Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources

Abstract

A generalized toxicity classification model for 7 different oxide nanomaterials is presented in this study. A data set extracted from multiple literature sources and screened by physicochemical property based quality scores were used for model development. Moreover, a few more preprocessing techniques, such as synthetic minority over-sampling technique, were applied to address the imbalanced class problem in the data set. Then, classification models using four different algorithms, such as generalized linear model, support vector machine, random forest, and neural network, were developed and their performances were compared to find the best performing preprocessing methods as well as algorithms. The neural network model built using the balanced data set was identified as the model with best predictive performance, while applicability domain was defined using k-nearest neighbours algorithm. The analysis of relative attribute importance for the built neural network model identified dose, formation enthalpy, exposure time, and hydrodynamic size as the four most important attributes. As the presented model can predict the toxicity of the nanomaterials in consideration of various experimental conditions, it has the advantage of having a broader and more general applicability domain than the existing quantitative structure-activity relationship model.

Comprehensive ensemble in QSAR prediction for drug discovery

“…As illustrated in Fig. 4 of the preprocessing step, the input SMILES strings were preprocessed with onehot encoding [44][45][46], which sets only the correspond-ing symbol to 1 and others to 0. The input is truncated/padded to a maximum length of 100.…”

A health concern regarding the protein corona, aggregation and disaggregation

“…Also, Manganelli, Leone, Toropov, Toropova and Benfenati [115] designed a QSAR model that accurately predicts the human embryonic kidney cells (HEK293) response in the presence of 20 to 50 nm silica NPs. In another study based on the QSAR model and the 7 types of oxide NPs, it was shown that increasing the measured properties of NPs, especially the nanoparticle network model, the dosage, the enthalpy of formation, the exposure time and the hydrodynamic size, could increase the prediction level of the model by more than 90% [116]. The greater surface area of NPs results in their high chemical activity and subsequent enhanced reactive oxygen species (ROS) production causing oxidative stress, inflammation [117,118].…”

Nano-(Q)SAR for Cytotoxicity Prediction of Engineered Nanomaterials

“…Classification models for six different metal oxides and SiO 2 were presented in [57]. The authors compared the performance of four different algorithms: Generalized linear model, SVM, RF, and neural network.…”

“…The neural network model was identified as the model with the best predicting ability. The analysis of relative descriptor importance for the built neural network model identified dose, formation enthalpy, exposure time, and hydrodynamic size as the four most important descriptors [57]. However, the advantage of regression models for the analysis of toxicity of NPs was shown in comparison with the classification models on metal NPs and metal oxide NPs [58]: Regression models allow not only qualitative, but also a quantitative evaluation of the studied nanomaterials.…”