[The application of artificial neural network in QSAR research of PCDD]

The study of QSAR between molecular structure and retention behavior of solutes is an important topic of chromatographic basic theory. PCDD (polychlorinated dioxin) is a kind of important environmental toxin. The basic skeleton of PCDD is [symbol: see text]. PCDDs are all chlorine substituted, so they are only different from each other in the number and position of chlorine substitutents on the skeleton. There are 76 kinds of homologues (1 to 8 chlorine substituent) for 3, 4, 5 and 6 chlorine substituted compounds including more than ten kinds of isomerides. In this paper, the description of molecular structure and feature selection have been investigated. Artificial neural network (ANN) is used to relate the molecular structure and retention time of PCDD. The predicted results of 49 PCDDs retention time by ANN are listed. It was shown that as to the relative error more than 95% data was less than 10% and more than 80% data was less than 5%.