Application of Machine Learning in Nanotoxicology: a Critical Review and Perspective
The massive production and application of nanomaterials (NMs) have raised concerns about the potential adverse effects of NMs on human health and the environment. Evaluating the adverse effects of NMs by laboratory methods is expensive and time-consuming, and often fail to keep pace with the invention of new materials. Therefore, in silico methods that utilize machine learning (ML) techniques to predict the toxicity potentials of NMs become a promising alternative approach. Previous reviews have discussed in detail how to build an in silico predictive model for NMs. Nevertheless, there is still room for improvement in addressing the ways to enhance the model representativeness and performance from different angles, such as dataset curation, descriptor selection, task type (classification/regression), algorithm choice and model evaluation (internal- and external validation, applicability domain and mechanistic interpretation). This review focuses on the above-mentioned aspects to explore how to build better prediction models. The current research state is analyzed based on literature data collection and statistical evaluation, the challenges faced and future perspectives are also summarized. Moreover, a recommended workflow and best practices are provided to help in developing more predictive, reliable and interpretable models that can assist safe-by-design criteria for NMs.