• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Genomics >Pred-BVP-Unb: Fast prediction of bacteriophage Virion proteins using un-biased multi-perspective properties with recursive feature elimination
【24h】

Pred-BVP-Unb: Fast prediction of bacteriophage Virion proteins using un-biased multi-perspective properties with recursive feature elimination

机译：PRED-BVP-UNB：使用未偏置的多透视性能进行递归特征消除的噬菌体病毒蛋白的快速预测

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

摘要

Bacteriophage virion proteins (BVPs) are bacterial viruses that have a great impact on different biological functions of bacteria. They are significantly used in genetic engineering and phage therapy applications. Correct identification of BVP through conventional pathogen methods are slow and expensive. Thus, designing a Bioinformatics predictor is urgently desirable to accelerate correct identification of BVPs within a huge volume of proteins. However, available prediction tools performance is inadequate due to the lack of useful feature representation and severe imbalance issue. In the present study, we propose an intelligent model, called Pred-BVP-Unb for discrimination of BVPs that employed three nominal sequences-driven descriptors, i.e. Bi-PSSM evolutionary information, composition & translation, and split amino acid composition. The imbalance phenomena between classes were coped with the help of a synthetic minority oversampling technique. The essential attributes are selected by a robust algorithm called recursive feature elimination. Finally, the optimal feature space is provided to support vector machine classifier using a radial base kernel in order to train the model. Our predictor remarkably outperforms than existing approaches in the literature by achieving the highest accuracy of 92.54% and 83.06% respectively on the benchmark and independent datasets. We expect that Pred-BVP-Unb tool can provide useful hints for designing antibacterial drugs and also helpful to expedite large scale discovery of new bacteriophage virion proteins. The source code and all datasets are publicly available at https://github.com/Muhammad-Arif-NUST/BVP_Pred_Unb.
机译：噬菌体病毒蛋白蛋白（BVP）是对细菌不同生物功能产生很大影响的细菌病毒。它们显着用于基因工程和噬菌体疗法应用。通过常规病原体方法正确鉴定BVP是缓慢和昂贵的。因此，迫切希望在大量的蛋白质内加速BVP的正确鉴定，设计生物信息性预测器。但是，由于缺乏有用的特征表示和严重的不平衡问题，可用预测工具性能不足。在本研究中，我们提出了一种智能模型，称为Pred-BVP-UNB，用于辨别使用三个标称序列驱动的描述符，即Bi-PSSM进化信息，组成和翻译和分裂氨基酸组合物。在合成少数群体过采样技术的帮助下，课程之间的不平衡现象被应对。基本属性由名为递归特征消除的强大算法选择。最后，提供最佳特征空间以支持矢量机器分类器使用径向基础内核以训练模型。我们的预测仪通过在基准和独立数据集中实现了92.54％和83.06％的最高精度来显着优于文献中的现有方法。我们预计Pred-BVP-UNB工具可以提供用于设计抗菌药物的有用提示，并有助于加快大规模发现新的噬菌体病毒蛋白。源代码和所有数据集在https://github.com/muhammad-arif-nust/bvp_pred_unb上公开可用。

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