On Outliers and Activity CliffsWhy QSAR Often Disappoints

Quantitative structure activity relationships (QSAR) have been around for many years and have been employed in numerous fields from drug design to environmental toxicology. Countless papers have been written employing a wide variety of descriptors and computational methods in order to determine them. Nevertheless, while the jury is still out, it is safe to say that QSAR have not generally lived up to expectations, especially in cases where they are applied to data sets determined after the QSAR models were constructed. But this is true even in many "typical cases" where all of the data are known beforehand and are divided into training and test sets in order to construct and validate a model. Certainly the number of parameters available for use in QSAR models is sufficiently large and diverse to ensure reasonable predictions of bioactivity.