|
|||||
|
|
| 基于级联神经网络的蛋白质二级结构预测 | |
| 引用本文： | 王艳春,何东健,王守志.基于级联神经网络的蛋白质二级结构预测[J].计算机工程,2010,36(4):22-24. |
| 作者姓名： | 王艳春 何东健 王守志 |
| 作者单位： | 1. 西北农林科技大学机械与电子工程学院,杨陵,712100;青岛农业大学信息科学与工程学院,青岛,266109 2. 西北农林科技大学信息工程学院,杨陵,712100 3. 威海职业学院机电工程系,威海,264210 |
| 基金项目： | 国家自然科学基金资助项目(30471138) |
| 摘 要： | 为提高蛋白质二级结构预测的精度，提出一种由两层网络构成的级联神经网络模型。第1层网络采用具有差异度的5个子网构成的网络模型，对第2层网络的输入编码进行改进。对PDBSelect25中的36条蛋白质共6 122个残基进行测试，结果表明，该模型能有效预测蛋白质二级结构，其预测精度分别比SNN, DSC, PREDSATOR方法提高5.31%, 1.21%和0.92%，平均预测精度提高到69.61%。 |
| 关 键 词： | 神经网络 蛋白质 二级结构预测 |
| 修稿时间： | |
Protein Secondary Structure Prediction Based on Cascade Neural Networks |
|
| WANG Yan-chun,HE Dong-jian,WANG Shou-zhi.Protein Secondary Structure Prediction Based on Cascade Neural Networks[J].Computer Engineering,2010,36(4):22-24. | |
| Authors: | WANG Yan-chun HE Dong-jian WANG Shou-zhi |
| Affiliation: | (1. College of Mechanical and Electronic Engineering, Northwest A & F University, Yangling 712100; 2. College of Information Science and Engineering, Qingdao Agricultural University, Qingdao 266109; 3. College of Information Engineering, Northwest A & F University, Yangling 712100; 4. Department of Mechanical and Electronic Engineering, Weihai Vocational College, Weihai 264210) |
| Abstract: | In order to improve the prediction accuracy of protein secondary structure, a cascade neural networks composed of two-level network is presented. The first level is composed of five subnets with different structure, and the coding method of the second-level is studied and improved. The model is employed to predict 36 nonhomologous protein sequences with 6 122 residues in PDBSelect25. Results show that the proposed model can efficiently improve the prediction accuracy, increasing the prediction accuracy by 5.31%, 1.21% and 0.92% respectively compared with SNN, DSC and PREDSATOR method, improving the average prediction accuracy to 69.61%. |
| Keywords: | neural networks protein secondary structure prediction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《计算机工程》浏览原始摘要信息 | |
| 点击此处可从《计算机工程》下载全文 | |