用机器学习预测纳米颗粒毒性，关键看尺寸和表面特性。
AI and Machine Learning Approaches for Predicting Nanoparticles Toxicity The Critical Role of Physiochemical Properties
- 基于物理化学属性构建决策树、随机森林等模型。
- 氧原子含量、粒径、比表面积与毒性显著相关。
- 适合材料安全评估与药物研发人员参考。
本研究探讨人工智能与机器学习在预测纳米颗粒毒性中的应用，该问题因纳米材料广泛应用于各行业且其生物相互作用难以评估而尤为紧迫。采用决策树、随机森林及XGBoost等模型，分析粒径、形状、表面电荷与化学成分等理化性质对毒性的影响。研究发现，氧原子含量、颗粒尺寸、比表面积、剂量及暴露时间对毒性水平具有显著影响。机器学习能更精准捕捉这些属性在生物环境中的复杂关联，相较于传统方法具备更高的效率与预测能力。该方法有助于通过计算化学开发更安全的纳米材料，减少对昂贵耗时实验的依赖。研究成果不仅深化了对纳米颗粒生物行为的理解，也优化了安全评估流程，推动计算技术在纳米毒理学中的应用进展。
原文摘要 · Abstract (English)
This research investigates the use of artificial intelligence and machine learning techniques to predict the toxicity of nanoparticles, a pressing concern due to their pervasive use in various industries and the inherent challenges in assessing their biological interactions. Employing models such as Decision Trees, Random Forests, and XGBoost, the study focuses on analyzing physicochemical properties like size, shape, surface charge, and chemical composition to determine their influence on toxicity. Our findings highlight the significant role of oxygen atoms, particle size, surface area, dosage, and exposure duration in affecting toxicity levels. The use of machine learning allows for a nuanced understanding of the intricate patterns these properties form in biological contexts, surpassing traditional analysis methods in efficiency and predictive power. These advancements aid in developing safer nanomaterials through computational chemistry, reducing reliance on costly and time-consuming experimental methods. This approach not only enhances our understanding of nanoparticle behavior in biological systems but also streamlines the safety assessment process, marking a significant stride towards integrating computational techniques in nanotoxicology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。