相关实验视频

Updated: May 20, 2025

Localization of SUMO-modified Proteins Using Fluorescent Sumo-trapping Proteins

Localization of SUMO-modified Proteins Using Fluorescent Sumo-trapping Proteins

Published on: April 27, 2019

SUMO-LMNet:使用高维特征预测SUMO1和SUMO2中的SUMOylation位点的无损映射网络

Cheng-Hsun Ho¹, Yen-Wei Chu^2,3,4,5, Lan-Ying Huang³

¹Department of Medical Laboratory Science, College of Medical Science and Technology, I-Shou University, Kaohsiung City, Taiwan.

Computational and structural biotechnology journal

|March 27, 2025

概括

预测SUMO1和SUMO2修饰点是一个挑战. 深度学习模型SUMO-LMNet使用无损映射策略和综合热图特征分析准确地区分这些对应物.

科学领域:

生物化学生物化学
生物信息学是一种生物信息学.
计算生物学计算生物学

背景情况:

SUMOylation对于基因调节和疾病至关重要.
由于结构相似,很难区分SUMO1和SUMO2地点.
现有的模型在区分SUMO对应物方面缺乏准确性.

研究的目的:

开发一个精确的深度学习模型来预测SUMO1和SUMO2站点.
为了提高SUMOylation位点识别中的预测准确性和可解释性.
为了解决传统模型在区分SUMO对应器方面的局限性.

主要方法:

实施了一个深度学习框架,SUMO-LMNet.
使用无损映射策略 (LM-Net) 来保护特征.
用户组合热图特征分析 (CHFA) 用于全数据集特征重要性评估.
应用卷积神经网络 (CNN) 在由序列衍生的二维特征地图上.

主要成果:

在区分SUMO1和SUMO2站点方面,SUMO-LMNet的准确度超过80%.
确定了SUMO1和SUMO2修改特有的独特特征依赖.
与Grad-CAM不同,CHFA提供了可靠的全数据集特征重要性分析.
证明了对等式特定预测模型的必要性.

结论:

在预测SUMO1和SUMO2修改站点方面,SUMO-LMNet提供了显著的进步.
该模型通过优先考虑候选SUMOylation目标来帮助实验设计.
这种方法加快了生物学上相关的SUMOylation目标的发现.
SUMO-LMNet是公开可用于研究的.

关键词:

2D卷积神经网络是一个2D卷积神经网络.分析特征的重要性分析.这就是SUMO的类比.预测SUMOylation的预测序列的特征是序列的特征.

更多相关视频

SUMO-Binding Entities SUBEs as Tools for the Enrichment, Isolation, Identification, and Characterization of the SUMO Proteome in Liver Cancer

SUMO-Binding Entities SUBEs as Tools for the Enrichment, Isolation, Identification, and Characterization of the SUMO Proteome in Liver Cancer

Published on: November 1, 2019

A Fast and Quantitative Method for Post-translational Modification and Variant Enabled Mapping of Peptides to Genomes

A Fast and Quantitative Method for Post-translational Modification and Variant Enabled Mapping of Peptides to Genomes

Published on: May 22, 2018

相关概念视频

Conserved Binding Sites

Conserved Binding Sites

Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...