DeepRank-GNN-esm:使用蛋白质语言模型的蛋白质蛋白质模型评分图形神经网络
Xiaotong Xu1, Alexandre M J J Bonvin1
1Department of Chemistry, Faculty of Science, Computational Structural Biology Group, Bijvoet Centre for Biomolecular Research, Utrecht 3584 CS, The Netherlands.
DeepRank-GNN-esm通过用高效的蛋白质语言模型嵌入来取代计算上昂贵的PSSM功能来增强蛋白质-蛋白质相互作用建模,提高可用性和性能.
科学领域:
- 计算生物学 计算生物学
- 结构生物学 结构生物学
- 生物信息学是一种生物信息学.
背景情况:
- 蛋白与蛋白相互作用 (PPI) 对细胞功能至关重要.
- 建模3D蛋白质复杂结构有助于药物设计和蛋白质工程.
- 从众多生成的模型中识别准确的模型是一个关键的挑战.
研究的目的:
- 开发一种更有用,更有效的方法来建模蛋白质复合体.
- 将蛋白质语言模型嵌入式集成到现有的图形神经网络框架中,用于PPI建模.
主要方法:
- 介绍了DeepRank-GNN-esm,一个包含ESM-2蛋白语言模型嵌入的图形神经网络.
- 使用ESM-2嵌入式作为取代位置特定评分矩阵 (PSSMs).
- 评估PPI任务的性能,包括对接姿势得分和晶体文物检测.
主要成果:
- 在PPI建模任务中,ESM-2嵌入式提供了与PSSM相匹配或优于PSSM的性能.
- DeepRank-GNN-esm消除了对计算密集型PSSM生成的需要.
- 新模型显示了改进的可用性,并将应用扩展到PSSM无法实现的系统.
结论:
- 通过利用蛋白质语言模型,DeepRank-GNN-esm在蛋白质复合体建模方面取得了重大进展.
- 该方法提高了计算效率,并扩大了PPI建模工具的适用性.
- 该软件是公开可用的,有助于进一步的研究和开发.
更多相关视频
09:34A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
07:35A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
相关概念视频
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Protein-protein Interfaces
Protein and Protein Structure
A protein's shape is critical to its function. For example, an enzyme...
Protein Organization
The primary structure of a protein is its amino acid sequence....
Protein and Protein Structures
Classification of Neurotransmitters
