Concerns regarding chronic injuries (e.g., fibrosis and carcinogenesis) induced by nanoparticles raised public health concerns and need to be rapidly assessed in hazard identification. Although in silico analysis is commonly used for risk assessment of chemicals, predicting chronic in vivo nanotoxicity remains challenging due to the intricate interactions at multiple interfaces like nano-biofluids and nano-subcellular organelles. Herein, we develop a multimodal feature fusion analysis framework to predict the fibrogenic potential of metal oxide nanoparticles (MeONPs) in female mice. Treating each nano-bio interface as an independent entity, eighty-seven features derived from MeONP-lung interactions are used to develop a machine learning-based predictive framework for lung fibrosis. We identify cell damage and cytokine (IL-1β and TGF-β1) production in macrophages and epithelial cells as key events closely associated with particle size, surface charge, and lysosome interactions. Experimental validations show that the developed in silico model has 85% accuracy. Our findings demonstrate the potential usefulness of this predictive model for risk assessment of nanomaterials and in assisting regulatory decision-making. While the model is developed based on 52 MeONPs, further validation using a larger nanoparticle library is necessary to confirm its broader applicability.

Key Laboratory of Industrial Ecology and Environmental Engineering School of Environmental Science and Technology Dalian University of Technology Dalian 116024 China

Nanotechnology Centre VSB Technical University of Ostrava Ostrava Poruba 70800 Czech Republic

National Center for Toxicological Research U S Food and Drug Administration Jefferson AR 72079 USA

School of Chemistry and Materials Science Ludong University Yantai 264025 China

School of Public Health Soochow University Suzhou Jiangsu 215123 China

State Key Laboratory of Radiation Medicine and Protection Soochow University Suzhou China

See more in PubMed

Nanotechnology Products Database (NPD). https://product.statnano.com (2023).

Kokot, H. et al. Prediction of chronic inflammation for inhaled particles: the impact of material cycling and quarantining in the lung epithelium. Adv. Mater.32, 2003913 (2020). PubMed

Garcia-Mouton, C., Hidalgo, A., Cruz, A. & Perez-Gil, J. The lord of the lungs: the essential role of pulmonary surfactant upon inhalation of nanoparticles. Eur. J. Pharm. Biopharm.144, 230–243 (2019). PubMed

Liu, S. & Xia, T. Continued efforts on nanomaterial-environmental health and safety is critical to maintain sustainable growth of nanoindustry. Small16, 2000603 (2020). PubMed PMC

Wu, Z. et al. Inflammation increases susceptibility of human small airway epithelial cells to pneumonic nanotoxicity. Small16, 2000963 (2020). PubMed PMC

Zhang, H. et al. Use of metal oxide nanoparticle band gap to develop a predictive paradigm for oxidative stress and acute pulmonary inflammation. ACS Nano6, 4349–4368 (2012). PubMed PMC

Cai, X. et al. Multi-hierarchical profiling the structure-activity relationships of engineered nanomaterials at nano-bio interfaces. Nat. Commun.9, 4416 (2018). PubMed PMC

Li, R. et al. Surface interactions with compartmentalized cellular phosphates explain rare earth oxide nanoparticle hazard and provide opportunities for safer design. ACS Nano8, 1771–1783 (2014). PubMed PMC

Zhu, M. et al. Cell-penetrating nanoparticles activate the inflammasome to enhance antibody production by targeting microtubule-associated protein 1-light chain 3 for degradation. ACS Nano14, 3703–3717 (2020). PubMed PMC

Huang, Y. et al. Quantitative structure-activity relationship models for predicting inflammatory potential of metal oxide nanoparticles. Environ. Health Perspect.128, 67010 (2020). PubMed PMC

Barosova, H. et al. Use of EpiAlveolar lung model to predict fibrotic potential of multiwalled carbon nanotubes. ACS Nano14, 3941–3956 (2020). PubMed

Wang, X. et al. Toxicological profiling of highly purified metallic and semiconducting single-walled carbon nanotubes in the rodent lung and E. coli. ACS Nano10, 6008–6019 (2016). PubMed PMC

Jiang, W. et al. Pro-inflammatory and pro-fibrogenic effects of ionic and particulate arsenide and indium-containing semiconductor materials in the murine lung. ACS Nano11, 1869–1883 (2017). PubMed PMC

Rahman, L. et al. 21st century tools for nanotoxicology: transcriptomic biomarker panel and precision-cut lung slice organ mimic system for the assessment of nanomaterial-induced lung fibrosis. Small16, 2000272 (2020). PubMed

Zhu, M. et al. Comparative study of pulmonary responses to nano- and submicron-sized ferric oxide in rats. Toxicology247, 102–111 (2008). PubMed

Jiang, J. et al. Intracellular dehydrogenation catalysis leads to reductive stress and immunosuppression. Nat. Nanotechnol.10.1038/s41565-025-01870-y. (2025). PubMed

Schraufnagel, D. E. The health effects of ultrafine particles. Exp. Mol. Med.52, 311–317 (2020). PubMed PMC

