Multivariate structure‐activity relationships between data from a battery of biological tests and an ensemble of structure descriptors: The PLS method

Abstract

Abstract Quantitative structure‐activity relationships (QSAR) are discussed for the case when the chemical structure is characterised by a multitude of structure descriptors and the biological activity measured as the values of several tests. The use of the multivariate data analytical method PLS (partial least squares modelling with latent variables) in this type of problems is described. PLS has some advantages before regression methods, notably the ability to handle both multivariate activity and structure descriptor data and the ability to handle more variables (descriptors) than compounds. As an illustration, a battery of five measures of the mutagenicity of seven chlorinated aliphatic hydrocarbons is analysed in relation to eleven structure descriptors.