NanoSafety Group, International Iberian Nanotechnology Laboratory, Braga, 4715-330, Portugal.
Instituto di Ricerche Farmacologiche Mario Negri IRCCS, Via Mario Negri 2, Milano, 20156, Italy.
Part Fibre Toxicol. 2023 May 22;20(1):21. doi: 10.1186/s12989-023-00530-0.
The widespread use of new engineered nanomaterials (ENMs) in industries such as cosmetics, electronics, and diagnostic nanodevices, has been revolutionizing our society. However, emerging studies suggest that ENMs present potentially toxic effects on the human lung. In this regard, we developed a machine learning (ML) nano-quantitative-structure-toxicity relationship (QSTR) model to predict the potential human lung nano-cytotoxicity induced by exposure to ENMs based on metal oxide nanoparticles.
Tree-based learning algorithms (e.g., decision tree (DT), random forest (RF), and extra-trees (ET)) were able to predict ENMs' cytotoxic risk in an efficient, robust, and interpretable way. The best-ranked ET nano-QSTR model showed excellent statistical performance with R and Q-based metrics of 0.95, 0.80, and 0.79 for training, internal validation, and external validation subsets, respectively. Several nano-descriptors linked to the core-type and surface coating reactivity properties were identified as the most relevant characteristics to predict human lung nano-cytotoxicity.
The proposed model suggests that a decrease in the ENMs diameter could significantly increase their potential ability to access lung subcellular compartments (e.g., mitochondria and nuclei), promoting strong nano-cytotoxicity and epithelial barrier dysfunction. Additionally, the presence of polyethylene glycol (PEG) as a surface coating could prevent the potential release of cytotoxic metal ions, promoting lung cytoprotection. Overall, the current work could pave the way for efficient decision-making, prediction, and mitigation of the potential occupational and environmental ENMs risks.
新型工程纳米材料（ENMs）在化妆品、电子和诊断纳米器件等行业的广泛应用正在改变我们的社会。然而，新兴研究表明，ENMs 对人类肺部可能具有潜在的毒性作用。在这方面，我们开发了一种机器学习（ML）纳米定量结构-毒性关系（QSTR）模型，以基于金属氧化物纳米粒子预测暴露于 ENMs 后人类肺部纳米细胞毒性的潜在风险。
基于树的学习算法（例如决策树（DT）、随机森林（RF）和 Extra-Trees（ET））能够以高效、稳健和可解释的方式预测 ENMs 的细胞毒性风险。排名最高的 ET 纳米 QSTR 模型在训练、内部验证和外部验证子集中的 R 和 Q 基于指标分别为 0.95、0.80 和 0.79，显示出出色的统计性能。确定了几个与核心类型和表面涂层反应性相关的纳米描述符，作为预测人类肺部纳米细胞毒性的最相关特征。
提出的模型表明，ENMs 直径的减小可能会显著增加它们进入肺部亚细胞区室（例如线粒体和细胞核）的潜在能力，从而促进强烈的纳米细胞毒性和上皮屏障功能障碍。此外，表面涂层中存在聚乙二醇（PEG）可以防止潜在的细胞毒性金属离子释放，从而促进肺部细胞保护。总的来说，这项工作可以为高效的决策制定、预测和减轻潜在的职业和环境 ENMs 风险铺平道路。
