简单,高效和可扩展的结构意识适配器提高了蛋白质语言模型.
Yang Tan1,2,3, Mingchen Li1,2,3, Bingxin Zhou3,4
1School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China.
Journal of chemical information and modeling
|August 7, 2024
概括
通过整合结构信息,SES-Adapter 增强了蛋白质语言模型 (PLM),提高了下游任务性能,加快了融合. 这种方法甚至在低质量的结构数据中也提供了显著的收益.
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.
- 机器学习 机器学习
背景情况:
- 微调预训练的蛋白质语言模型 (PLMs) 对于下游预测任务至关重要.
- 来自自然语言处理的参数高效微调技术显示出希望,但在生命科学中面临挑战.
- 调整这些技术需要解决培训策略和数据格式的差异.
研究的目的:
- 引入SES-Adapter,这是一种用于增强生命科学中PLM表示学习的新方法.
- 通过将PLM嵌入与结构序列嵌入相结合,创建结构意识的蛋白质表示.
- 为了证明SES-Adapter在各种PLM架构和任务中的效率和可扩展性.
主要方法:
- 开发了SES-Adapter,这是一个参数高效的微调方法.
- 集成的蛋白质语言模型嵌入与结构序列嵌入.
- 通过使用9个基准数据集和2种类型的折叠结构,对各种下游任务进行SES-Adapter的评估.
主要成果:
- 与香草PLM相比,SES-Adapter的下游任务性能平均提高了3%至11%.
- 实现了趋同速度的显著加快,平均为362%,高达1034%.
- 证明了提高训练效率 (大约2倍) 和稳定性与低质量的预测结构.
结论:
- SES-Adapter是一种兼容且有效的方法,可以在不同的架构和任务中增强PLM.
- 这种方法显著提高了绩效,加速了融合,提高了培训效率.
- 通过SES-Adapter,即使有不完美的结构数据,也可以促进蛋白质表示学习.
相关概念视频
Improving Translational Accuracy
9.6K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.6K
Adaptability of Cytoskeletal Filaments
3.7K
The cytoskeleton is a complex dynamic structure performing varied functions based on cellular requirements. The adaptability of the individual filaments in the cytoskeleton determines their ability to perform various functions within the cell. It can undergo rapid reorganization during processes like cell division or remain stable for several hours as in the interphase. The adaptability of these filaments depends on stringent regulatory mechanisms. The microfilament and microtubules of the...
3.7K
Protein and Protein Structure
79.2K
Proteins are one of the most abundant organic molecules in living systems and have the most diverse range of functions of all macromolecules. Proteins may be structural, regulatory, contractile, or protective. They may serve in transport, storage, or membranes; or they may be toxins or enzymes. Their structures, like their functions, vary greatly. They are all, however, amino acid polymers arranged in a linear sequence.
A protein's shape is critical to its function. For example, an enzyme...
A protein's shape is critical to its function. For example, an enzyme...
79.2K
Protein and Protein Structures
10.4K
10.4K
Protein Complexes with Interchangeable Parts
1.8K
1.8K
Conservation of Protein Domains Over Different Proteins
10.8K
Protein domains are small structurally independent units that are part of a single amino acid chain. Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
10.8K


