Predictive modeling of nanomaterial biological effects

Abstract

Nanomaterial environmental impact (NEI) modeling is critical for industry and policymakers to assess the unintended biological effects (e.g. mortality, malformation, growth inhibition) resulting from the application of engineered nanomaterials. The scope of NEI modeling covers nanomaterial physical, chemical and manufacturing properties, exposure and study scenarios, environmental and ecosystem responses, biological responses, and their interactions. In this paper, we introduce a data mining approach to modeling the biological effects of nanomaterials. Data mining techniques can assist analysts in developing risk assessment models for nanomaterials. Using an experimental dataset on the toxicity of nanomaterials to embryonic zebrafish, we conducted case studies on modeling the overall effect/impact of nanomaterials and the specific toxic end-points such as mortality, delayed development, and morpholigcal malformations and behavioral abnormalities. The results show that different biological effects have different modeling accuracy given the same set of algorithms and data. The results also show that the weighting scheme for different biological effects has a significant influence on modeling the overall biological effect. These results provide insights into the understanding and modeling of nanomaterial biological effects.