QSAR modeling of aquatic toxicity of aromatic aldehydes using artificial neural network (ANN) and multiple linear regression (MLR)

Department of Pharmacy, Sultan Qaboos University Hospital, PO Box 38, AI Khod, Muscat 123, Oman
E-mail : louisb4425@yahoo.com
QSAR and Computer Chemical Laboratories, A. P. S. University, Rewa-486 003, Madhya Pradesh, India
Manuscript received 06 December 2010, accepted 14 December 2010

 In the present work, quantitative structure-activity relationship analysis (QSAR) to predict the toxic potency of 77 aromatic aldehydes to ciliate Tetralrymeua pyriformis has been investigated by means of multiple linear re11rcssion (MLR) and artificial neural network (ANN). The relationships between structure and toxicity were examined quantitatively using octanol/water partition coefficient (log Kow) encoding hydrophobic and molecular connectivity index depictin11 topological structural features of aldehydes. The data set was split into train and test set and these sets were used to derive statistically robust and predictive (both internally and externally) models. The study demonstrates that both MLR and ANN models have good predictive power but ANN model shows a better statistical parameter in comparison with MILR model.