Pattern recognition, QSAR

In the early 1960 s Hansch and coworkers developed the Hansch equation. Since then quantum mechanical QSAR and pattern recognition QSAR have emerged. The Hansch approach today is still a widely used technique in medicinal chemistry and insecticide chemistry. 

Another technique is to use pattern recognition routines. Whereas QSAR relates activity to properties such as the dipole moment, pattern recognition examines only the molecular structure. It thus attempts to find correlations between the functional groups and combinations of functional groups and the biological activity. 

While principal components models are used mostly in an unsupervised or exploratory mode, models based on canonical variates are often applied in a supervisory way for the prediction of biological activities from chemical, physicochemical or other biological parameters. In this section we discuss briefly the methods of linear discriminant analysis (LDA) and canonical correlation analysis (CCA). Although there has been an early awareness of these methods in QSAR [7,50], they have not been widely accepted. More recently they have been superseded by the successful introduction of partial least squares analysis (PLS) in QSAR. Nevertheless, the early pattern recognition techniques have prepared the minds for the introduction of modem chemometric approaches. 

There is a tendency to think of medicinal chemistry as primarily a logical exercise. A specific and trivial example would be the much maligned QSAR exploration of methyl, ethyl, butyl, futile. This author believes that equating medicinal chemistry with QSAR is incorrect. There is a definite place for what might for want of a better term be called high-order pattern recognition. A specific example is the time tested... 

Similarly, quantitative structure-metabolism relationships (QSMR) have been studied [42]. QSAR tools, such as pattern recognition analysis, have been used to e. g. predict phase II conjugation of substituted benzoic acids in the rat [53]. 

ADAPT Pattern recognition Cluster analysis Uses QSAR descriptors of molecular structure Limited to congeneric series of chemicals... 

In Chapter 4, David Lewis introduces computer-assisted methods in the evaluation of chemical toxicology. He points out that any substance can be toxic, and thus it is the dose of the substance that determines a toxic response. How, then, does one predict toxicity Lewis examines QSAR methods, pattern recognition techniques, computer modeling, and knowledge-based systems to answer this question. Ideally, one would like to assess toxicity of a structure before the compound is synthesized. To bring all this into focus, emphasis is placed on the cytochromes P450. 

Dunn III, W.J. and Wold. S. SIMCA Pattern Recognition and Classification. In QSAR Chemometric Methods in Molecular Design, Methods and Principles in Medicinal Chemistry, 2, Ed. van de Waterbeemd, H., Verlag Chemie, Weinheim, Germany, 1995. 

Miyashita, Y., Li, Z.L. and Sasaki, S. (1993). Chemical Pattern Recognition and Multivariate Analysis for QSAR Studies. TRAC, 12,50-60. 

A large number of substituent descriptors have been reported in the literature. In order to use this information for substituent selection, appropriate statistical methods may be used. Pattern recognition or data reduction techniques, such as PCA or CA are good choices. As explained in Section III.B.3. in more detail, PCA consists of condensing the information in a data table into a few new descriptors made of linear combinations of the original ones. These new descriptors are called PCs or latent variables. This technique has been applied to define new descriptors for amino acids, as well as for aromatic or aliphatic substituents, which are called principal properties (PPs). These PPs can be used in FD methods or as variables in QSAR analysis. ... 

Hyde, R. M., Livingstone, D. J. Perspectives in QSAR computer chemistry and pattern recognition. J. Comput.-Aided Mol. Des. 1988, 2,145-155. 

On the other hand, several investigators (6, 7) have taken another approach, based on pattern recognition. These dichotomous models search for agreement between dependent variables i.e., whether a chemical entity or substructure can be associated with a particular toxic property. For example, certain N-nitrosamine groups are associated with tumors in animals. Since this consideration is not dependent on a relationship between the endpoint and the dose, the quantitative term is dropped from QSAR and the effort simply named SAR. This approach is best expressed by the dependent equation ... 

---