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

Modern Molecular Taxonomy01:29

Modern Molecular Taxonomy

47
Advancements in molecular biology have revolutionized the identification and characterization of bacteria, with multiple methods leveraging DNA sequencing for enhanced precision. As sequencing technologies improve and costs decline, these approaches are increasingly used in clinical, environmental, and evolutionary studies.Multilocus Sequence Typing (MLST) examines several housekeeping genes, essential chromosomal genes encoding cellular functions, to distinguish strains. Approximately...
47

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

Oral-Gut Microbiome Axis in Crohn's Disease: A Potential Role of Ectopic Colonization.

Microorganisms·2026
Same author

Hybrid Graph-Machine Learning Framework for Accurate and Interpretable Band Gap Prediction.

Journal of chemical information and modeling·2026
Same author

Compact Involutional Transformer for Automated Detection of Pediatric Tooth Number Anomalies on Panoramic Radiographs.

Journal of imaging informatics in medicine·2026
Same author

Reply to Pastore, E.P. Comment on "Korkmaz et al. A Deep Learning and Explainable AI-Based Approach for the Classification of Discomycetes Species. <i>Biology</i> 2025, <i>14</i>, 719".

Biology·2026
Same author

Combination Ensemble and Explainable Deep Learning Framework for High-Accuracy Classification of Wild Edible Macrofungi.

Biology·2025
Same author

A Comparative Analysis of CNN Architectures, Fusion Strategies, and Explainable AI for Fine-Grained Macrofungi Classification.

Biology·2025

相关实验视频

Updated: Jul 16, 2025

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing
11:22

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Published on: October 15, 2019

28.3K

使用基于序列的机器学习分析对人类微生物组进行克罗恩病预测.

Metehan Unal1, Erkan Bostanci1, Ceren Ozkul2

  • 1Department of Computer Engineering, Ankara University, 06830 Ankara, Turkey.

Diagnostics (Basel, Switzerland)
|September 9, 2023
PubMed
概括

机器学习模型可以从人类微生物群序列数据中预测炎症性肠病. 光梯度增强机模型表现最好,证明了早期疾病检测的潜力.

关键词:
机器学习 机器学习生物信息学是一种生物信息学.肠道疾病是一种肠道疾病.我们的微生物群.

更多相关视频

Analysis of Fecal Microbiota Dynamics in Lupus-Prone Mice Using a Simple, Cost-Effective DNA Isolation Method
05:28

Analysis of Fecal Microbiota Dynamics in Lupus-Prone Mice Using a Simple, Cost-Effective DNA Isolation Method

Published on: May 2, 2022

2.2K
Characterization and Functional Prediction of Bacteria in Ovarian Tissues
10:12

Characterization and Functional Prediction of Bacteria in Ovarian Tissues

Published on: October 23, 2021

2.8K

相关实验视频

Last Updated: Jul 16, 2025

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing
11:22

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Published on: October 15, 2019

28.3K
Analysis of Fecal Microbiota Dynamics in Lupus-Prone Mice Using a Simple, Cost-Effective DNA Isolation Method
05:28

Analysis of Fecal Microbiota Dynamics in Lupus-Prone Mice Using a Simple, Cost-Effective DNA Isolation Method

Published on: May 2, 2022

2.2K
Characterization and Functional Prediction of Bacteria in Ovarian Tissues
10:12

Characterization and Functional Prediction of Bacteria in Ovarian Tissues

Published on: October 23, 2021

2.8K

科学领域:

  • 微生物学 微生物学
  • 生物信息学是一种生物信息学.
  • 计算生物学 计算生物学

背景情况:

  • 人类微生物群在健康和疾病中起着至关重要的作用.
  • 机器学习 (ML) 为分析大规模生物数据提供了强大的工具.
  • 从微生物数据预测诸如炎症性肠病 (IBD) 这样的疾病是一个新兴的领域.

研究的目的:

  • 从原始人类微生物群序列数据来评估各种ML技术在预测炎症性肠病 (IBD) 中的有效性.
  • 为了比较七种不同的ML算法的疾病预测性能.
  • 为IBD预测确定最佳的ML模型和数据表示.

主要方法:

  • 利用NCBI数据库中的原始序列数据,转换为结构化图表表示.
  • 应用了七个ML算法:随机森林,支持向量机器,极端梯度增强,光梯度增强机器,高斯天真贝斯,物流回归和k-最近邻居.
  • 使用网格搜索优化了超参数,并使用Mc Nemar的统计显著性测试评估了准确性,精度,f-score,kappa和AUC的模型性能.

主要成果:

  • 光梯度增强机 (LGBM) 模型在不同的k-mer长度中实现了最高的精度:67.24% (k=3),74.63% (k=4) 和76.47% (k=5).
  • 在所有评估的绩效指标中,LGBM的表现始终优于其他模型.
  • 麦克尼马尔的测试证实了各种ML方法在性能上的统计学上显著差异.

结论:

  • 机器学习模型,特别是LightGBM模型,显示出从人类微生物群序列数据直接预测炎症性肠病的显著前景.
  • 该研究强调了使用基于k-mer的序列数据和先进的ML用于非侵入性疾病诊断的潜力.
  • 进一步的研究可以利用这些发现来开发用于早期IBD检测和管理的新型计算工具.