piloto de Ingeniería Univ. Naci ...
Venue:
EvoBIO'08 Proceedings of the 6th European conference on Evolutionary computation, machine learning and data mining in bioinformatics
Year:
2008

Citing 8
Cited 3

Selection of relevant features and examples in machine learning

Artificial Intelligence - Special issue on relevance
Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
An introduction to variable and feature selection

The Journal of Machine Learning Research
An extensive empirical study of feature selection metrics for text classification

The Journal of Machine Learning Research
Prediction methods and databases within chemoinformatics: emphasis on drugs and drug candidates

Bioinformatics
GALGO: an R package for multivariate variable selection using genetic algorithms

Bioinformatics
Markov blanket-embedded genetic algorithm for gene selection

Pattern Recognition
A genetic algorithm-based method for feature subset selection

Soft Computing - A Fusion of Foundations, Methodologies and Applications

Matrix Metric Adaptation Linear Discriminant Analysis of Biomedical Data

IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part I: Bio-Inspired Systems: Computational and Ambient Intelligence
Segregating Confident Predictions of Chemicals' Properties for Virtual Screening of Drugs

IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part II: Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living
On the use of machine learning methods for modern drug discovery

AI Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Wrapper methods look for the selection of a subset of features or variables in a data set, in such a way that these features are the most relevant for predicting a target value. In chemoinformatics context, the determination of the most significant set of descriptors is of great importance due to their contribution for improving ADMET prediction models. In this paper, a comprehensive analysis of descriptor selection aimed to physicochemical property prediction is presented. In addition, we propose an evolutionary approach where different fitness functions are compared. The comparison consists in establishing which method selects the subset of descriptors that best predicts a given property, as well as maintaining the cardinality of the subset to a minimum. The performance of the proposal was assessed for predicting hydrophobicity, using an ensemble of neural networks for the prediction task. The results showed that the evolutionary approach using a non linear fitness function constitutes a novel and a promising technique for this bioinformatic application.