期刊
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
卷 11, 期 5, 页码 775-787出版社
IEEE COMPUTER SOC
DOI: 10.1109/TCBB.2014.2325031
关键词
Link prediction; collective inference; heterogeneous similarities; drug target prediction; drug target interaction prediction; drug repurposing; drug discovery; polypharmacology; drug adverse effect prediction; statistical relational learning; hinge-loss Markov random fields; machine learning; bipartite networks; systems biology
类别
资金
- US National Science Foundation (NSF) [IIS0746930, CCF0937094, IIS1218488, DBI1147144]
- Div Of Biological Infrastructure
- Direct For Biological Sciences [1147144] Funding Source: National Science Foundation
Drug-target interaction studies are important because they can predict drugs' unexpected therapeutic or adverse side effects. In silico predictions of potential interactions are valuable and can focus effort on in vitro experiments. We propose a prediction framework that represents the problem using a bipartite graph of drug-target interactions augmented with drug-drug and target-target similarity measures and makes predictions using probabilistic soft logic (PSL). Using probabilistic rules in PSL, we predict interactions with models based on triad and tetrad structures. We apply (blocking) techniques that make link prediction in PSL more efficient for drug-target interaction prediction. We then perform extensive experimental studies to highlight different aspects of the model and the domain, first comparing the models with different structures and then measuring the effect of the proposed blocking on the prediction performance and efficiency. We demonstrate the importance of rule weight learning in the proposed PSL model and then show that PSL can effectively make use of a variety of similarity measures. We perform an experiment to validate the importance of collective inference and using multiple similarity measures for accurate predictions in contrast to non-collective and single similarity assumptions. Finally, we illustrate that our PSL model achieves state-of-the-art performance with simple, interpretable rules and evaluate our novel predictions using online data sets.
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