深度学习用于NAD/NADP辅因子预测和工程,使用酶中的变压器注意力分析
Jaehyung Kim1, Jihoon Woo1, Joon Young Park1
1School of Energy and Chemical Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, 44919, Republic of Korea.
Metabolic engineering
|November 21, 2024
概括
一个新的深度学习模型DISCODE准确地预测了依赖NAD (P) 的氧化还原酶的辅因子偏好. 该工具通过识别酶重新设计和切换辅因子特异性的关键残留物来帮助生物工程.
科学领域:
- 生物化学 生物化学
- 生物工程是生物工程.
- 计算生物学 计算生物学
背景情况:
- 依赖NAD (((P) 的氧化还原酶是具有广泛自然分布的重要酶.
- 操纵它们的辅因子偏好对于生物工程应用至关重要.
- 目前用于识别辅因子偏好和设计突变的方法复杂且规模有限.
研究的目的:
- 开发一种新的深度学习模型,用于预测氧化还原酶的尼古丁胺氨基二核酸 (酸盐) [NAD(P) ]辅因子偏好.
- 为了实现大规模分析,并促进具有改变辅因子特异性的酶的设计.
- 为识别参与辅因子结合的关键残留物提供一个可解释的模型.
主要方法:
- 开发DISCODE,一个基于变压器的深度学习模型.
- 在7132个NAD(P) 依赖酶序列的数据集上训练模型.
- 在没有结构或分类学约束的情况下利用全长酶序列进行预测.
- 分析变压器的注意层,以确定影响辅因子特异性的关键残留物.
主要成果:
- DISCODE实现了高预测准确度 (97.4%) 和F1得分 (97.3%) 的NAD(P) 辅因子偏好.
- 注意层分析成功地确定了对NAD (P) 相互作用和特异性至关重要的残留物.
- 识别的关键残留物与已知的辅因子切换突变体具有很高的一致性.
- 该模型的可解释性促进了对辅因子特异性决定因素的理解.
结论:
- DISCODE提供了一种准确而有效的方法,用于预测氧化还原酶中的NAD (P) 辅因子偏好.
- 该模型的可解释性有助于识别酶工程的关键残留物.
- 与注意力分析集成的DISCODE提供了一个完全自动化的管道,用于重新设计酶辅因子特异性.
相关概念视频
Role of Reduced Coenzymes NADH and FADH₂
11.2K
The energy released from the breakdown of the chemical bonds within nutrients can be stored either through the reduction of electron carriers or in the bonds of adenosine triphosphate (ATP). In living systems, a small class of compounds functions as mobile electron carriers, molecules that bind to and shuttle high-energy electrons between compounds in pathways. The principal electron carriers that will be considered originate from the B vitamin group and are derivatives of nucleotides; they are...
11.2K
Introduction to Enzymes
17.2K
The use of enzymes by humans dates to 7000 BCE. Humans first used enzymes to ferment sugars and produce alcohol without knowing that this was an enzyme-catalyzed reaction. Wilhelm Kuhne coined the term 'enzyme' in 1877 from the Greek words ‘en’ meaning ‘in’ or ‘within’ and ‘zyme’ meaning ‘yeast.’
Most enzymes are proteins that speed up biochemical reactions without being consumed. Enzymes contain one or more active sites that...
Most enzymes are proteins that speed up biochemical reactions without being consumed. Enzymes contain one or more active sites that...
17.2K
Enzymes
80.8K
Inside living organisms, enzymes act as catalysts for many biochemical reactions involved in cellular metabolism. The role of enzymes is to reduce the activation energies of biochemical reactions by forming complexes with its substrates. The lowering of activation energies favor an increase in the rates of biochemical reactions.
Enzyme deficiencies can often translate into life-threatening diseases. For example, a genetic abnormality resulting in the deficiency of the enzyme G6PD...
Enzyme deficiencies can often translate into life-threatening diseases. For example, a genetic abnormality resulting in the deficiency of the enzyme G6PD...
80.8K
Turnover Number and Catalytic Efficiency
9.9K
The turnover number of an enzyme is the maximum number of substrate molecules it can transform per unit time. Turnover numbers for most enzymes range from 1 to 1000 molecules per second. Catalase has the known highest turnover number, capable of converting up to 2.8×106 molecules of hydrogen peroxide into water and oxygen per second. Lysozyme has the lowest known turnover number of half a molecule per second.
Chymotrypsin is a pancreatic enzyme that breaks down proteins during digestion....
Chymotrypsin is a pancreatic enzyme that breaks down proteins during digestion....
9.9K


