Neural networks, structural effects

The selection of cluster number, which is generally not known beforehand, represents the primary performance criterion. Optimization of performance therefore requires trial-and-error adjustment of the number of clusters. Once the cluster number is established, the neural network structure is used as a way to determine the linear discriminant for interpretation. In effect, the RBFN makes use of known transformed features space defined in terms of prototypes of similar patterns as a result of applying /c-means clustering. 

L. Luo, Predictability comparison of four neural network structures for correcting matrix effects in X-ray fluorescence spectrometry, J. Trace Microprobe Tech., 18(3), 2000, 349-360. 

The role of an artificial neural network is to discover the relationships that link patterns of input data to associated output data. Suppose that a database contains information on the structure of many potential drug molecules (the input) and their effectiveness in treating some specific disease (the output). Since the clinical value of a drug must in some way be related to its molecular structure, correlations certainly exist between structure and effectiveness, but those relationships may be very subtle and deeply buried. 

We have already met one tool that can be used to investigate the links that exist among data items. When the features of a pattern, such as the infrared absorption spectrum of a sample, and information about the class to which it belongs, such as the presence in the molecule of a particular functional group, are known, feedforward neural networks can create a computational model that allows the class to be predicted from the spectrum. These networks might be effective tools to predict suitable protective glove material from a knowledge of molecular structure, but they cannot be used if the classes to which samples in the database are unknown because, in that case, a conventional neural network cannot be trained. 

A classical Hansch approach and an artificial neural networks approach were applied to a training set of 32 substituted phenylpiperazines characterized by their affinity for the 5-HTiA-R and the generic arAR [91]. The study was aimed at evaluating the structural requirements for the 5-HTiA/ai selectivity. Each chemical structure was described by six physicochemical parameters and three indicator variables. As electronic descriptors, the field and resonance constants of Swain and Lupton were used. Furthermore, the vdW volumes were employed as steric parameters. The hydrophobic effects exerted by the ortho- and meta-substituents were measured by using the Hansch 7t-ortho and n-meta constants [91]. The resulting models provided a significant correlation of electronic, steric and hydro-phobic parameters with the biological affinities. Moreover, it was inferred that the... 

Classical QSAR will continue to play its part in the optimization and selection of drug candidates. A fundamental difficulty with classical (property-based) QSAR is an over-reliance on the relevance of hydrophobicity, electrostatic and simple bulk steric effects as determinants of relative potency. We know that conformation is crucially important, but this is ignored in the classical approaches. The need for a structure-based QSAR method which also incorporates conformational flexibility might be met by development of a neural network (Livingstone and Salt, 1992 So and Richards, 1992) or machine learning program (King et al., 1992). 

Vivarelli et al. (1995) used a hybrid system that combined a local genetic algorithm (LGA) and neural networks for the protein secondary structure prediction. The LGA, a version of the genetic algorithms (GAs), was particularly suitable for parallel computational architectures. Although the LGA was effective in selecting different... 

---