Machine learning as a tool to analyze biological responses to nanomaterials

Xiangang Hu

College of Environmental Science and Engineering, Nankai University, Tianjin China, 300350

EXTENDED ABSTRACT: The development of machine learning provides solutions for predicting the complicated immune responses and pharmacokinetics of nanoparticles (NPs) in vivo, which is critical to the effective design and safe applications of NPs in various fields (e.g., cancer treatment and drug delivery). However, highly heterogeneous data in NP studies remain challenging due to the low interpretability of machine learning. Here, we propose a tree-based random forest feature importance and feature network interaction analysis framework (TBRFA) and accurately predict the pulmonary immune responses and lung burden of NPs, with the correlation coefficient of all training sets > 0.9 and half of the test sets > 0.75. This framework overcomes the feature importance bias brought by small datasets through a multiway importance analysis. TBRFA also builds feature interaction networks that are difficult to identify by machine learning, boosts model interpretability and reveals hidden interactional factors (e.g., various NP properties and exposure conditions). TBRFA provides guidance for the design and application of ideal NPs and discovers the feature interaction networks that contribute to highly complex systems with small-size data, such as human diseases.  

REFERENCES

1.F. Yu, C. Wei, P. Deng, et al. Sci. Adv. 2021, 7 (22): 4130. 

2.Z. Ban, P. Yuan, F. Yu, et al. P. Natl. Acad. Sci. USA. 2020, 17(19): 10492-10499. 

3.T. Shi, X. Hou, S. Guo, et al. Nat. Commun. 2021, 12:493.