Predicting the acute toxicity of a large dataset of diverse chemicals against fathead minnows (Pimephales promelas) is challenging. In this paper, 963 organic compounds with acute toxicity towards fathead minnows were split into a training set (482 compounds) and a test set (481 compounds) with an approximate ratio of 1 : 1. Only six molecular descriptors were used to establish the quantitative structure–activity/toxicity relationship (QSAR/QSTR) model for 96 hour pLC₅₀ through a support vector machine (SVM) along with genetic algorithm. The optimal SVM model (R² = 0.756) was verified using both internal (leave-one-out cross-validation) and external validations. The validation results (q_int ² = 0.699 and q_ext ² = 0.744) were satisfactory in predicting acute toxicity in fathead minnows compared with other models reported in the literature, although our SVM model has only six molecular descriptors and a large data set for the test set consisting of 481 compounds.

A four-descriptor quantitative structure–property relationship model was constructed to predict 65 intrinsic viscosities [η] of polymer solutions. Four quantum chemical descriptors, the traceless quadrupole moment θ_(R), the hydrogen bond or electrostatic attraction descriptor Q_H, the partition function Q_BOT(R) and the frontier orbital descriptor E_HOMO, were calculated with density functional theory at the B3LYP/6-31G(d) level and used to develop the model by multivariate linear regression (MLR) analysis. The model possesses coefficients of determination r² of 0.827 for the training set and 0.808 for the test set, and shows better statistical characteristics than the existing MLR models of intrinsic viscosities [η] of polymer–solvent combinations. Moreover, the four descriptors were used to develop a support vector machine model for [η] that possesses a coefficient of determination r² of 0.911 for the whole data set.

Pesticide usage reaches several million metric tons annually worldwide, and the effects of pesticides on non-target species, such as various fishes in aquatic environments, have resulted in serious concerns. Predicting pesticide aquatic toxicity to fish is of great significance. In this paper, 20 molecular descriptors were successfully used to develop a regression quantitative structure-activity/toxicity relationship (QSAR/QSTR) model for the toxicity logLC50 of a large data set consisting of 1106 pesticides on fishes by using a general regression neural network (GRNN) algorithm. The optimal GRNN model produced correlation coefficients R of 0.8901 (rms = 0.6910) for the training set, 0.8531 (rms = 0.7486) for the validation set, and 0.8802 (rms = 0.6903) for the test set, which are satisfactory compared with other models in the literature, although a large data set of toxicity logLC50 was used in this work.