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

Screening of Small Peptide Against Ischemic Fatty-Acid Binding Protein (FABP).

The protein journal·2026
Same author

XGBPred-ACSM: A Hybrid Descriptor-Driven XGBoost Framework for Anticancer Small Molecule Prediction.

Pharmaceuticals (Basel, Switzerland)·2026
Same author

Metagenome Sequencing and Recovery of 52 Microbial Genomes from Plastic-Polluted Coastal Sediment.

Scientific data·2026
Same author

Thermally stable network-structured polysiloxane hybrimers with high refractive index for optical applications.

RSC advances·2026
Same author

Exploring Eugenol as a Growth and Biofilm Inhibitor in Leptospira interrogans by a Combined Experimental and Computational Approach.

APMIS : acta pathologica, microbiologica, et immunologica Scandinavica·2025
Same author

Comparative study on the inhibitory potential of anticancer drugs and natural compounds against PHB proteins.

Natural product research·2025

相关实验视频

Updated: Jun 3, 2025

Facilitating Drug Discovery: An Automated High-content Inflammation Assay in Zebrafish
07:50

Facilitating Drug Discovery: An Automated High-content Inflammation Assay in Zebrafish

Published on: July 16, 2012

14.2K

AISMPred:一种用于预测抗炎小分子的机器学习方法.

Subathra Selvam1, Priya Dharshini Balaji1, Honglae Sohn2

  • 1Computational Biology Laboratory, Department of Genetic Engineering, School of Bioengineering, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu 603203, Tamil Nadu, India.

Pharmaceuticals (Basel, Switzerland)
|January 8, 2025
PubMed
概括

一种新的计算方法,AISMPred,有效地选抗炎小分子 (AISM). 这种方法有助于通过准确识别潜在的AISM来发现新的候选药物,加速药物发现过程.

关键词:
这是一种抗炎药物.自身免疫性疾病是一种自身免疫性疾病.在k倍的交叉验证中.机器学习是机器学习.小分子的小分子.

更多相关视频

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.3K
Screening Assays to Characterize Novel Endothelial Regulators Involved in the Inflammatory Response
12:50

Screening Assays to Characterize Novel Endothelial Regulators Involved in the Inflammatory Response

Published on: September 15, 2017

6.5K

相关实验视频

Last Updated: Jun 3, 2025

Facilitating Drug Discovery: An Automated High-content Inflammation Assay in Zebrafish
07:50

Facilitating Drug Discovery: An Automated High-content Inflammation Assay in Zebrafish

Published on: July 16, 2012

14.2K
Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.3K
Screening Assays to Characterize Novel Endothelial Regulators Involved in the Inflammatory Response
12:50

Screening Assays to Characterize Novel Endothelial Regulators Involved in the Inflammatory Response

Published on: September 15, 2017

6.5K

科学领域:

  • 计算化学和化学信息学
  • 药理学和药物发现
  • 机器学习在药物化学中的应用.

背景情况:

  • 炎症是一种关键的生物反应,但慢性炎症驱动疾病.
  • 类疗法提供了特异性,但面临着发展挑战.
  • 由于稳定性和生物可用性,小分子对抗炎药物开发具有前景.

研究的目的:

  • 开发和验证一种计算方法,AISMPred,用于分类抗炎小分子 (AISM) 和非AISM.
  • 提高识别潜在抗炎药物候选药物的效率和降低成本.

主要方法:

  • 1750个AISM和非AISM的数据集与PubChem.chem的IC50值进行了策划.
  • 使用PADEL和Mordred计算分子描述符,然后将其结合成混合特征集.
  • 使用L1规范化的支持向量分类器 (SVC-L1) 进行特征选择,并训练了五个ML分类器 (RF,ET,KNN,LR,Ensemble).

主要成果:

  • 开发了15个机器学习 (ML) 模型,使用2D,指纹 (FP) 和混合功能集.
  • 使用混合功能的额外树木 (ET) 模型实现了最高的性能.
  • 在一个独立的测试组中,表现最好的ET模型显示了92%的准确性和0.97的AUC.

结论:

  • AISMPred提供了一种有效的计算策略,用于选抗炎小分子.
  • 这种方法有可能显著影响和加速药物发现和设计管道.
  • 这项研究强调了ML在识别炎症状况的新疗法中对ML的有用性.