An accurate nonlinear QSAR model for the antitumor activities of chloroethylnitrosoureas using neural networks

The quantitative structure–activity relationship (QSAR) studies are investigated in a series of chloroethylnitrosoureas (CENUs) acting as alkylating agents of tumors by neural networks (NNs). The QSAR model is described inaccurately by the traditional multiple linear regression (MLR) model for the substitution of CENUs at N-3, whose characteristics play key roles in the biological activity. A nonlinear QSAR study is undertaken by a three-layered NN model, using molecular descriptors that are known to be responsible for the antitumor activity to optimize the input variables of the MLR model. The results demonstrate that NN models present the relationship between antitumor activity and molecular descriptors clearly, and they yield predictions in excellent agreement with the experiment's obtained values (R2 = 0.983). The R2 value is 0.983 for the 5-8-1 NN model, compared with 0.506 for the MLR model, and the nonlinear model is able to account for 98.3% of the variance of antitumor activities.

Figure optionsDownload high-quality image (76 K)Download as PowerPoint slideResearch highlights
► We establish linear and nonlinear QSAR models to study antitumor activity of chloroethylnitrosoureas.
► We examine the linear MLR model based on the selected five molecular descriptors.
► The mean of these descriptors is also interpreted.
► The nonlinear NN models are generated using the five descriptors as their inputs.
► The results show that the 5-8-1 NN model has higher accuracy than others and nonlinear models can be reliable for the design of new antitumor drugs.