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

Sampling Plans01:23

Sampling Plans

868
Sampling is a crucial step in analytical chemistry, allowing researchers to collect representative data from a large population. Common sampling methods include random, judgmental, systematic, stratified, and cluster sampling.
Random sampling is a method where each member of the population has an equal chance of being selected for the sample. It involves selecting individuals randomly, often using random number generators or lottery-type methods. For example, when analyzing the properties of a...
868

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

Data-efficient learning for accurate identification of MAPK1 inhibitors using an active meta-deep learning framework.

Journal of cheminformatics·2026
Same author

Leveraging a Meta-Learning Strategy to Advance the Accuracy of Neutralizing Antibodies against Dengue Virus Serotype Prediction.

ACS omega·2026
Same author

XAI-ACSM: An Ensemble-Based Explainable Artificial Intelligence Framework for the Accurate Prediction of Anticancer Small Molecules.

ACS omega·2025
Same author

BLSAM-TIP: Improved and robust identification of tyrosinase inhibitory peptides by integrating bidirectional LSTM with self-attention mechanism.

PloS one·2025
Same author

MetaAMPK: Accurate Prediction of Adenosine Monophosphate-Activated Protein Kinase Activators Using a Meta-Learner Neural Network.

ACS omega·2025
Same author

Toward Explainable Carcinogenicity Prediction: An Integrated Cheminformatics Approach and Consensus Framework for Possibly Carcinogenic Chemicals.

Journal of chemical information and modeling·2025

相关实验视频

Updated: Jan 10, 2026

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation
16:02

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Published on: February 10, 2023

3.2K

积极堆叠-深度学习与战略采样用于小和不平衡的化学毒性预测.

Darlene Nabila Zetta1, Watshara Shoombuatong2, Tarapong Srisongkram3

  • 1Graduate School in the Program of Pharmaceutical Sciences, Faculty of Pharmaceutical Sciences, Khon Kaen University, Khon Kaen 40002, Thailand.

ACS omega
|November 24, 2025
PubMed
概括

这项研究引入了一个主动堆叠深度学习框架,通过有效使用有限的数据和战略采样来改进化学毒性预测,特别是甲状腺破坏性化学物质 (TDCs).

更多相关视频

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

808
Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
08:58

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

569

相关实验视频

Last Updated: Jan 10, 2026

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation
16:02

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Published on: February 10, 2023

3.2K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

808
Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
08:58

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

569

科学领域:

  • 计算毒理学和化学信息学
  • 机器学习用于化学安全评估.

背景情况:

  • 毒性预测模型与不平衡和有限的数据集作斗争,阻碍了准确的化学风险评估.
  • 由于数据稀缺和阶级不平衡问题,现有的方法往往无法很好地泛化.
  • 甲状腺破坏性化学物质 (TDCs) 对人类健康构成重大风险,需要可靠的预测方法.

研究的目的:

  • 开发和评估一个积极堆叠的深度学习框架,以提高毒性预测.
  • 在预测化学有害潜力方面解决数据不平衡和稀缺性挑战.
  • 提高识别甲状腺破坏性化学物质 (TDCs) 的准确性和效率.

主要方法:

  • 集成的深度神经网络 (DNN),包括CNN,BiLSTM,以及在堆叠组合中的注意力机制.
  • 采用积极学习 (AL) 与战略数据采样,以优化在有限数据上的模型培训.
  • 专注于针对甲状腺过氧化酶的TDC用于化学风险评估验证.

主要成果:

  • 积极堆叠的深度学习框架取得了显著的表现,MCC为0.51,AUROC为0.824,AUPRC为0.851.
  • 基于不确定性的AL方法在严重的阶级失衡下显示出优越的稳定性.
  • 与完整数据堆叠组合相比,拟议的方法需要高达73.3%的标签数据,同时实现了竞争力或优越的AUROC和AUPRC.

结论:

  • 积极堆叠-深度学习与战略采样为毒性预测提供了数据高效和准确的解决方案.
  • 该框架有效地解决了化学风险评估中的不平衡和有限数据挑战.
  • 分子对接验证了模型在识别有毒化合物的可靠性,特别是TDCs.