期刊
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
卷 18, 期 6, 页码 2733-2740出版社
IEEE COMPUTER SOC
DOI: 10.1109/TCBB.2020.2976997
关键词
Drugs; Cancer; Chemicals; Predictive models; Computational modeling; Genomics; Bioinformatics; Drug response prediction; drug; cell line
类别
资金
- Natural Science Foundation of Heilongjiang Province [F2016016]
- National Key Research and Development Program of China [2016YFC0901905]
Due to the high consumption of cost and time for experimental verification in clinical trials, computational models for drug response prediction have become increasingly important. Our proposed method WMMDCA considers chemical structural features of drugs and adds modular information to predict drug-cell line associations, showing superior performance compared to other state-of-the-art methods.
Due to the high consumption of cost and time for experimental verification in clinical trials, drug response prediction by computational models have become important challenges. The existing drug response data in diverse cell lines enable prediction of potential sensitive associations. Here, we propose a weight-based modular mapping method, named as WMMDCA, to predict drug-cell line associations. The method fully considers the effects of drugs' chemical structural feature, and adds modular information into the network projection. Leave-one-out cross-validation was used to evaluate the predictive ability of WMMDCA, which showed the best performance among several state-of-the-art methods in not only the whole dataset but also the major tissue types of cell lines. Literature support of highly ranked potential associations was found manually, demonstrating the effectiveness of WMMDCA on drug response prediction.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据