相关实验视频

Updated: Jan 10, 2026

Creating and Applying a Reference to Facilitate the Discussion and Classification of Proteins in a Diverse Group

Creating and Applying a Reference to Facilitate the Discussion and Classification of Proteins in a Diverse Group

Published on: August 16, 2017

CATHe2:使用ProstT5和结构字母的增强CATH超级家族检测

Orfeú Mouret^1,2, Jad Abbass¹

¹School of Computer Science and Mathematics, Kingston University, Kingston-upon-Thames KT1 2EE, United Kingdom.

Biology methods & protocols

|November 24, 2025

概括

CATHe2通过集成先进的蛋白质语言模型和3D结构信息来增强蛋白质域分类. 这种新模型显著提高了预测CATH超级家族的准确性和F1分数.

科学领域:

计算生物学是一种计算生物学.
结构生物信息学结构生物信息学
在基因组学中的机器学习.

背景情况:

CATH数据库对蛋白质域结构和进化关系进行了分类.
AlphaFold加速了蛋白质结构预测,需要自动化分类方法.
之前的CATHe分类器使用蛋白质语言模型 (pLM) 嵌入用于超级家族预测.

研究的目的:

为CATH超级家族开发一个改进的自动分类器,CATHe2.
为了提高蛋白质域分类的准确性和效率.
利用最近蛋白质语言模型的进展,并纳入3D结构数据.

主要方法:

使用了更新的pLM嵌入式 (ProstT5) 和3Di序列嵌入式来表示3D结构.
实现了一个微调的前神经网络 (FNN) 分类器架构.
训练和评估的模型在一个数据集的远程蛋白质同类的 20% 序列识别值.

主要成果:

最好的CATHe2模型在最大的数据集 (~1700个超级家族) 上实现了92.2%的准确性和82.3%的F1得分.
这比以前的CATHe版本 (85.6%的准确率,72.4%的F1得分) 显著改进.
即使是仅使用氨基酸序列的简化CATHe2版本也显示出显著的性能增长.

结论:

CATHe2为自动CATH超级家族分类提供了更准确和更强大的方法.
集成先进的pLM和3D结构信息对于改善蛋白质分类至关重要.
这一进步有助于在大规模结构预测时代了解蛋白质的进化和功能.

关键词:

3DiDi是什么意思 3DiDi是什么意思在CATH系统中,CATH 凯瑟琳凯瑟琳在 ProstT5T5 中使用.蛋白质语言模型 (pLM)结构字母表结构字母表分类器分类器是分类器.蛋白质蛋白质是蛋白质蛋白质的组成部分.

更多相关视频

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

An Integrated Approach for Microprotein Identification and Sequence Analysis

An Integrated Approach for Microprotein Identification and Sequence Analysis

Published on: July 12, 2022

相关概念视频

Allosteric Proteins-ATCase

Allosteric Proteins-ATCase

Binding sites linkages can regulate a protein's function. For example, enzyme activity is often regulated through a feedback mechanism where the end product of the biochemical process serves as an inhibitor.
Aspartate transcarbamoylase (ATCase) is a cytosolic enzyme that catalyzes the condensation of L-aspartate and carbamoyl phosphate to N-carbamoyl-L-aspartate. This reaction is the first step in pyrimidine biosynthesis. UTP and CTP, the end products of the pyrimidine synthesis...

Catenins

Catenins

Catenins are characterized by multiple binding domains and dynamic structures that allow them to function as linker proteins in cell junction complexes. All catenins, except α-catenin, contain a characteristic protein sequence called the armadillo repeat and are therefore also called armadillo proteins.
Catenins in Cell Junctions
Catenins bind to cell adhesion molecules such as cadherins and link them to different cytoskeletal proteins depending on the type of cell junction. At the...

Structure of Cadherins

Structure of Cadherins

The cadherins were one of the first cell adhesion molecules discovered; the term “cadherins” is based on their calcium-dependent adhering properties. The first cadherins discovered on the epithelial, neuronal, and placental cells were named E-cadherin, P-cadherin, and N-cadherin, respectively. These classical cadherins share sequence and structural similarities. Other cadherins, including those involved in cell signaling, are grouped into non-classical cadherins. This...