Structure-toxicity relationships study of a series of organophosphorus insecticides

Abstract

Structure-toxicity relationships were studied for a set of 47 insecticides by means of multiple linear regression (MLR) and artificial neural network (ANN). A model with three descriptors, including shape surface [S(R2)], hydrogen-bonding acceptors [HBA(R2)] and molar refraction [MR(R1)], showed good statistics both in the regression (r = 0.875, s = 0.417 and q2 = 0.675) and artificial neural network model with a configuration of [3-5-1] (r = 0.966, s = 0.200 and q2 = 0.647). The statistics for the prediction on toxicity [log LD50 (lethal dose 50, oral, rat)] in the test set of 20 organophosphorus insecticides derivatives is (r = 0.849, s = 0.435) and (r = 0.748, s = 0.576) for MLR and ANN respectively. The model descriptors indicate the importance of molar refraction and shape contributions toward toxicity of organophosphorus insecticides derivatives used in this study. This information is pertinent to the further design of new insecticides.

Genetic neural network modeling of the selective inhibition of the intermediate-conductance Ca2+-activated K+ channel by some triarylmethanes using topological charge indexes descriptors

“…These results are expectable since several previous reports demonstrated that when ANNs were trained with variables selected by linear search routines, the networks largely overcame linear models by increasing data fitting but the predictors did not exhibit a remarkable improvement in predictive power [15,17,20,46]. In such cases ANNs were able to learn the data very well but they were not stable enough predicting the activity of newer compounds presented to the networks.…”

Evaluation of a neural networks QSAR method based on ligand representation using substituent descriptors

“…Similar substituent-based schemes have been successfully used for input encoding in NN-based methods: QSPR applications predicting the toxicity of organophosphorus insecticides [71] and in QSAR applications on a set of benzodiazepines used in treatment of anxiety and emotional disorders [72], or on analogues of the hept inhibitors of HIV-1 reverse transcriptase [73].…”

ANN and MLR Model of Specific Fuel Consumption for Pyrolysis Oil Blended with Diesel used in a Single Cylinder Diesel Engine: A Comparative Study

“…Target data files include targets (normalized measured shear stress values respectively of input data sets) for training, validation and testing data sets. The work in this paper included a function approximation or prediction problem that required the final error to be reduced to a very small value [7,8]. The training stopped after 1000 epochs because the validation error increased.…”