Wu Guang, Yan Shaomin
Computational Mutation Project, DreamSciTech Consulting, Nanyou A-zone, Jiannan Road, Shenzhen, Guangdong Province, China.
Mol Divers. 2007 Aug-Nov;11(3-4):131-40. doi: 10.1007/s11030-008-9067-y. Epub 2008 Feb 19.
Recently, we defined the randomness within a protein as an important force engineering mutations. Thereafter we build a cause-mutation relationship, where one side is the quantified randomness and the other side is the occurrence or non-occurrence of mutation. This way, we switch the prediction of mutation into the problem of classification, which can be solved using either logistic regression or neural network. Very recently, we attempted to apply the logistic regression to predicting the mutation positions in proteins from influenza A virus. In this study, we attempt to explore the possibility of applying the neural network to predicting the mutation positions in H1 neuraminidase from influenza A virus. Then we applied the amino-acid mutating probability to predicting the would-be-mutated amino acids at predicted positions. The results confirm the possibility of prediction of mutation using this approach and pave the way for future development.
最近，我们将蛋白质内部的随机性定义为驱动突变的一种重要力量。此后，我们建立了一种因果突变关系，其中一方是量化的随机性，另一方是突变的发生或不发生。通过这种方式，我们将突变预测转换为分类问题，可以使用逻辑回归或神经网络来解决。就在最近，我们尝试将逻辑回归应用于预测甲型流感病毒蛋白质中的突变位置。在本研究中，我们试图探索将神经网络应用于预测甲型流感病毒H1神经氨酸酶中突变位置的可能性。然后，我们将氨基酸突变概率应用于预测预测位置处可能发生突变的氨基酸。结果证实了使用这种方法进行突变预测的可能性，并为未来的发展铺平了道路。