Oberdorster, C. et al. Principles for characterizing the potential human health effects from exposure to nanomaterials: elements of a screening strategy. Part. Fibre Toxicol.2, 8 (2005). PubMed PMC

Anonymous. The risks of nanomaterial risk assessment. Nat. Nanotechnol.15, 163–163 (2020). PubMed

Choi, J. Y., Ramachandran, G. & Kandlikar, M. The impact of toxicity testing costs on nanomaterial regulation. Environ. Sci. Technol.43, 3030–3034 (2009). PubMed

Yu, F. Wei, C. Deng, P., Peng, T. & Hu, X. Deep exploration of random forest model boosts the interpretability of machine learning studies of complicated immune responses and lung burden of nanoparticles. Sci. Adv.7, eabf4130 (2021). PubMed PMC

Ji, Z. et al. Machine learning models for predicting cytotoxicity of nanomaterials. Chem. Res. Toxicol.35, 125–139 (2022). PubMed

Roy, J. & Roy, K. Assessment of toxicity of metal oxide and hydroxide nanoparticles using the QSAR modeling approach. Environ. Sci. Nano8, 3395–3407 (2021).

Labouta, H. I., Asgarian, N., Rinker, K. & Cramb, D. T. Meta-analysis of nanoparticle cytotoxicity via data-mining the literature. ACS Nano13, 1583–1594 (2019). PubMed

Oh, E. et al. Meta-analysis of cellular toxicity for cadmium-containing quantum dots. Nat. Nanotechnol.11, 479 (2016). PubMed

Cao, J. et al. Computer-aided nanotoxicology: risk assessment of metal oxide nanoparticles via nano-QSAR. Green. Chem.22, 3512–3521 (2020).

Huang, Y. et al. Use of dissociation degree in lysosomes to predict metal oxide nanoparticle toxicity in immune cells: machine learning boosts nano-safety assessment. Environ. Int.164, 107258 (2022). PubMed

Yan, X. L., Sedykh, A., Wang, W. Y., Yan, B. & Zhu, H. Construction of a web-based nanomaterial database by big data curation and modeling friendly nanostructure annotations. Nat. Commun.11, 2519 (2020). PubMed PMC

Ban, Z. et al. Machine learning predicts the functional composition of the protein corona and the cellular recognition of nanoparticles. Proc. Natl Acad. Sci. USA117, 10492–10499 (2020). PubMed PMC

Friedersdorf, L. E., Bjorkland, R., Klaper, R. D., Sayes, C. M. & Wiesner, M. R. Fifteen years of nanoEHS research advances science and fosters a vibrant community. Nat. Nanotechnol.14, 996–998 (2019). PubMed

Wyrzykowska, E. et al. Representing and describing nanomaterials in predictive nanoinformatics. Nat. Nanotechnol.17, 924–932 (2022). PubMed

Tung Xuan, T. et al. Quasi-SMILES-based nano-quantitative structure-activity relationship model to predict the cytotoxicity of multiwalled carbon nanotubes to human lung cells. Chem. Res. Toxicol.31, 183–190 (2018). PubMed

Forest, V. et al. Towards an alternative to nano-QSAR for nanoparticle toxicity ranking in case of small datasets. J. Nanopart. Res.21, 95 (2019).

Gajewicz, A. et al. Towards understanding mechanisms governing cytotoxicity of metal oxides nanoparticles: Hints from nano-QSAR studies. Nanotoxicology9, 313–325 (2015). PubMed

Le, T. C. et al. An experimental and computational approach to the development of ZnO nanoparticles that are safe by design. Small12, 3568–3577 (2016). PubMed

Hansjosten, I. et al. Microscopy-based high-throughput assays enable multi-parametric analysis to assess adverse effects of nanomaterials in various cell lines. Arch. Toxicol.92, 633–649 (2018). PubMed

Puzyn, T. et al. Using nano-QSAR to predict the cytotoxicity of metal oxide nanoparticles. Nat. Nanotechnol.6, 175–178 (2011). PubMed

Mu, Y. et al. Predicting toxic potencies of metal oxide nanoparticles by means of nano-QSARs. Nanotoxicology10, 1207–1214 (2016). PubMed

Boyles, M. S. P. et al. Multi-walled carbon nanotube induced frustrated phagocytosis, cytotoxicity and pro-inflammatory conditions in macrophages are length dependent and greater than that of asbestos. Toxicol. Vitr.29, 1513–1528 (2015). PubMed

Gosens, I. et al. Organ burden and pulmonary toxicity of nano-sized copper (II) oxide particles after short-term inhalation exposure. Nanotoxicology10, 1084–1095 (2016). PubMed PMC

Zhong, S. et al. Machine learning: new ideas and tools in environmental science and engineering. Environ. Sci. Technol.55, 12741–12754 (2021). PubMed

Guan, Y. et al. Pathological comparison of rat pulmonary models induced by silica nanoparticles and indium-tin oxide nanoparticles. Int. J. Nanomed.17, 4277–4292 (2022). PubMed PMC

