The use of self-organising neural networks in dye design

The mapping of molecular surfaces is of particular interest to dye chemists for numerous reasons. none more so than the prediction of dye-substrate bi nding. Self-organising neural networks have been used to map the hydrogen b onding, electrostatic and hydrophobic 3D molecular surface potentials of a series of dyes. The results indicate that the hydrogen bonding potential, t he molecular electrostatic potential and their combination are useful in cl assifying the dyes and that the hydrogen bonding potential is a useful mole cular descriptor of substantivity. (C) 2001 Elsevier Science Ltd. All right s reserved.