Synthesize and Submit for Biological Evaluation

Pattern recognition techniques attempt to find which faaors can account for the differences between active and inactive compounds. In his parameter focusing approach, Magee uses two-dimensional x-y scatter plots to achieve this purpose. The active compounds are distinguished from the inactive ones on the plot. All combinations of two parameters are examined. Discrimination 

Magee recognizes that a two-dimensional plot of this type cannot represent the three basic faaors in structure-aaivity space but hypothesizes that most published models are usually made up of only two parameters. Therefore such two-dimensional plots will cover most cases. They also have the distinct advantage of not requiring computers or extensive statistical knowledge. 

If the assumption that only two parameters are important to aaivity is troublesome, an alternative approach would be the use of discriminant analysis. This technique uses any number of parameters to attempt to discriminate between active and inactive compounds or any other grouping of properties. The average values of a property for the active set and the inactive set are compared to the average value of the same property for both sets combined. If they are statistically different, then the factor involved can be used as a discriminant. A good example of this approach can be found in a report by Martin et al. Additional examples can be found in the work of Franke and Meisske, Henry and Block, and Ogino et al.  

One major issue that causes some problems in the application of discriminant techniques, such as parameter focusing and discriminant analysis, is the definition of what is aaive and what is inactive. An approach to solving this problem is to define activity as very active, active, sli tly active, and inactive, and then to remove the compounds fitting the middle two classifications. The ultimate product of such pattern recognition techniques should be 

---