Prev. Article Next Article Table of Contents

Research Article

Modeling Toxicity by Using Supervised Kohonen Neural Networks

Paolo Mazzatorta,*^†^‡ Marjan Vra

ko,^‡ Aneta Jezierska,^‡^§ and Emilio Benfenati^†

Istituto Mario Negri, via Eritrea 62, 20157 Milan, Italy, National Institute of Chemistry, Hajdrihova 19, 1001 Ljubljana, P.O. Box 3430, Slovenia, and University of Wroclaw, Faculty of Chemistry, F. Joliot-Curie 14, 50-385 Wroclaw, Poland

J. Chem. Inf. Comput. Sci., 2003, 43 (2), pp 485–492

DOI: 10.1021/ci0256182

Publication Date (Web): March 6, 2003

Corresponding author phone: +39-02-39014499; fax: +39-02-39001916; e-mail: mazzatorta@marionegri.it.

†

Istituto Mario Negri.

‡

National Institute of Chemistry.

University of Wroclaw.

Abstract

Counterprogation neural network is shown to be a powerful and suitable tool for the investigation of toxicity. This study mined a data set of 568 chemicals. Two hundred eighty-two objects were used as the training set and 286 as the test set. The final model developed presents high performances on the data set R² = 0.83 (R² = 0.97 on the training set, R² = 0.59 on the test set). This technique distinguishes itself also for the ability to give to the expert two-dimensional maps suitable for the study of the distribution/clustering of the data and the identification of outliers.

View: Full Text HTML | Hi-Res PDF