• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Bioinformatics and Computational Biology >Prediction of Polyanion Binding Potential in Proteins Using Random Forest
【24h】

Prediction of Polyanion Binding Potential in Proteins Using Random Forest

机译：用随机林预测蛋白质中的聚膜结合电位

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The interactions between polyanions (PAs) and polyanion-binding proteins (PABPs) have been suggested to play significant roles in many essential biological processes. The exact nature of many PA-PABP interactions, however, is just starting to be uncovered. The purpose of this study was to develop Random Forest models to predict DNA and heparin binding capacity of different proteins, based on features such as physicochemical properties, sequence information, function, and localization annotations. The area under receiver operating characteristic curve (AUC) values of 0.831 and 0.719 were achieved for DNA and heparin binding protein classifiers, respectively, suggesting an accurate and reliable classification. After the number of features was reduced from 75 to 15 using a Random Forest based feature selection scheme, the AUC values were decreased to 0.768 for DNA and increased to 0.747 for heparin binding protein classifiers. The study may help in a better understanding of the nature of PA-PABP interactions.
机译：已经提出了多阴离子（PAS）和聚阴离子结合蛋白（PABP）之间的相互作用在许多基本生物过程中起显着作用。然而，许多PA-PABP交互的确切性质刚刚开始被揭露。本研究的目的是开发随机林模型，以预测不同蛋白质的DNA和肝素结合能力，基于诸如物理化学特性，序列信息，功能和定位注释等特征。对于DNA和肝素结合蛋白分类剂，达到了0.831和0.719的接收器操作特性曲线（AUC）值的区域，表明准确且可靠的分类。使用随机林的特征选择方案从75〜15减少特征的数量后，AUC值降至0.768，用于DNA，对于肝素结合蛋白分类器增加至0.747。该研究可能有助于更好地理解PA-PABP相互作用的性质。

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