Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Anomalous Diffusion of Nanoparticles in Semidilute Hyaluronic Acid Solutions.

Biomacromolecules·2026
Same author

Effects of different mixing techniques on mRNA lipid nanoparticle physicochemistry and biological performance.

Nature communications·2026
Same author

American Life in Realtime: Benchmark, publicly available person-generated health data for equity in precision health.

PNAS nexus·2025
Same author

Physics-Informed Neural Network-Based Inverse Framework for Time-Fractional Differential Equations for Rheology.

Biology·2025
Same author

Limit of Detection of Raman Spectroscopy Using Polystyrene Particles from 25 to 1000 nm in Aqueous Suspensions.

Analytical chemistry·2025
Same author

Hyperspectral enhanced imaging analysis of nanoparticles using machine learning methods.

Nanoscale advances·2024

相关实验视频

Updated: May 20, 2025

Formulating and Characterizing Lipid Nanoparticles for Gene Delivery using a Microfluidic Mixing Platform
09:41

Formulating and Characterizing Lipid Nanoparticles for Gene Delivery using a Microfluidic Mixing Platform

Published on: February 25, 2021

22.7K

机器学习框架预测脂纳米颗粒的性能,以提供核酸.

Gaurav Kumar1, Arezoo M Ardekani1

  • 1School of Mechanical Engineering, Purdue University, West Lafayette, Indiana 47907, United States.

ACS applied bio materials
|April 23, 2025
PubMed
概括

机器学习模型预测脂质纳米粒子 (LNP) 活性和基因治疗的可行性. 该框架通过识别关键特征和弥合体外-体内生物预测差距,使得合理的LNP设计成为可能.

科学领域:

  • 纳米医学是一种纳米医学.
  • 计算化学的计算化学
  • 生物技术是生物技术.

背景情况:

  • 脂质纳米颗粒 (LNP) 对于基因疗法如mRNA和siRNA传递至关重要.
  • 定量结构-活动关系 (QSAR) 建模对于LNP制定至关重要,但由于复杂的组成和相互作用而面临挑战.
  • 预测LNP性能需要复杂的方法来处理多组件系统和生物变异性.

研究的目的:

  • 开发一种机器学习 (ML) 框架,用于预测核酸输送中的LNP活动和细胞活力.
  • 为了克服复杂LNP配方的传统QSAR建模的局限性.
  • 建立一个可扩展的方法来预测LNP性能和指导合理设计.

主要方法:

  • 策划了来自21项研究的6454种LNP配方的数据集.
  • 采用了11种分子特征化技术和6种ML算法进行分类.
  • 使用基于支架的5倍交叉验证和SHAP进行特征归属.
  • 开发了一种转移学习策略,以弥合体外-体内生物预测差距.

主要成果:

  • 在使用ML模型预测LNP活动和细胞活力方面取得了>90%的准确性.
  • 基于描述器的特征与集成模型 (随机森林,额外的树木) 显示出最高的性能.
关键词:
活动活动活动活动活动活动.细胞活力细胞的活力.脂质纳米颗粒的使用方法机器学习是机器学习.分子描述器 分子描述器随机的森林随机的森林结构 - 活动关系关系.

更多相关视频

Testing the In Vitro and In Vivo Efficiency of mRNA-Lipid Nanoparticles Formulated by Microfluidic Mixing
08:55

Testing the In Vitro and In Vivo Efficiency of mRNA-Lipid Nanoparticles Formulated by Microfluidic Mixing

Published on: January 20, 2023

10.8K
Author Spotlight: Enhancing Lipid Nanoparticle Formation Through Turbulent Mixing in Confined Geometries
08:10

Author Spotlight: Enhancing Lipid Nanoparticle Formation Through Turbulent Mixing in Confined Geometries

Published on: August 23, 2024

3.1K

相关实验视频

Last Updated: May 20, 2025

Formulating and Characterizing Lipid Nanoparticles for Gene Delivery using a Microfluidic Mixing Platform
09:41

Formulating and Characterizing Lipid Nanoparticles for Gene Delivery using a Microfluidic Mixing Platform

Published on: February 25, 2021

22.7K
Testing the In Vitro and In Vivo Efficiency of mRNA-Lipid Nanoparticles Formulated by Microfluidic Mixing
08:55

Testing the In Vitro and In Vivo Efficiency of mRNA-Lipid Nanoparticles Formulated by Microfluidic Mixing

Published on: January 20, 2023

10.8K
Author Spotlight: Enhancing Lipid Nanoparticle Formation Through Turbulent Mixing in Confined Geometries
08:10

Author Spotlight: Enhancing Lipid Nanoparticle Formation Through Turbulent Mixing in Confined Geometries

Published on: August 23, 2024

3.1K
  • 通过SHAP分析确定了推动LNP性能的主要物理化学和组成特征.
  • 转移学习模型在体外到体外预测方面实现了>82%的准确性.

    • 结论:

    • 可解释的ML框架可以指导基因治疗的合理LNP设计.
    • 开发的ML框架为纳米医学的QSAR建模提供了一个可扩展的方法.
    • 分子特征的协同效应对LNP性能至关重要.