Yan Shaomin, Wu Guang
State Key Laboratory of Nonfood Biomass Enzyme Technology, National Engineering Research Center for Non-food Biorefinery, Guangxi Academy of Sciences, 98 Daling Road, Nanning, Guangxi, 530007, China.
Protein Pept Lett. 2011 Oct;18(10):1053-7. doi: 10.2174/092986611796378747.
In this study, we attempted to use the neural network to model a quantitative structure-K(m) (Michaelis-Menten constant) relationship for beta-glucosidase, which is an important enzyme to cut the beta-bond linkage in glucose while K(m) is a very important parameter in enzymatic reactions. Eight feedforward backpropagation neural networks with different layers and neurons were applied for the development of predictive model, and twenty-five different features of amino acids were chosen as predictors one by one. The results show that the 20-1 feedforward backpropagation neural network can serve as a predictive model while the normalized polarizability index as well as the amino-acid distribution probability can serve as the predictors. This study threw lights on the possibility of predicting the K(m) in beta-glucosidases based on their amino-acid features.
在本研究中，我们尝试使用神经网络为β-葡萄糖苷酶建立定量结构 - K(m)（米氏常数）关系模型，β-葡萄糖苷酶是一种在葡萄糖中切断β-键连接的重要酶，而K(m)是酶促反应中一个非常重要的参数。应用八个具有不同层数和神经元的前馈反向传播神经网络来开发预测模型，并逐一选择二十五个不同的氨基酸特征作为预测因子。结果表明，20 - 1前馈反向传播神经网络可作为预测模型，而归一化极化率指数以及氨基酸分布概率可作为预测因子。本研究揭示了基于β-葡萄糖苷酶的氨基酸特征预测其K(m)的可能性。
