AIPred:通过蛋白质语言模型和可解释的机器学习来全面预测和分析非海斯乙化
Yuqing Geng1, Hao Luo2, Feng Gao3,4,5
1Department of Physics, School of Science, Tianjin University, Tianjin, 300072, China.
BMC biology
|October 17, 2025
概括
使用可解释的机器学习和蛋白质语言模型,AIPred准确地预测了非素乙化位点. 这个框架增强了对细胞过程和疾病中的乙化理解,提供了更好的预测准确性和可用性.
科学领域:
- 生物化学和分子生物学
- 计算生物学 计算生物学
- 基因组学就是基因组学.
背景情况:
- 非希斯 lysine 乙化是一种关键的翻译后修饰,调节细胞过程.
- 乙化失调与各种人类疾病有关.
- 准确识别乙化位点至关重要,但在计算上具有挑战性.
研究的目的:
- 开发一个准确和可解释的计算工具,用于预测非希斯顿乙化位点.
- 在预测准确性,解释性和可用性方面改进现有方法.
- 促进对乙化在细胞调节和疾病中的作用的研究.
主要方法:
- 综合框架将ESM坎布里亚蛋白语言模型嵌入与生物信息学特征相结合.
- 利用可解释的机器学习进行预测和分析.
- 采用沙普利增量解释和梯度归因用于特征分析.
主要成果:
- 与最先进的模型相比,AIPred表现出优越的性能,F1分数,MCC和AUPRC的显著改善.
- 确定了关键特征和序列模式,推动了预测的准确性.
- 在TDP-43中揭示了功能性重要的乙化位点,包括新的预测.
结论:
- 艾普雷德提供了一个准确,可解释和可访问的计算框架,用于非素乙化场地的预测.
- 该工具有望加速对细胞调节和疾病中的乙化机制的研究.
- AIPred提供了一个用户友好的在线服务器和数据库,以实现更广泛的可访问性.
相关概念视频
Covalently Linked Protein Regulators
8.7K
Proteins can undergo many types of post-translational modifications, often in response to changes in their environment. These modifications play an important role in the function and stability of these proteins. Covalently linked molecules include functional groups, such as methyl, acetyl, and phosphate groups, and also small proteins, such as ubiquitin. There are around 200 different types of covalent regulators that have been identified.
These groups modify specific amino acids in a protein....
These groups modify specific amino acids in a protein....
8.7K
Histone Modification
15.9K
The histone proteins have a flexible N-terminal tail extending out from the nucleosome. These histone tails are often subjected to post-translational modifications such as acetylation, methylation, phosphorylation, and ubiquitination. Particular combinations of these modifications form “histone codes” that influence the chromatin folding and tissue-specific gene expression.
Acetylation
The enzyme histone acetyltransferase adds acetyl group to the histones. Another enzyme, histone...
Acetylation
The enzyme histone acetyltransferase adds acetyl group to the histones. Another enzyme, histone...
15.9K


