Pattern recognition activity relations using

Studies of Chemical Structure-Biological Activity Relations Using Pattern Recognition... 

Jurs, P. C., Chou, J. T. and Yuan, M. (1979). Studies of chemical structure-biological activity relations using pattern recognition. In Computer-Assisted Drug Design. 

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. 

Applications of pattern recognition methodology to chemical problems were first reported in the 1960 s (20,21) with studies of mass spectra. Since then papers have described work in a variety of areas (22,23) including mass spectrometry, infrared spectroscopy, NMR spectroscopy, electrochemistry, materials science and mixture analysis, and the modeling of chemical experiments. Diagnosis of pathological conditions from sets of measurements made on complex biological mixtures, e.g., serum, have been reported (24). The successes in these areas have led to the belief that these methods should prove useful in the development of structure-activity relations. 

Andreazza Costa, M.C., Soares Barata, L.E. and Takahata, Y. (1995) SAR analysis of synthetic neolignans and related compounds which are antileishmaniasis active compounds using pattern recognition methods. J. Mol. Struct. (Theochem), 340, 185-192. 

Coluci, V.R., Vendrame, R., Braga, R.S. and Gamper, A.M. (2002) Identifying relevant molecular descriptors related to carcinogenic activity of polycyclic aromatic hydrocarbons (PAHs) using pattern recognition methods./. Chem. Inf. Comput. Sci., 42. 1479-1489. 

In summary, the pattern recognition studies indicate that the reactivity of the p-lactam ring is a crucial determinant of the in vitro antibacterial activity of a related series of cephalosporins. Physicochemical properties that do not reflect reactivity appear to be less useful indicators of activity. 

The unsupervised pattern recognition normally consists of cluster analysis. Using a couple of dozen descriptors of molecules, it is possible to see which activities of molecules are most similar and draw a picture of these similarities, called a dendrogram, in which more closely related activities are closer to each other... 

---