Quantitative structure activity relationship study on EC50 of anti-HIV drugs

A quantitative model was developed to predict the EC50 of nucleoside by the gene expression programming (GEP). Each kind of compound was represented by several calculated structural descriptors involving constitutional, topological, geometrical, electrostatic and quantum-chemical features of the compound. The GEP method produced a nonlinear quantitative model of the five-descriptor with a correlation coefficient and a mean error of 0.91 and 0.41 for the training set, 0.63 and 0.67 for the test set, respectively. It is shown that the GEP predicted results are in good agreement with experimental ones, better than those of the support vector machine.