Abstract: Some molecules can formaggregates in solution that may inhibit several enzymes, known as promiscuous inhibitors. This phenomenon has been found in traditional Chinese medicinal recipes. To study the aggregation, classification model was constructed by the support vector machine (SVM) classifier. The results indicated that this classification model had good stability and good prediction performance. The experimental results had showed that this predicted model had good generalization. The model was also used to predict the molecules in the Chinese herbal drugs database (CHDD) for further research.

Key words: Aggregation, Classification, Support vector machine