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

Inhibitors of Virion Maturation and Assembly01:19

Inhibitors of Virion Maturation and Assembly

As part of their replication cycle, certain viruses synthesize long precursor proteins called polyproteins within infected host cells. In human immunodeficiency virus (HIV), two major polyproteins are produced: Gag and Gag-Pol. The Gag polyprotein supplies the structural components of the virus, while Gag-Pol includes essential viral enzymes such as reverse transcriptase, integrase, and protease. After synthesis, these polyproteins move to the host cell membrane, where they assemble into an...

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

Structural and dynamic properties of guanosine-analog binding to 2'-deoxyguanosine-II riboswitch: a computational study.

Journal of biomolecular structure & dynamics·2025
Same author

Computational Structural Comparison of Toxoplasma gondii CDPK1 and Human BUB1 kinases: Implications for Selective Inhibitor Design.

ACS omega·2025
Same author

Engineering Protein Dynamics through Mutational Energy Landscape Traps.

Journal of chemical information and modeling·2025
Same author

Characterization of <i>Mycobacterium smegmatis</i> Glutaminase-Free Asparaginase (MSMEG_3173).

ACS omega·2024
Same author

Differences in Charge Distribution in <i>Leishmania tarentolae</i> Leishmanolysin Result in a Reduced Enzymatic Activity.

International journal of molecular sciences·2022
Same author

<i>In silico</i> investigation of riboswitches in fungi: structural and dynamical insights into TPP riboswitches in <i>Aspergillus oryzae</i>.

RNA biology·2022

相关实验视频

Updated: Jun 23, 2026

An Affordable HIV-1 Drug Resistance Monitoring Method for Resource Limited Settings
19:57

An Affordable HIV-1 Drug Resistance Monitoring Method for Resource Limited Settings

Published on: March 30, 2014

19.1K

对HIV-1蛋白酶抑制剂耐药性的基准机器学习模型预测:数据集构造和特征表示的影响.

Rocío Lucía Beatriz Riveros Maidana1,2, Lucas de Almeida Machado3, Ana Carolina Ramos Guimarães1,2

  • 1Laboratório de Genómica Aplicada e Bioinovac̨ões, Instituto Oswaldo Cruz/Fiocruz, Rio de Janeiro 21040-900, Brazil.

Journal of chemical information and modeling
|September 25, 2025
PubMed
概括

评估用于预测HIV-1蛋白酶抑制剂耐药性的机器学习模型显示,数据预处理显著影响性能. 物理化学信息后勤回归模型提供与神经网络相比较的准确性,具有更高的可解释性和效率.

更多相关视频

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
10:29

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors

Published on: May 9, 2025

2.2K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K

相关实验视频

Last Updated: Jun 23, 2026

An Affordable HIV-1 Drug Resistance Monitoring Method for Resource Limited Settings
19:57

An Affordable HIV-1 Drug Resistance Monitoring Method for Resource Limited Settings

Published on: March 30, 2014

19.1K
Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
10:29

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors

Published on: May 9, 2025

2.2K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K

科学领域:

  • * 计算生物学和生物信息学
  • * 机器学习在药物发现中的作用
  • * 病毒传染病和抵抗机制

背景情况:

  • * 病毒感染中的耐药性,特别是HIV-1病毒,构成了全球主要的健康威胁.
  • *机器学习 (ML) 模型越来越多地用于从基因组数据中预测抗病毒药物耐药性.
  • *HIV-1蛋白酶抑制剂 (PI) 是一种关键的治疗方法,因此对抗性的预测至关重要.

研究的目的:

  • * 系统地评估现有的ML模型来预测HIV-1PI耐药性.
  • * 评估不同数据预处理策略对模型性能的影响.
  • * 提出和验证一种新的,严格的方法来评估模型通用性.

主要方法:

  • *在三个不同的HIV-1蛋白酶数据集上比较了各种ML模型 (神经网络,随机森林,KNN,逻辑回归).
  • *研究了不同的预处理技术,包括模两可的序列处理和数据扩展.
  • *采用zScales物理化学描述符和Rosetta能量术语作为模型特征.
  • * 实施基于集群的验证方法,以进行可靠的概括性评估.

主要成果:

  • *数据扩展预处理通过引入冗余性来人工膨胀性能指标.
  • *基于集群的验证提供了对模型通用性的更严格,更可靠的评估.
  • * 基于物理化学信息的逻辑回归模型 (zScales LR,Rosetta LR) 实现了与复杂神经网络相当的性能.
  • *zScales LR在罗塞塔LR的计算效率和解释性方面表现出了卓越的优势.
  • * 相互信息分析确定了不同的阻力机制:zScales突出了特定的热点,而罗塞塔则揭示了相互连接的能量网络.

结论:

  • * 数据集的构造和预处理选择极大地影响了在阻力预测中明显的ML模型性能.
  • *精心选择的物理化学特征可以产生准确和可解释的HIV-1 PI耐药性模型,与复杂的神经网络相竞争.
  • * 拟议的基于集群的验证和物理化学特征表示提供了一个强大的框架,用于开发临床相关的耐药性预测工具.