| 一个大数据库中预测蛋白质二级结构 |
| |
| 引用本文： | 冯永娥,罗辽复. 一个大数据库中预测蛋白质二级结构[J]. 内蒙古农业大学学报(自然科学版), 2012, 33(1): 225-230 |
| |
| 作者姓名： | 冯永娥 罗辽复 |
| |
| 作者单位： | 1. 内蒙古农业大学理学院,呼和浩特,0100182
2. 内蒙古大学物理科学与技术学院,呼和浩特,010021 |
| |
| 基金项目： | 内蒙古农业大学博士科研启动基金,内蒙古农业大学科技创新团队 |
| |
| 摘 要： | 本文在1个大数据库中采用广义的2次判别法来预测蛋白质二级结构.在包含2640个蛋白的数据库中,先是定义4肽结构字,然后利用3种4肽结构字建立多样性源同时结合二次判别法来预测21残基片段中心残基的二级结构,最后在误差允许范围内对预测结果进行修正,自治检验和独立检验的三态预测精度均超过83％.在同样的数据库中,与其它预测软件相比较,显示了我们的方法是占优势的.
|
| 关 键 词： | 蛋白质二级结构 4肽结构字 多样性增量 二次判别法 允许误差范围 |
THE PREDICTION OF PROTEIN SECONDARY STRUCTURE IN A LARGE DATASET |
| |
| FENG Yong-e , LUO Liao-fu. THE PREDICTION OF PROTEIN SECONDARY STRUCTURE IN A LARGE DATASET[J]. Journal of Inner Mongolia Agricultural University(Natural Science Edition), 2012, 33(1): 225-230 |
| |
| Authors: | FENG Yong-e LUO Liao-fu |
| |
| Affiliation: | 1.College of Science,Inner Mongolia Agriculture University,Hohhot,010018 China 2.School of Physical Science and Technology,Inner Mongolia University,Hohhot,010021 China) |
| |
| Abstract: | In this article the secondary structure of protein is tested with a large dataset of 2640 protein.The method is based on tetra-peptide structural words.We have used the method of Increment of Diversity combined with Quadratic Discriminant analysis(for short IDQD) to predict the structure of central residue for a sequence fragment.The accuracy of Q3=83% is achieved in the self-consistency test and independent test in 2640 proteins in error allowed scope.Compared to the other prediction software,the result shows that our method more effectively in the same database. |
| |
| Keywords: | Protein secondary structure Tetra-peptide structural words Increment of diversity Quadratic discriminant analysis in error allowed scope |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
