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

High-resolution spatial transcriptomics of adult and pediatric human liver with Visium HD.

Scientific data·2026
Same author

Global genetic interaction network of a human cell maps conserved principles and informs functional interpretation of gene co-essentiality profiles.

Cell·2026
Same author

Metabolomic Signatures of Relapse and Survival in AML Patients Receiving Allogeneic Hematopoietic Stem Cell Transplantation.

Hematology reports·2026
Same author

From FAIR to CURE: guidelines for computational models of biological systems.

NPJ systems biology and applications·2026
Same author

FLASH-MM: fast and scalable single-cell differential expression analysis using linear mixed-effects models.

Nature communications·2026
Same author

Tutorial: annotation of animal genomes.

Nature protocols·2026
Same journal

Correction to: Pathogenicity patterns in cytochrome P450 family.

Bioinformatics advances·2026
Same journal

Region-aware bridge modeling enables interpretable mesoscale representation of spatial transcriptomic tissue sections.

Bioinformatics advances·2026
Same journal

Microbiome differential abundance methodologies to detect relevant taxa associated with chemotherapy toxicity rate in colorectal cancer.

Bioinformatics advances·2026
Same journal

maldipickr dereplicates microbial MALDI-TOF spectra to facilitate multiplexed isolation.

Bioinformatics advances·2026
Same journal

RAM-MSA: an anytime memory-bounded method for exact multiple sequence alignment using path finding.

Bioinformatics advances·2026
Same journal

Interpretable machine learning for low-sample multi-omics: a case study of ferret vaccine response.

Bioinformatics advances·2026
查看所有相关文章

相关实验视频

Updated: Jul 8, 2025

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues
10:12

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

18.6K

对抗性训练提高了单细胞RNA-seq分析中的模型解释性.

Mehrshad Sadria1, Anita Layton1,2,3,4, Gary D Bader5,6,7,8,9

  • 1Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada.

Bioinformatics advances
|December 15, 2023
PubMed
概括
此摘要是机器生成的。

反对训练增强了用于细胞类型预测的深度学习模型,提高了对输入变化的稳定性和生物数据分析中的可解释性. 这种方法对于需要可靠和可理解的人工智能的一般应用具有前景. 关键词:对抗训练,深度学习,模型可解释性,生物数据.

更多相关视频

Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq
06:24

Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq

Published on: March 12, 2021

3.6K
Author Spotlight: Deciphering the Cellular Mysteries of Intermuscular Adipose Tissue in Humans
05:59

Author Spotlight: Deciphering the Cellular Mysteries of Intermuscular Adipose Tissue in Humans

Published on: May 3, 2024

718

相关实验视频

Last Updated: Jul 8, 2025

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues
10:12

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

18.6K
Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq
06:24

Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq

Published on: March 12, 2021

3.6K
Author Spotlight: Deciphering the Cellular Mysteries of Intermuscular Adipose Tissue in Humans
05:59

Author Spotlight: Deciphering the Cellular Mysteries of Intermuscular Adipose Tissue in Humans

Published on: May 3, 2024

718

科学领域:

  • 计算生物学是一种计算生物学.
  • 医学中的人工智能
  • 机器学习用于基因组学.

背景情况:

  • 可靠的预测计算模型对生物学和医学至关重要.
  • 模型的稳定性 (对输入变化的不敏感性) 和可解释性 (决策的可解释性) 是信任的关键.
  • 现有的方法通常独立地解决稳定性和可解释性,而它们的相互作用被人们理解得很差.

研究的目的:

  • 研究对抗性培训对深度学习模型的稳定性和可解释性的影响.
  • 探索这些模型在预测单细胞RNA测序数据的细胞类型中的应用.

主要方法:

  • 对抗性训练应用于用于细胞类型预测的深度学习模型.
  • 用标准方法评估模型解释性,以确定重要的基因进行分类.
  • 单细胞RNA测序数据被用作示例任务.

主要成果:

  • 对抗性训练显著提高了细胞类型预测模型的稳定性.
  • 令人惊的是,对抗性训练也提高了模型的解释性,基因重要性识别证明了这一点.
  • 这些发现表明对抗训练是改进深度学习模型的有价值技术.

结论:

  • 反对训练可以同时提高深度学习模型的稳定性和可解释性.
  • 这种方法有可能在科学研究中得到更广泛的应用,特别是在需要可靠和可解释的人工智能的领域.
  • 建议进一步评估跨不同任务的对抗性培训.