Exploring the structural topology of genome-based large-scale metabolic network is essential for in- vestigating possible relations between structure and functionality.Visualization would be helpful for obtaining immediate information about structural organization.In this work,metabolic networks of 75 organisms were investigated from a topological point of view.A spread bow-tie model was proposed to give a clear visualization of the bow-tie structure for metabolic networks.The revealed topological pattern helps to design more efficient algorithm specifically for metabolic networks.This coarse- grained graph also visualizes the vulnerable connections in the network,and thus could have important implication for disease studies and drug target identifications.In addition,analysis on the reciprocal links and main cores in the GSC part of bow-tie also reveals that the bow-tie structure of metabolic networks has its own intrinsic and significant features which are significantly different from those of random networks.
分别采用支持向量学习机、人工神经网络、调节性逻辑回归和K-最临近等机器学习方法对761个二氢叶酸还原酶抑制剂建立了其活性分类预测模型.采用组成描述符和拓扑描述符表征抑制剂的分子结构及物理化学性质,使用Kennard-Stone方法进行训练集的设计,并用Metropolis Monte Carlo模拟退火方法作变量选择.结果表明,支持向量学习机优于其它机器学习方法,所得到的最优模型具有较好的预测结果,其预测正确率为91.62%.说明通过合适的训练集设计及变量选择,支持向量学习机方法可以很好地用于二氢叶酸还原酶抑制剂的活性分类预测.
