Search for substructures amenable to MS classification

Among the 1790 substructures there are 301 for which such sets can be obtained. For each of these 301 substructures we calculate MS classifiers. For descriptor selection we use, as described above, the 50 -fold stepwise procedure within MLR. By so doing we obtain 13 MS descriptors relevant for modeling for each substructure. For classification CT, LDA, ANN with one, two, or three HN, and SVM with linear, radial, polynomial (degree = 2), and sigmoid kernel are used. 

We are interested only in those substructures for which good classifiers can be found. There are 15 substructures for which altogether 80 classifiers of MCE-j-g 0.1 are found. The 80 classifiers are distributed over the various methods as follows  

---