【摘要】 随着人类基因组计划的成果和生物信息学的发展,DNA、RNA和蛋白质的数据量空前增长。从这些生物数据中挖掘出有用的知识对于基因组处理尤为重要。其中,通过对DNA序列的分类来预测蛋白质的功能是分子生物研究的一个核心目标。介绍并实现了一种特征提取的方法,并将其应用于神经网络构造分类器,用来对未知类别的DNA序列分类,将分类结果与当前应用广泛的BLAST算法的结果进行比较和分析。更多还原

【Abstract】 With the achievement of the human genome project and the development of bioinformatics, the number of DNA, RNA and protein data accumulates at a surprising rate. It is very important to fetch useful knowledge from these biological data. Predicting the function of protein through the method of classifying DNA sequences is one of the key destinations. The concepts and implementations of a features extraction method are introduced, which is applied into neural network based classifier to classify the unknown DNA series. The comparison between our results and those of widely used BLAST algorithm is also presented.更多还原