Predictability and prediction of lowest observed adverse effect levels in a structurally heterogeneous set of chemicals

Abstract

A database of chronic lowest observed adverse effect levels (LOAELs) for 234 compounds, previously compiled from different sources (Toxicology Letters 79, 131–143 (1995)), was modelled using graph theoretical descriptors. This study reveals that data are not homogeneous. Only those data originating from the U.S. Environmental Protection Agency (EPA) reports could be well modelled by multilinear regression (MLR) and linear discriminant analysis (LDA). In contrast, data available from the specific procedures of the National Toxicology Program (NTP) database introduced noise and did not render good models either alone, or in combination with the EPA data.

Keywords:

• Lowest observed adverse effect level
• Topological indices
• Multilinear regression
• Linear discriminant analysis
• Data homogeneity
• External validation

Acknowledgements

The authors acknowledge the financing of this research to the Red Temática de Investigación Cooperativa RICET (Red de Investigación de Centros de Enfermedades Tropicales) of the Spanish Ministry of Health.