ActiMut-XGB:使用蛋白质语言模型预测CALB点突变的热力学稳定性
Yuxin Jiang1, Shuai Huang1, Hai-Feng Chen1
1State Key Laboratory of Microbial metabolism, Joint International Research Laboratory of Metabolic & Developmental Sciences, Department of Bioinformatics and Biostatistics, National Experimental Teaching Center for Life Sciences and Biotechnology, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China.
预测蛋白质的热稳定性对于蛋白质工程至关重要. 本研究介绍了一种机器学习模型,使用序列数据和转移学习来准确预测暴露在热量后的残余活动,帮助优化酶.
科学领域:
- 生物化学和分子生物学
- 计算生物学和生物信息学
- 蛋白质工程是指蛋白质工程.
背景情况:
- 评估单点突变对高温化后蛋白质残留活性的影响对于蛋白质工程至关重要.
- 现有的方法往往需要复杂的三维结构信息,这限制了它们的广泛应用.
研究的目的:
- 开发一种创新的机器学习模型,仅使用蛋白质序列数据来预测蛋白质的热稳定性.
- 通过转移学习和多种特征类型的整合来提高预测准确性和概括性.
主要方法:
- 使用了极端梯度提升 (XGBoost) 机器学习算法.
- 来自ESM2蛋白语言模型的综合特征,物理化学性质,进化数据和位置信息.
- 员工转移学习与来自不同蛋白质来源的热稳定性数据.
主要成果:
- 该模型准确地预测了蛋白质的热稳定性,从而规避了对3D结构数据的需求.
- 转移学习显著提高了预测准确性和模型通用性.
- 使用Candida antarctica脂酶B单点突变体的实验数据进行验证,证明了模型的有效性.
结论:
- 开发的机器学习模型在预测蛋白质热稳定性的传统方法上提供了显著的进步.
- 这种方法为蛋白质工程,酶优化和稳定的治疗蛋白质的开发提供了宝贵的见解.
- 该模型依赖于序列数据,使其在各种蛋白质科学领域广泛适用.
更多相关视频
06:50Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
08:13Differential Scanning Calorimetry — A Method for Assessing the Thermal Stability and Conformation of Protein Antigen
Published on: March 4, 2017
相关概念视频
Covalently Linked Protein Regulators
These groups modify specific amino acids in a protein....
Mutations
Conserved Binding Sites
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Improving Translational Accuracy
Calmodulin-dependent Signaling
The Ca2+-CaM complex does not have enzymatic activity by itself. Instead, the complex binds downstream target proteins, including membrane proteins or enzymes,...
Nonsense-mediated mRNA Decay
Usually, Upf3 binds to an Exon Junction Complex (EJC) at mRNA splice sites. If a ribosome fully translates the mRNA,...
