Nanotechnology is an emerging field of science and engineering that has already been applied to a variety of industrial fields. Given the ever increasing use of engineered nanomaterials (ENMs) in industry, it is essential to properly assess all potential risks that may occur as a result of exposure to ENMs. It is generally agreed that the distinctive characteristics of ENMs that have made them superior to bulk materials for particular applications might also have a substantial impact on the level of risk they pose. Despite the clear benefits that nanotechnology can bring to various sectors of industry, there are serious concerns about the potential health risks associated with the production and use of engineered nanomaterials ENMs, intensified by the limited understanding of what makes ENMs toxic and how to make them safe.<br/>The involvement of computational specialists in nano-safety research has become more prominent since REACH regulation promoted the use of in silico techniques, such as quantitative structure-activity relationship (QSAR), for the purpose of toxicity assessment. It is now widely recognised that data-driven models that decode the relationships between the biological activities of ENMs and their physicochemical characteristics provide an attractive means of maximising the value of scarce and expensive experimental nanotoxicity data.<br/>As the field of nanotoxicology is still in its infancy, the use of predictive approaches in the risk assessment of ENMs is correspondingly recent. New computational modelling tools or new ways of using existing tools are required to model the relatively sparse and sometimes lower quality data on the biological effects of ENMs. The most commonly used QSAR modelling methods work best with large data sets, but are not particularly good at feature selection, and may not account for non-linearity in the structure-property relationships. To overcome these limitations, we describe the application of a novel algorithm, a genetic programming-based decision tree construction tool (GPTree) to ENM toxicity modelling and demonstrate its potential in QSAR modelling of ENM toxicity by a number of case studies. GPTree is a robust, automatic method for the generation of accurate nano-(Q)SAR models with additional advantages that it works with small datasets, automatically selects descriptors, and provides improved interpretability of models.

Accurate and interpretable nanoQSAR models from genetic programming-based decision tree construction approaches

254th National Meeting (2017)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.