DRIVING-FORCE PREDICTION FOR INCLUSION COMPLEXATION OF ALPHA-CYCLODEXTRIN WITH BENZENE-DERIVATIVES BY A WAVELET NEURAL-NETWORK

A wavelet neural network (WNN) has been constructed and used to predic t the binding constant for the inclusion of alpha-cyclodextrin with be nzene derivatives from the substituent molar refraction (R-m) and hydr ophsbic constant (pi). The In K-a values predicted by WNN from R-m and pi are close to the experimental data. The results indicate that the inclusion complexation of alpha-cyclodextrin with mono- and 1,4-disubs tituted benzene is dominantly driven by the van der Waals force and hy drophobic interactions. (C) 1998 Elsevier Science B.V. All rights rese rved.