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

Uncertainty: Overview00:59

Uncertainty: Overview

In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.

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

Evaluating the role of pretraining dataset size and diversity on single-cell foundation model performance.

Nature methods·2026
Same author

Scalable and cost-efficient custom gene library assembly from oligopools.

Science advances·2026
Same author

Sequence Display enables large-scale sequence-activity datasets for rapid protein evolution.

Nature biotechnology·2026
Same author

Trainable subnetworks reveal insights into structure knowledge organization in protein language models.

PLoS computational biology·2026
Same author

Improving atlas-scale single-cell annotation models with hierarchical cross-entropy loss.

Nature computational science·2026
Same author

Deep learning guided design of protease substrates.

Nature communications·2026
Same journal

Detection, communication, and individual identification with deep audio embeddings: A case study with North Atlantic right whales.

PLoS computational biology·2026
Same journal

Exploring the structural lexicon of the Proteome via Metric Geometry.

PLoS computational biology·2026
Same journal

Linking retinal sampling in neural encoding models to temporal profiles of visual processing in humans.

PLoS computational biology·2026
Same journal

CAdir: Joint clustering of cells and genes for single-cell transcriptomics with visualization-driven cluster quality assessment.

PLoS computational biology·2026
Same journal

Systematic design of auxotrophic strains and media conditions to probe metabolic functions in E. coli.

PLoS computational biology·2026
Same journal

Neuronal excitability and parameter variability in the Hodgkin-Huxley model.

PLoS computational biology·2026
查看所有相关文章

相关实验视频

Updated: May 7, 2026

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

17.0K

对蛋白质工程的基准测试不确定性量化.

Kevin P Greenman1,2,3, Ava P Amini4, Kevin K Yang4

  • 1Department of Chemical Engineering, Catholic Institute of Technology, Cambridge, Massachusetts, United States of America.

PLoS computational biology
|January 8, 2025
PubMed
概括
此摘要是机器生成的。

用于蛋白质工程的机器学习模型需要准确的不确定性估计. 本研究对蛋白质数据集的深度学习不确定性量化方法进行了基准测试,没有发现单一的最佳方法,并且基于不确定性的抽样获得的收益有限.

更多相关视频

Calibration-free In Vitro Quantification of Protein Homo-oligomerization Using Commercial Instrumentation and Free, Open Source Brightness Analysis Software
08:22

Calibration-free In Vitro Quantification of Protein Homo-oligomerization Using Commercial Instrumentation and Free, Open Source Brightness Analysis Software

Published on: July 17, 2018

7.2K
Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting
08:13

Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting

Published on: April 9, 2019

14.1K

相关实验视频

Last Updated: May 7, 2026

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

17.0K
Calibration-free In Vitro Quantification of Protein Homo-oligomerization Using Commercial Instrumentation and Free, Open Source Brightness Analysis Software
08:22

Calibration-free In Vitro Quantification of Protein Homo-oligomerization Using Commercial Instrumentation and Free, Open Source Brightness Analysis Software

Published on: July 17, 2018

7.2K
Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting
08:13

Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting

Published on: April 9, 2019

14.1K

科学领域:

  • 计算生物学是一种计算生物学.
  • 机器学习 机器学习
  • 蛋白质工程是一种蛋白质工程.

背景情况:

  • 机器学习序列功能模型对于蛋白质工程至关重要.
  • 有效的蛋白质设计需要序列选择和模型改进的方法.
  • 这些方法依赖于校准模型不确定性估计.

研究的目的:

  • 在蛋白质序列功能回归任务上对深度学习不确定性量化 (UQ) 方法进行基准测试.
  • 为了评估在不同分布式转移和数据表示中UQ方法的性能.
  • 评估UQ方法在主动学习和贝叶斯优化蛋白质设计中的实用性.

主要方法:

  • 在蛋白质 (FLIP) 的健身景观推断基准上实施并比较了各种深度学习的UQ方法.
  • 使用准确性,校准,覆盖范围,宽度和等级相关性等指标评估UQ表现.
  • 在回顾式主动学习和贝叶斯优化中评估了使用一热编码和预训练语言模型表示的UQ方法.

主要成果:

  • 没有单一的UQ方法在所有数据集,分割和指标中表现出优异的性能.
  • 在贝叶斯优化中基于不确定性的采样通常不超过贪的采样.
  • 性能因特定的UQ方法,数据表示和分布式转移而有所不同.

结论:

  • 在蛋白质机器学习应用中,选择UQ方法至关重要,并且取决于环境.
  • 当前的UQ方法可能无法持续改善蛋白质工程中的积极学习或贝叶斯优化.
  • 提供了使用机器学习和UQ优化生物序列设计的建议.