Chapter 4 - Algorithms for (Q)SAR model building

Abstract

The concept of mathematically relating biological activity with physicochemical properties of related chemical compounds emerged in the 1960s. Early quantitative structure–activity relationships (QSARs) were based on simple principles, such as substituent parameters, and linear mathematics. It was gradually realized that QSAR models based on such simplistic properties and statistical algorithms only worked well in certain well-defined situations. QSAR models for relatively simple sets of molecular data are still based on linear algorithms, but this approach has only a limited usefulness in finding multidimensional relational patterns in complex data sets. Linear models are also often hard to generalize across chemical classes and/or test species. This has led to the use of nonlinear algorithms and soft computing techniques, such as fuzzy systems, probabilistic methods, and artificial neural networks to decipher relational patterns in large, imprecise, and complex data sets. This shift in QSAR paradigm has made it possible to predict biological properties of a wide range of chemicals, which otherwise would be difficult, or impossible to determine experimentally.