Predicting and investigating cytotoxicity of nanoparticles by translucent machine learning
| Autor: | Hengjie Yu, Fang Cheng, Zhilin Zhao |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Environmental Engineering
Computer science Health Toxicology and Mutagenesis 0208 environmental biotechnology Engineered nanomaterials Metal Nanoparticles 02 engineering and technology Metal oxide nanoparticles 010501 environmental sciences Causal structure Machine learning computer.software_genre 01 natural sciences Model validation Interpretation (model theory) Machine Learning Feature (machine learning) Environmental Chemistry 0105 earth and related environmental sciences business.industry Public Health Environmental and Occupational Health Oxides General Medicine General Chemistry Pollution Engineered nanoparticles 020801 environmental engineering Nanoparticles Artificial intelligence Model interpretation business computer |
| Zdroj: | Chemosphere. 276:130164 |
| ISSN: | 0045-6535 |
| DOI: | 10.1016/j.chemosphere.2021.130164 |
| Popis: | Safety concerns of engineered nanoparticles (ENPs) hamper their applications and commercialization in many potential fields. Machine learning has been proved as a great tool to understand the complex ENP-organism-environment relationship. However, good-performance machine learning models usually exist as black boxes, which may be difficult to build trust and whose ways of expressing knowledge rarely directly map to forms familiar to scientists. Here, we present an approach for uncovering causal structure in nanotoxicity datasets by mutual-validated and model-agnostic interpretation methods. Model predictions can be explained from feature importance, feature effects, and feature interactions. The utility of this approach is demonstrated through two case studies, the cytotoxicity of cadmium-containing quantum dots and metal oxide nanoparticles. Further, these case studies indicate the efficacy and impacts at two scales: (i) model interpretation, where the most relevant features for correlating cytotoxicity are identified and their influence on model predictions and interactions with other features are then explained, and (ii) model validation, where the difference among interpretation results of different methods (or the difference between interpretation results and well-known toxicity mechanisms) may reflect some inherent problems in the used dataset (or the developed models). Our approach of integrating machine learning models and interpretation methods provides a roadmap for predicting the toxicity of ENPs in a translucent way. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect