PepBERT:生物活性体表示的轻量级语言模型
Zhenjiao Du1, Doina Caragea2, Xiaolong Guo3
1Department of Grain Science and Industry, Kansas State University, Manhattan, KS 66506, USA.
bioRxiv : the preprint server for biology
|July 9, 2025
概括
蛋白质语言模型 (pLMs) 低于短. PepBERT是一种新的语言模型,在任务上提供了卓越的性能,加速了用于功能性食品的生物活性的发现.
科学领域:
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
- 酸科学 酸科学
背景情况:
- 蛋白质语言模型 (pLMs) 对蛋白质和的任务是有效的.
- 短 (<50个残留物) 在标准的pLM培训数据中不足 (例如,UniProt参考集群,2.8%).
- 这种代表性不足限制了pLMs在特异性应用中的有效性.
研究的目的:
- 开发一种专门的语言模型来编码序列.
- 解决现有的pLM在处理短的局限性.
- 为了提高功能性食品的生物活性的发现.
主要方法:
- 开发PepBERT,一种轻量化型语言模型,有两个版本:PepBERT-大 (4.9M参数) 和PepBERT-小 (1.86M参数).
- 从零开始使用四个定制数据集进行PepBERT模型的预训练.
- 对9个相关下游预测任务的PepBERT模型的评估,将性能与基准ESM-2 (7.5M参数) 进行比较.
主要成果:
- 在9个评估的预测任务中,PepBERT模型在8个方面实现了优于ESM-2或与ESM-2相当的性能.
- PepBERT提供了一个紧而高效的解决方案,用于生成高质量的体表示.
- 这些模型在编码序列方面表现出有效性,性能优于较大的基准模型.
结论:
- 佩伯特为序编码和下游应用提供了专门有效的解决方案.
- 该模型可以加速发现具有健康益处的食品衍生生物活性.
- 佩伯特支持开发可持续的功能性食品和利用食品加工副产品.
相关概念视频
01:33Peptide Identification Using Tandem Mass Spectrometry
6.8K
Tandem mass spectrometry, also known as MS/MS or MS2, is an analytical technique that employs two mass analyzers. Essentially it is a series of mass spectrometers that helps isolate a particular biomolecule and then helps study its chemical properties.
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...
6.8K
02:43Peptide Bonds
77.4K
A peptide bond covalently attaches amino acids through a dehydration reaction. One amino acid's carboxyl group and another amino acid's amino group combine, releasing a water molecule. The resulting bond is the peptide bond. The products that such linkages form are peptides. As more amino acids join this growing chain, the resulting chain is a polypeptide. Each polypeptide has a free amino group at one end. This end has the N-terminal, or the amino-terminal, and the other end has a free...
77.4K
02:04Protein-Protein Interfaces
3.9K
3.9K
02:04Protein-protein Interfaces
13.4K
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...
13.4K
02:40Ligand Binding Sites
13.4K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
13.4K
02:26Protein Networks
2.4K
2.4K