Classification models for anticancer activity

Despite significant research in understanding of neoplastic diseases, the success rate for oncology drugs is relatively very low. A major challenge before the scientific community is to design new chemical entities that will be highly selective for cancer cells so as to minimize side effects. Classification models (CMs) models play a prominent role in prediction of the biological properties of newly designed compounds before their synthesis and prevent non-optimal use of resources. Though correlation models far outnumber classification models for development of various therapeutic agents but the significance of classification models for development of anti-cancer agents can not be underestimated. Various techniques employed for development of classification models for anti-cancer activity have been briefly reviewed. Moreover, successful use of some of these classification techniques for the development of models for anti-proliferative activity has been illustrated using a data set comprising of 53 analogues of N-Benzoylated phenoxazines and phenothiazines. Resulting classification models with high degree of accuracy can play a vital role in providing lead structures for the development of novel anti-proliferative agents for cancer chemotherapy.