Pattern recognition chemical structure information

Figure I. Flow chart of steps involved in structure-activity studies using chemical structure information handling and pattern recognition techniques...

Pattern recognition can be applied for the determination of structural features of unknown (monofunctional) compounds (Huber and Reich ). The information about the chemical structure is contained in a multidimensional gas-liquid retention data/stationary liquid phases set. The linear learning machine method is applied in a two step classification procedure. After the determination of a correction term, the skeleton number, a classification step for the determination of the functional group is executed. It is remarkable that 10 stationary phases are sufficient for the classification. 

Because pattern recognition is well suited to the consideration of large amounts of information and to making use of obscure relations, we have applied it to chemical structure identification from electrochemical data. The main questions have been what data should be collected and how much ... 

One of the main advantages of RDF descriptors is that they are interpretable. A simple approach to the recognition of structural features is to search for patterns, which provide valuable information in RDF descriptors for similarity searches. The importance of recognizing patterns in chemical data has already been emphasized. 

An early application of a pattern recognition method to the prediction of olfactory qualities from physicochemical data was reported by Schiffman C2623. A set of 39 odorants was represented by 25 parameters (including Raman spectral information). Non-linear mapping revealed correlations of the chemical structure and smell. 

Three different approaches have been used for computer-assisted interpretations of chemical data. 1. Heuristic methods try to formulate computer programs working in a similar way as a chemist would solve the problem. 2. Retrieval methods have been successfully used for library search (an unknown spectrum is compared with a spectral library). 3. Pattern recognition methods are especially useful for the classification of objects (substances, materials) into discrete classes on the basis of measured features. A set of characteristic features (e.g. a spectrum) of an object is considered as an abstract pattern that contains information about a not directly measurable property (e.g. molecular structure or biological activity) of the object. Pure pattern recognition methods try to find relationships between the pattern and the "obscure property" without using chemical knowledge or chemical prejudices. 

Unfortunately, real data from electrochemical experiments are usually confused by noise and experimental artifacts. Although, signal processing techniques, such as Fourier transformation and digital filtering, can be used to improve the quality of the data, there is still a need for techniques that can extract useful information where there is inherent data uncertainty which cannot be removed. Pattern recognition techniques are powerful tools for this purpose (34,, W). They have been applied to classify electrochemical data on the basis of electrode mechanism (37, ) and chemical structure (i9,4Q). 

This concept involves the selection of one or more bench-mark chemicals from important classes of toxic chemicals and measurement of their essential environmental parameters and physico-chemical properties. This information is then integrated to build an environmental profile (Haque et aL, 1980) for the class of chemical. The new chemical is compared with the corresponding bench mark for structural similarity and, using pattern recognition methods, the behavior of the new chemical can be predicted (Figure 11.5). 

---