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

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

Adaptive radiation and structural tailoring of the Vietnamese <i>Blec2</i> immunogenetic reservoir.

Frontiers in genetics·2026

Same author

DNA purity over yield: optimizing extraction and PCR in degraded Asian elephant (Elephas maximus) fecal samples.

Genes & genomics·2026

Same author

Ancestral <i>BG1</i> Alleles and Structural Conservation Ensure Immune-Related Genetic Resilience in Southeast Asian Chicken Lineages.

Animals : an open access journal from MDPI·2026

Same author

Harnessing Deep Learning in Searching Wild Relatives of Domestic Animals.

Molecular ecology resources·2026

Same author

Mixed modes of satellite DNA and transposable element evolution, which shape the repetitive landscape of air-breathing catfishes (Clarias).

Chromosome research : an international journal on the molecular, supramolecular and evolutionary aspects of chromosome biology·2026

Same author

Landscape Features Shape Maternal Genetic Structure of Asian Elephants in Thailand: Insights from mtDNA.

Biology·2026

Search research articles

相关实验视频

Updated: Jan 13, 2026

RNA-Seq Analysis of Differential Gene Expression in Electroporated Chick Embryonic Spinal Cord

RNA-Seq Analysis of Differential Gene Expression in Electroporated Chick Embryonic Spinal Cord

Published on: November 1, 2014

使用微卫星基因型数据和AutoGluon框架的高精度品种识别.

Rajaonarison Faniriharisoa Maxime Toky¹, Sutthisak Sukhamsri², Sadeep Medhasi¹

¹Animal Genomics and Bioresource Research Unit (AGB Research Unit), Faculty of Science, Kasetsart University, Bangkok 10900, Thailand.

|January 10, 2026

概括

机器学习,特别是随机森林模型,使用微观卫星数据准确识别品种. 这种具有成本效益的方法提高了品种保护和育种计划的设计.

关键词:

品种的确定品种的确定的品种的品种机器学习是机器学习.微卫星微卫星是什么意思随机的森林随机的森林

更多相关视频

Avian Influenza Surveillance with FTA Cards: Field Methods, Biosafety, and Transportation Issues Solved

Avian Influenza Surveillance with FTA Cards: Field Methods, Biosafety, and Transportation Issues Solved

Published on: August 2, 2011

A Noninvasive Hair Sampling Technique to Obtain High Quality DNA from Elusive Small Mammals

A Noninvasive Hair Sampling Technique to Obtain High Quality DNA from Elusive Small Mammals

Published on: March 13, 2011

相关实验视频

Last Updated: Jan 13, 2026

RNA-Seq Analysis of Differential Gene Expression in Electroporated Chick Embryonic Spinal Cord

RNA-Seq Analysis of Differential Gene Expression in Electroporated Chick Embryonic Spinal Cord

Published on: November 1, 2014

Avian Influenza Surveillance with FTA Cards: Field Methods, Biosafety, and Transportation Issues Solved

Avian Influenza Surveillance with FTA Cards: Field Methods, Biosafety, and Transportation Issues Solved

Published on: August 2, 2011

A Noninvasive Hair Sampling Technique to Obtain High Quality DNA from Elusive Small Mammals

A Noninvasive Hair Sampling Technique to Obtain High Quality DNA from Elusive Small Mammals

Published on: March 13, 2011

科学领域:

生物信息学是一种生物信息学.
动物遗传学动物遗传学
机器学习应用机器学习应用

背景情况:

准确的品种识别对于保护和繁殖计划至关重要.
区分表型相似的品种是具有挑战性和昂贵的.
机器学习 (ML) 为分析复杂的遗传数据提供了先进的工具.

研究的目的:

开发一种可访问和优化的品种识别方法.
用微卫星数据评估随机森林 (RF) 模型用于分类品种的有效性.
证明ML的实用性,特别是AutoGluon,用于经济高效的品种确定.

主要方法:

利用了来自30个种群的651个个体的微卫星基因型数据.
采用随机森林 (RF) 模型进行品种分类.
应用交叉验证技术 (10倍和1次) 和性能指标 (准确性,科恩的卡帕,F1分数).

主要成果:

射频模型在测试数据集上实现了95.38%的准确性.
交叉验证准确率为91.44% (10倍) 和90.99% (留下一个).
经过训练的模型证明了用于品种决定的概括性.

结论:

机器学习,特别是RF和AutoGluon等自动化方法,为品种识别提供了强大的框架.
这种ML方法提供了一种简单,现代和具有成本效益的方法来确定品种.
预计更大的数据集将进一步改善各种品种的模型性能.