使用深度学习和大型蛋白质语言模型来预测外围膜蛋白质的蛋白质膜接口
Dimitra Paranou1,2, Alexios Chatzigoulas1, Zoe Cournia1,2
1Biomedical Research Foundation, Academy of Athens, Athens 11527, Greece.
Bioinformatics advances
|November 19, 2024
概括
人工智能,特别是自然语言处理和蛋白质语言模型,可以预测外围膜蛋白 (PMP) 的膜相互作用氨基酸. 这种方法为现有工具提供了更快,更准确的替代方案,而不需要3D结构数据.
科学领域:
- 计算生物学 计算生物学
- 生物信息学是一种生物信息学.
- 人工智能在生物学中的应用
背景情况:
- 蛋白质膜相互作用至关重要,与疾病相关的异常.
- 在外围膜蛋白 (PMPs) 中识别膜结合域是具有挑战性的.
- 目前分析蛋白质膜接口的方法可能耗时,需要结构数据.
研究的目的:
- 评估自然语言处理 (NLP) 和蛋白质语言模型 (pLMs) 在预测PMP的膜相互作用氨基酸方面的有效性.
- 建立一种更快,更容易获得的蛋白质膜接口分析方法.
主要方法:
- 利用两个pLM (ProtTrans和ESM) 的实验数据和蛋白质嵌入.
- 使用这些嵌入式的训练分类器模型.
- 评估了NLP和基于pLM的预测与现有方法的性能.
主要成果:
- 展示了第一个使用深度学习和pLMs来预测蛋白质膜接口的概念验证.
- 实现了与现有工具相提并论的准确性.
- 显著减少了预测时间,并消除了对3D结构数据的需求.
结论:
- 在预测蛋白质膜相互作用方面,NLP和pLM显著有前途.
- 这种方法为研究PMP提供了一个更快,更有效的替代方案.
- 开发的方法可以促进与异常蛋白质膜附着相关的疾病的研究.
相关概念视频
Protein-protein Interfaces
12.5K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
12.5K
Introduction to Membrane Proteins
66.1K
The cell membrane, or plasma membrane, is an ever-changing landscape. It is described as a fluid mosaic where various macromolecules are embedded in the phospholipid bilayer. Among the macromolecules are proteins. The protein content varies across cell types. For example, mitochondrial inner membranes contain ~76% protein content, while myelin contains ~18% protein content. Individual cells contain many types of membrane proteins—red blood cells contain over 50—and different cell...
66.1K
Membrane Proteins
18.2K
Plasma membranes have integral transmembrane proteins involved in facilitated transport. These proteins are collectively referred to as transport proteins, and they function as either channels for the material or as carriers themselves. Channel proteins have hydrophilic domains exposed to the intracellular and extracellular fluids and a hydrophilic channel through their core that provides a hydrated opening for solutes to pass through the membrane layers. Passage through the channel allows...
18.2K
Protein-Protein Interfaces
3.7K
3.7K
Multi-pass Transmembrane Proteins and β-barrels
5.2K
In multi-pass transmembrane proteins, the polypeptide chain crosses the membrane more than once. The transmembrane polypeptide chain either forms an α-helix or β-strand structure. α-Helix containing multi-pass transmembrane proteins are ubiquitous, whereas β-strand containing ones are mainly found in gram-negative bacteria, mitochondria, and chloroplasts.
α-Helix containing multi-pass transmembrane proteins
Multi-pass transmembrane proteins such as...
α-Helix containing multi-pass transmembrane proteins
Multi-pass transmembrane proteins such as...
5.2K
Mechanisms of Membrane Domain Formation
3.0K
Different physical properties of lipids and proteins allow them to localize and form distinct islands or domains in the membrane. Some membrane domains are formed due to protein-protein interactions, whereas others are formed due to the presence of specific lipids such as sphingolipids and sterols—for example, large proteins, such as bacteriorhodopsin, aggregate and create distinct domains.
Another mechanism for membrane domain formation involves membrane proteins interacting with...
Another mechanism for membrane domain formation involves membrane proteins interacting with...
3.0K


