首页    期刊浏览 2024年12月12日 星期四
登录注册

文章基本信息

  • 标题:Machine Learning Method To Screen Inhibitors of Virulent Transcription Regulator of Salmonella Typhi
  • 本地全文:下载
  • 作者:Syed Asif Hassan ; Atif Hassan ; Tabrej Khan
  • 期刊名称:International Journal of Advanced Computer Science and Applications(IJACSA)
  • 印刷版ISSN:2158-107X
  • 电子版ISSN:2156-5570
  • 出版年度:2018
  • 卷号:9
  • 期号:2
  • DOI:10.14569/IJACSA.2018.090235
  • 出版社:Science and Information Society (SAI)
  • 摘要:The PhoP regulon, a two-component regulatory system is a well-studied system of Salmonella enterica serotype typhi and has proved to play a crucial role in the pathophysiology of typhoid as well as the intercellular survival of the bacterium within host macrophages. The absence of PhoP regulon in the human system makes regulatory proteins of PhoP regulon for target specific for future drug discovery program against multi-drug resistant strains of Salmonella enterica serotype typhi. In recent years, high-throughput screening method has proven to be a reliable source of hit finding against various diseases including typhoid. However, the cost and time involved in HTS are of significant concern. Therefore, there is still a need for an expedient method which is also reliable in screening active hits molecules as well as less time consuming and inexpensive. In this regards, the application of machine learning (ML) based chemoinformatics model to perform HTS of drug-like hit molecules against MDR strain of Salmonella enterica serotype typhi is the most applicable. In this study, bagging and gradient boosting based ML algorithm was used to build a predictive classification model to perform virtual HTS of active inhibitors of the PhoP regulon of Salmonella enterica serotype typhi. The eXtreme Gradient Boosting (XGBoost) based classification model was comparatively accurate and sensitive in classifying active drug-like inhibitors of PhoP regulon of Salmonella enterica serotype typhi.
  • 关键词:Typhoid; PhoP regulon; classification model; machine learning (ML) algorithm; eXtreme Gradient Boosting; random forest; sensitivity; accuracy
国家哲学社会科学文献中心版权所有