Skip to content


  • Poster presentation
  • Open Access

Adaptive matrix metrics for molecular descriptor assessment in QSPR classification

  • 1,
  • 2 and
  • 1
Journal of Cheminformatics20102 (Suppl 1) :P47

  • Published:


  • Discriminant Analysis
  • Classification Accuracy
  • Linear Discriminant Analysis
  • Candidate Drug
  • Discovery Process

QSPR methods represent a useful approach in the drug discovery process, since they allow predicting in advance biological or physicochemical properties of a candidate drug. For this goal, it is necessary that the QSPR method be as accurate as possible to provide reliable predictions. Moreover, the selection of the molecular descriptors is an important task to create QSPR prediction models of low complexity which, at the same time, provide accurate predictions.

In this work, a matrix-based method [1] is used to transform the original data space of chemical compounds into an alternative space where compounds with different target properties can be better separated. For using this approach, QSPR is considered as a classification problem. The advantage of using adaptive matrix metrics is twofold: it can be used to identify important molecular descriptors and at the same time it allows improving the classification accuracy.

A recently proposed method making use of this concept [2] is extended to multi-class data. The new method is related to linear discriminant analysis and shows better results at yet higher computational costs. An application for relating chemical descriptors to hydrophobicity property [3] shows promising results.

Authors’ Affiliations

Planta Piloto de Ingeniería Química (PLAPIQUI), Universidad Nacional del Sur, Alem 1250, 8000 Bahía Blanca, Argentina
Leibniz Institute of Plant Genetics and Crop Plant Research (IPK), Corrensstr. 3, 06466 Gatersleben, Germany


  1. Strickert M, Keilwagen J, Schleif F-M, Villmann T, Biehl M: Matrix Metric Adaptation Linear Discriminant Analysis of Biomedical Data. Lecture Notes in Computer Science. 2009, 5517/2009: 933-940. full_text.View ArticleGoogle Scholar
  2. Strickert M, Soto AJ, Keilwagen J, Vazquez GE: Towards matrix-based selection of feature pairs for efficient ADMET prediction. Argentine Symposium on Artificial Intelligence, ASAI. 2009, 83-94.Google Scholar
  3. Soto AJ, Cecchini RL, Vazquez GE, Ponzoni I: A Wrapper-based Feature Selection Method for ADMET Prediction using Evolutionary Computing. Lecture Notes in Computer Science. 2008, 4973/2008: 188-199. full_text.View ArticleGoogle Scholar


© Axel J et al; licensee BioMed Central Ltd. 2010

This article is published under license to BioMed Central Ltd.