欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
根据氨基酸的物化特性，基于氨基酸组成成分与氨基酸残基指数自相关函数相结合特征提取法，从非同源蛋白质序列中提取7个特征集（COMP、FINA、MAXF、NAKH、BIOV、OOBM、RICJ），采用有先验知识的投票表决特征融合算法融合这7个特征集，对蛋白质结构类进行预测．结果表明，投票表决融合算法的预测总精度及每一类别的预测精度与7个特征集相比较均有不同程度的提高，说明投票表决融合算法在一定程度上能较多地反映蛋白质的空间结构信息．
英文摘要：
According to physicochemical properties of amino acid, the approach of feature extraction of incorporating amino acid composition with different auto-correlation functions has been introduced to predict non-homologous protein structural classes, and seven feature sets（COMP, FINA, MAXF, NAKH, BIOV, OOBM, RICJ ）could be gained. We have combined multiple features using voting based on information algorithm to predict protein structural classes. The comparisons of the predictive results from the fusion of multiple features and each parameter data set show that the total predictive accuracies and each class predictive accuracy are remarkably improved by voting based on information algorithm. To some extent, fusion of multiple features can reflect more protein spatial information.
同期刊论文项目
同项目期刊论文
期刊信息
位置：