Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Mismatch Repair

Mismatch Repair

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

Unsupervised clustering FLIM-phasor from multifunctionalized nanoparticles in living cancer cells.

Methods and applications in fluorescence·2026

Same author

Crossing thermal limits: functional collapse of the surfgrass Phyllospadix scouleri under simulated extreme marine heatwave.

Journal of experimental botany·2026

Same author

Cultivation potential of the tropical carrageenophyte Eucheumatopsis isiformis (Solieriaceae, Rhodophyta) from Yucatán, Mexico.

PloS one·2026

Same author

Guava (Psidium guajava L.) leaf extract improves the prognosis of nonalcoholic fatty liver and biochemical parameters in rats with metabolic syndrome.

Journal of complementary & integrative medicine·2025

Same author

Whole-Genome Sequence Analysis to Assess Mutations in Efflux Pumps in <i>Mycobacterium tuberculosis</i>: The Influence in Drug Resistance.

Microorganisms·2025

Same author

Zika Virus Infection in Asymptomatic Pregnant Women.

Infectious disease reports·2025

Search research articles

相关实验视频

Updated: May 28, 2025

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Published on: April 25, 2014

预测Mycobacterium结核病的耐药性:一种机器学习方法来分析基因组突变.

Guillermo Paredes-Gutierrez¹, Ricardo Perea-Jacobo^1,2, Héctor-Gabriel Acosta-Mesa³

¹Facultad de Ingeniería Arquitectura y Diseño, Universidad Autónoma de Baja California, Campus Ensenada, Ensenada 22860, Mexico.

Diagnostics (Basel, Switzerland)

|February 13, 2025

概括

机器学习使用基因组数据准确预测结核病 (TB) 的耐药性. 极端梯度增强分类器 (XGBC) 模型在识别对关键结核病药物耐药性的高性能.

关键词:

结核病菌菌菌的结核病菌的结核病菌.药物耐药性耐药性药物耐药性极端的梯度增强了极端的梯度.变种调用格式变种调用格式

更多相关视频

System for Efficacy and Cytotoxicity Screening of Inhibitors Targeting Intracellular Mycobacterium tuberculosis

System for Efficacy and Cytotoxicity Screening of Inhibitors Targeting Intracellular Mycobacterium tuberculosis

Published on: April 5, 2017

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening

Published on: January 17, 2014

相关实验视频

Last Updated: May 28, 2025

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Published on: April 25, 2014

System for Efficacy and Cytotoxicity Screening of Inhibitors Targeting Intracellular Mycobacterium tuberculosis

System for Efficacy and Cytotoxicity Screening of Inhibitors Targeting Intracellular Mycobacterium tuberculosis

Published on: April 5, 2017

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening

Published on: January 17, 2014

科学领域:

基因组学和生物信息学
传染病研究传染病研究
机器学习在医学中的应用

背景情况:

结核病 (TB) 是由Mycobacterium tuberculosis引起的,是全球主要的传染病.
结核病的耐药性是有效治疗和控制的主要挑战.
基因组测序和机器学习为预测耐药性提供了有前途的工具.

研究的目的:

评估四种机器学习模型,用于对M.结核病分离物中乙醇,异亚和利芬素的耐药性进行分类.
使用不同的数据预处理技术比较模型性能,包括PCA和突变优先级.

主要方法:

训练有素的极端梯度增强分类器 (XGBC),物流梯度增强分类器 (LGBC),梯度增强分类器 (GBC) 和人工神经网络 (ANN) 模型.
使用了由CRyPTIC联盟预处理的变种呼叫格式 (VCF) 数据集.
在使用灵敏度,特异性,精度,F1分数和准确度的原始,PCA减少和突变优先数据集上比较模型性能.

主要成果:

在原始数据集上训练的XGBC模型获得了最高的性能.
获得了高灵敏度 (0.97,0.90,0.94),特异性 (0.97,0.99,0.96) 和F1分数 (0.93,0.94,0.92) 对于乙胺醇,异化和利番素,分别.
与其他模型相比,XGBC模型在分类耐药性方面表现出卓越的准确性.

结论:

突变的二进制表示有效地训练XGBC模型来预测结核病药物耐药性和易感性.
在原始数据集上训练的XGBC模型显示了在诊断耐药结核病方面临床应用的巨大潜力.
建议进一步验证,以便在结核病诊断中更广泛地实施.