Suppr超能文献

用于触发式药物递送精确预测的深度学习

Deep Learning for the Accurate Prediction of Triggered Drug Delivery.

作者信息

Husseini Ghaleb A, Sabouni Rana, Puzyrev Vladimir, Ghommem Mehdi

出版信息

IEEE Trans Nanobioscience. 2025 Jan;24(1):102-112. doi: 10.1109/TNB.2024.3426291. Epub 2025 Jan 2.

Abstract

The need to mitigate the adverse effects of chemotherapy has driven the exploration of innovative drug delivery approaches. One emerging trend in cancer treatment is the utilization of Drug Delivery Systems (DDSs), facilitated by nanotechnology. Nanoparticles, ranging from 1 nm to 1000 nm, act as carriers for chemotherapeutic agents, enabling precise drug delivery. The triggered release of these agents is vital for advancing this novel drug delivery system. Our research investigated this multifaceted delivery capability using liposomes and metal organic frameworks as nanocarriers and utilizing all three targeting techniques: passive, active, and triggered. Liposomes are modified using targeting ligands to render them more targeted toward certain cancers. Moieties are conjugated to the surfaces of these nanocarriers to allow for their binding to receptors overexpressed on cancer cells, thus increasing the accumulation of the agent at the tumor site. A novel class of nanocarriers, namely metal organic frameworks, has emerged, showing promise in cancer treatment. Triggering techniques (both intrinsic and extrinsic) can be used to release therapeutic agents from nanoparticles, thus enhancing the efficacy of drug delivery. In this study, we develop a predictive model combining experimental measurements with deep learning techniques. The model accurately predicts drug release from liposomes and MOFs under various conditions, including low- and high-frequency ultrasound (extrinsic triggering), microwave exposure (extrinsic triggering), ultraviolet light exposure (extrinsic triggering), and different pH levels (intrinsic triggering). The deep learning-based predictions significantly outperform linear predictions, proving the utility of advanced computational methods in drug delivery. Our findings demonstrate the potential of these nanocarriers and highlight the efficacy of deep learning models in predicting drug release behavior, paving the way for enhanced cancer treatment strategies.

摘要

减轻化疗不良反应的需求推动了对创新药物递送方法的探索。癌症治疗中的一个新兴趋势是利用纳米技术促进的药物递送系统(DDS)。尺寸从1纳米到1000纳米的纳米颗粒充当化疗药物的载体,实现精确的药物递送。这些药物的触发释放对于推进这种新型药物递送系统至关重要。我们的研究使用脂质体和金属有机框架作为纳米载体,并利用被动、主动和触发这三种靶向技术,研究了这种多方面的递送能力。脂质体通过靶向配体进行修饰,使其对某些癌症更具靶向性。部分基团与这些纳米载体的表面结合,使其能够与癌细胞上过度表达的受体结合,从而增加药物在肿瘤部位的积累。一类新型的纳米载体,即金属有机框架,已经出现,在癌症治疗中显示出前景。触发技术(包括内在和外在的)可用于从纳米颗粒中释放治疗药物,从而提高药物递送的效果。在本研究中,我们开发了一个将实验测量与深度学习技术相结合的预测模型。该模型能够准确预测脂质体和金属有机框架在各种条件下的药物释放情况,包括低频和高频超声(外在触发)、微波照射(外在触发)、紫外线照射(外在触发)以及不同的pH水平(内在触发)。基于深度学习的预测明显优于线性预测,证明了先进计算方法在药物递送中的实用性。我们的研究结果证明了这些纳米载体的潜力,并突出了深度学习模型在预测药物释放行为方面的有效性,为改进癌症治疗策略铺平了道路。

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验