纳米技术和机器学习协同提高膳食多酚的生物利用度和功能功效
Nanotechnology and machine learning synergies for improving the bioavailability and functional efficacy of dietary polyphenols.
摘要(中文译文)
膳食多酚具有多种生物活性，但由于溶解度低、代谢迅速和吸收受限导致的生物利用度差，其临床应用受到限制。本综述系统总结了基于纳米载体的策略在改善膳食多酚递送方面的最新进展。分析了四种代表性纳米载体类型，包括脂质体、固体脂质纳米粒、纳米混悬液和聚合物胶束。我们讨论了其理化性质和界面相互作用如何增强溶解度、稳定性和靶向递送，同时也指出了潜在毒性、有限载药量和制剂复杂性等局限性。本综述的一个关键焦点是将机器学习（ML）整合到纳米载体设计中以优化性能。支持向量机、随机森林和XGBoost等监督模型在包封率、释放动力学和生物分布方面实现了高预测准确性。机器学习进一步实现了高通量筛选、毒性预测和制剂的迭代优化，提高了膳食多酚递送的有效性和安全性。机器学习驱动的多组学数据整合为纳米载体、多酚和生物系统之间的相互作用提供了机制性见解，支持生物标志物发现和精准递送。此外，我们提出了一个整合纳米技术和机器学习的逐步工作流程，以指导膳食多酚制剂的合理开发。最后，我们讨论了当前面临的挑战，包括数据异质性、模型可解释性和监管考量，并概述了推进机器学习驱动的纳米载体策略以实现高效膳食多酚递送的未来方向。总之，本综述提供了一个全面的框架，并强调了整合纳米技术和机器学习在设计下一代功能食品和精准营养方面的独特贡献。
Abstract
Dietary polyphenols exhibit diverse bioactivities, but their clinical application is limited by poor bioavailability due to low solubility, rapid metabolism, and restricted absorption. This review systematically summarizes recent advances in nanocarrier-based strategies for improving dietary polyphenol delivery. Four representative nanocarrier types are analyzed, including liposomes, solid lipid nanoparticles, nanosuspensions, and polymeric micelles. We discuss how their physicochemical properties and interfacial interactions enhance solubility, stability, and targeted delivery, while also highlighting limitations such as potential toxicity, limited loading capacity, and formulation complexity. A key focus of this review is the integration of machine learning (ML) into nanocarrier design to optimize performance. Supervised models such as support vector machines, random forests, and XGBoost achieve high predictive accuracy for encapsulation efficiency, release kinetics, and biodistribution. ML further enables high-throughput screening, toxicity prediction, and iterative refinement of formulations, improving the efficacy and safety of dietary polyphenol delivery. ML-driven integration of multi-omics data provides mechanistic insights into interactions among nanocarriers, polyphenols, and biological systems, supporting biomarker discovery and precision delivery. Additionally, we present a stepwise workflow that integrates nanotechnology and ML to guide the rational development of dietary polyphenol formulations. Finally, we discuss current challenges, including data heterogeneity, model interpretability, and regulatory considerations, and outline future directions to advance ML-driven nanocarrier strategies for efficient dietary polyphenol delivery. In conclusion, this review provides a comprehensive framework and highlights the unique contribution of integrating nanotechnology and ML for designing next-generation functional foods and precision nutrition.
如何引用
AMA
Wenze Wu, Bo Mei, Yongzi Wu, Linge Liu, Yichen Wang, Mauro Lombardo, et al. Nanotechnology and machine learning synergies for improving the bioavailability and functional efficacy of dietary polyphenols.. Food research international (Ottawa, Ont.). 2026; doi:10.1016/j.foodres.2026.118499.
APA
Wenze Wu, Bo Mei, Yongzi Wu, Linge Liu, Yichen Wang, Mauro Lombardo, et al (2026). Nanotechnology and machine learning synergies for improving the bioavailability and functional efficacy of dietary polyphenols.. Food research international (Ottawa, Ont.). https://doi.org/10.1016/j.foodres.2026.118499
GB/T 7714
Wenze Wu, Bo Mei, Yongzi Wu, Linge Liu, Yichen Wang, Mauro Lombardo, et al. Nanotechnology and machine learning synergies for improving the bioavailability and functional efficacy of dietary polyphenols.[J]. Food research international (Ottawa, Ont.), 2026 doi:10.1016/j.foodres.2026.118499.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出