...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Computer-Aided Molecular Design >StackHCV: a web-based integrative machine-learning framework for large-scale identification of hepatitis C virus NS5B inhibitors
【24h】

StackHCV: a web-based integrative machine-learning framework for large-scale identification of hepatitis C virus NS5B inhibitors

机译：StackHCV：一种基于网络的综合机器学习框架，用于大规模识别丙型肝炎病毒NS5B抑制剂

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

Fast and accurate identification of inhibitors with potency against HCV NS5B polymerase is currently a challenging task. As conventional experimental methods is the gold standard method for the design and development of new HCV inhibitors, they often require costly investment of time and resources. In this study, we develop a novel machine learning-based meta-predictor (termed StackHCV) for accurate and large-scale identification of HCV inhibitors. Unlike the existing method, which is based on single-feature-based approach, we first constructed a pool of various baseline models by employing a wide range of heterogeneous molecular fingerprints with five popular machine learning algorithms (k-nearest neighbor, multi-layer perceptron, partial least squares, random forest and support vectors machine). Secondly, we integrated these baseline models in order to develop the final meta-based model by means of the stacking strategy. Extensive benchmarking experiments showed that StackHCV achieved a more accurate and stable performance as compared to its constituent baseline models on the training dataset and also outperformed the existing predictor on the independent test dataset. To facilitate the high-throughput identification of HCV inhibitors, we built a web server that can be freely accessed at . It is expected that StackHCV could be a useful tool for fast and precise identification of potential drugs against HCV NS5B particularly for liver cancer therapy and other clinical applications.
机译：快速准确地鉴定对HCV NS5B聚合酶具有效力的抑制剂目前是一项具有挑战性的任务。由于传统的实验方法是设计和开发新型HCV抑制剂的金标准方法，因此它们通常需要昂贵的时间和资源投入。在这项研究中，我们开发了一种基于机器学习的新型元预测因子（称为StackHCV），用于准确和大规模地鉴定HCV抑制剂。与基于单特征方法的现有方法不同，我们首先通过采用广泛的异质分子指纹和五种流行的机器学习算法（k-最近邻、多层感知器、偏最小二乘法、随机森林和支持向量机）来构建各种基线模型的池。其次，我们整合了这些基线模型，以便通过堆叠策略开发最终的基于元的模型。广泛的基准测试实验表明，与训练数据集上的组成基线模型相比，StackHCV 的性能更准确、更稳定，并且在独立测试数据集上的表现也优于现有的预测变量。为了便于HCV抑制剂的高通量鉴定，我们建立了一个可以自由访问的Web服务器。预计StackHCV可以成为快速精确识别针对HCV NS5B的潜在药物的有用工具，特别是用于肝癌治疗和其他临床应用。

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