Using molecular representations in combination with neural networks. A case study: Prediction of the HPLC retention index

Factorial design in isocratic high-performance liquid chromatography of phenolic compounds

A multifactor optimization strategy was utilized to predict the isocratic HPLC separation of nine phenols. The retention behavior was studied as a function of changing eluent (methanol ? acetic acid) composition. The predicted and measured retentions are in rather good agreement. To locate the optimum in the factor space, the normalized resolution product criterion was applied. In virtually every case, the resolution is limited by the separation of the 2-chlorophenol and 2,4-dinitrophenol pair.

Application of neural networks in structure-activity relationships

Methodology and application of artificial neural networks in structure-activity relationships are reviewed focusing on the most frequently used three-layer feedforward back-propagation procedure. Two applications of neural networks are presented and a comparison of the performance with those of CoMFA and a classical QSAR analysis is also discussed.