...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Bioinformatics and Computational Biology >PROTEIN FOLD CLASSIFICATION WITH GENETICALGORITHMS AND FEATURE SELECTION
【24h】

PROTEIN FOLD CLASSIFICATION WITH GENETICALGORITHMS AND FEATURE SELECTION

机译：用遗传算法对蛋白质进行折叠分类和特征选择

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Protein fold classification is a key step to predicting protein tertiary structures. Thispaper proposes a novel approach based on genetic algorithms and feature selection toclassifying protein folds. Our dataset is divided into a training dataset and a test dataset.Each individual for the genetic algorithms represents a selection function of the featurevectors of the training dataset. A support vector machine is applied to each individualto evaluate the fitness value (fold classification rate) of each individual. The aim ofthe genetic algorithms is to search for the best individual that produces the highestfold classification rate. The best individual is then applied to the feature vectors ofthe test dataset and a support vector machine is built to classify protein folds based onselected features. Our experimental results on Ding and Dubchak's benchmark dataset of27-class folds show that our approach achieves an accuracy of 71.28%, which outperformscurrent state-of-the-art protein fold predictors.
机译：蛋白质折叠分类是预测蛋白质三级结构的关键步骤。本文提出了一种基于遗传算法和特征选择对蛋白质折叠进行分类的新颖方法。我们的数据集分为训练数据集和测试数据集。每个遗传算法的个体代表训练数据集特征向量的选择函数。将支持向量机应用于每个个体，以评估每个个体的适应度值（分类率）。遗传算法的目的是寻找产生最高分类率的最佳个体。然后将最佳个体应用于测试数据集的特征向量，并构建支持向量机，根据所选特征对蛋白质折叠进行分类。我们在Ding和Dubchak的27类折痕基准数据集上的实验结果表明，我们的方法达到了71.28％的准确度，胜过当前最新的蛋白质折痕预测因子。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号