QSPR study for the prediction of UV maximum absorption wavelength of coumarins by heuristic method and radial basis function neural network

In an attempt to develop predictive tools for the determination of the UV maximum absorption wavelength (λ_max), QSPR models for λ_max of 50 coumarins were developed based on their structures alone. A six-descriptor linear correlation by heuristic method (HM) and a non-linear model using radial basis function neural network (RBFNN) approach were reported. The statistical parameters provided by the HM model (R² =0.899 F=48.830, RMS=5.159 for the training set and R² =0.897 F=70.025, RMS=4.143 for the test set) and the RBFNN model (R²=0.926, F=475.097, RMS =4.010 for the training set, and R²=0.801, F=32.108, RMS=6.729 for the test set) indicated satisfactory stability and predictive ability.