在线客服: 点击这里给我发消息  新用户使用步骤:会员注册→充值→重新登入→进入资源
标题:A meta-learning framework using representation learning to predict drug-drug interaction.
时间:2020-02-14 17:31:13
DOI:10.1016/j.jbi.2018.06.015
PMID:29959033
作者:Deepika S.S.; Geetha T.V.
出版源: 《Journal of Biomedical Informatics》 :S1532046418301217-
摘要:Node2vec, a network representation learning method and bagging SVM, a PU learning algorithm, are used in this work. Both representation learning and PU learning algorithms improve the performance of the system by 22% and 12.7% respectively. The meta-classifier performs better and predicts more reliable DDIs than the base classifiers.
大小:1582 kb
页数:13 PAGES
下载: 点击下载
预览:

浏览器不支持嵌入PDF阅读,打开新页面在线阅读

目录:
  • A meta-learning framework using representation learning to predict drug-drug interaction
    • Introduction
      • PU learning
      • Meta-learning
    • Material and methods
      • Dataset description
        • Drug feature data
        • Positive DDIs
      • Proposed work
        • Chemical feature network (CFN)
        • Biological feature network (BFN)
        • Phenotypic feature network (PFN)
        • Therapeutic feature network (TFN)
      • Representation learning
      • PU learning
      • Meta-learning
    • Results
      • Bagging SVM
      • Network embedding
      • Meta-classifier
      • Newly-predicted DDIs
    • Discussion
      • Case study
        • Chemical base classifier
        • Biological base classifier
        • Phenotypic base classifier
        • Therapeutic base classifier
      • Limitations
      • Conclusion
    • Funding
    • References

本页内容由网络收集而来,版权归原创者所有,如有侵权请及时联系