Chang, X. et al. Nano nickel oxide promotes epithelial-mesenchymal transition through transforming growth factor β1/smads signaling pathway in A549 cells. Environ. Toxicol.35, 1308–1317 (2020). PubMed

Zhang, Y. B., Mo, Y. Q., Zhang, Y., Yuan, J. L. & Zhang, Q. W. MMP-3-mediated cleavage of OPN is involved in copper oxide nanoparticle-induced activation of fibroblasts. Part. Fibre Toxicol.20, 22 (2023). PubMed PMC

Cho, W.-S. et al. Metal oxide nanoparticles induce unique inflammatory footprints in the lung: important implications for nanoparticle testing. Environ. Health Perspect.118, 1699–1706 (2010). PubMed PMC

Presume, M. et al. Exposure to metal oxide nanoparticles administered at occupationally relevant doses induces pulmonary effects in mice. Nanotoxicology10, 1535–1544 (2016). PubMed

Henderson, N. C., Rieder, F. & Wynn, T. A. Fibrosis: from mechanisms to medicines. Nature587, 555–566 (2020). PubMed PMC

OECD. OECD guidelines for the testing of chemicals 90 day (subchronic) inhalation toxicity study. Organisation for Economic Co-operation and Development (OECD) (2018).

Stone, V. et al. A framework for grouping and read-across of nanomaterials- supporting innovation and risk assessment. Nano Today35, 100941 (2020).

Roy, K., Kar, S. & Ambure, P. On a simple approach for determining applicability domain of QSAR models. Chemometr. Intell. Lab. Syst.145, 22–29 (2015).

Cai, X. M. et al. Molecular mechanisms, characterization methods, and utilities of nanoparticle biotransformation in nanosafety assessments. Small16, 19 (2020). PubMed

Chetwynd, A. J. & Lynch, I. The rise of the nanomaterial metabolite corona, and emergence of the complete corona. Environ. Sci. Nano7, 1041–1060 (2020).

Wheeler, K. E. et al. Environmental dimensions of the protein corona. Nat. Nanotechnol.16, 617–629 (2021). PubMed

Liao, C.-M., Chiang, Y.-H. & Chio, C.-P. Assessing the airborne titanium dioxide nanoparticle-related exposure hazard at workplace. J. Hazard. Mater.162, 57–65 (2009). PubMed

Xing, M. et al. Workplace exposure to airborne alumina nanoparticles associated with separation and packaging processes in a pilot factory. Environ. Sci. Process. Impacts17, 656–666 (2015). PubMed

Xing, M. et al. Exposure characteristics of ferric oxide nanoparticles released during activities for manufacturing ferric oxide nanomaterials. Inhal. Toxicol.27, 138–148 (2015). PubMed

Xu, S. et al. Vacancies on 2D transition metal dichalcogenides elicit ferroptotic cell death. Nat. Commun.11, 3484 (2020). PubMed PMC

Wang, Z. Y., Chen, J. W. & Hong, H. X. Developing QSAR models with defined applicability domains on PPARγ binding affinity using large data sets and machine learning algorithms. Environ. Sci. Technol.55, 6857–6866 (2021). PubMed

Casey, W. M. et al. Evaluation and optimization of pharmacokinetic models for in vitro to in vivo extrapolation of estrogenic activity for environmental chemicals. Environ. Health Perspect.126, 097001 (2018). PubMed PMC

Wang, H., Wang, Z., Chen, J. & Liu, W. Graph attention network model with defined applicability domains for screening PBT chemicals. Environ. Sci. Technol.56, 6774–6785 (2022). PubMed

Booth, A. & Jensen, K. A. NANoREG D4.12 SOP probe sonicator calibration for ecotoxicological testing. https://www.rivm.nl/en/documenten/nanoreg-d412-sop-probe-sonicator-calibration-for-ecotoxicological-testing (2018).

Gao, M. et al. Two-dimensional tin selenide (SnSe) nanosheets capable of mimicking key dehydrogenases in cellular metabolism. Angew. Chem. Int. Ed.59, 3618–3623 (2020). PubMed

Zhang, X. et al. Sex-dependent depression-like behavior induced by respiratory administration of aluminum oxide nanoparticles. Int. J. Environ. Res. Public Health12, 15692–15705 (2015). PubMed PMC

Ray, J. L. & Holian, A. Sex differences in the inflammatory immune response to multi-walled carbon nanotubes and crystalline silica. Inhal. Toxicol.31, 285–297 (2019). PubMed PMC

Foot, N. C. The Masson trichrome staining methods in routine laboratory use. Stain Technol.8, 101–110 (1933).

Ashcroft, T., Simpson, J. M. & Timbrell, V. Simple method of estimating severity of pulmonary fibrosis on a numerical scale. J. Clin. Pathol.41, 467–470 (1988). PubMed PMC

Huang, Y. et al. Multimodal Feature Fusion Machine Learning for Predicting Chronic Injury Induced by Engineered Nanomaterials, Github repository. 10.5281/zenodo.14043988 (2025). PubMed

Multimodal feature fusion machine learning for predicting chronic injury induced by engineered nanomaterials