Capability of evolutionary neural network (ENN) based QSAR approach to direct the descriptor selection process towards stable descriptor subset (DS) composition characterized by acceptable generalization, as well as the influence of description stability on QSAR model interpretation have been examined. In order to analyze the DS stability and QSAR model generalization properties multiple random dataset partitions into training and test set were made. Acceptability criteria proposed by Golbraikh et al. [J. Comput.-Aided Mol. Des., 17 (2003) 241] have been chosen for selection of highly predictive QSAR models from a set of all models produced by ENN for each dataset splitting. All QSAR models that pass Golbraikh's filter generated by ENN for each dataset partition were collected. Two final DS forming principles were compared. Standard principle is based on selection of descriptors characterized by highest frequencies among all descriptors that appear in the pool [J. Chem. Inf. Comput. Sci., 43 (2003) 949]. Search across the model pool for DS that are stable against multiple dataset subsampling i.e. universal DS solutions is the basis of novel approach. Based on described principles benzodiazepine QSAR has been proposed and evaluated against results reported by others in terms of final DS composition and model predictive performance.

The set of gene micro-arrays, which consists of two leukemia types, was used as a target to evaluate the efficiency of novel integrated data mining classification process. Discovering the most relevant subset of genes among few thousands of analyzed genes is necessary to get accurate disease classification. Dimensional complexity of the classification process was reduced by a filter based on mutual information feature selection coupled with the support vector machines classifier in the leave-one-out loop. The result was an efficient and reliable tool named MIFS/SVM hybrid. Optimal procedure parameters that enable accurate classification and attribute selection could be determined within an acceptable time frame.