Hamed Ahmed Abdeen, Wu Xindong, Erickson Robert, Fandy Tamer
Vermont EPSCoR, University of Vermont, Burlington, VT 05401, United States.
Dept. of Computer Science, University of Vermont, Burlington, VT 05401, United States.
J Biomed Inform. 2015 Aug;56:157-68. doi: 10.1016/j.jbi.2015.05.015. Epub 2015 Jun 8.
The importance of searching biomedical literature for drug interaction and side-effects is apparent. Current digital libraries (e.g., PubMed) suffer infrequent tagging and metadata annotation updates. Such limitations cause absence of linking literature to new scientific evidence. This demonstrates a great deal of challenges that stand in the way of scientists when searching biomedical repositories. In this paper, we present a network mining approach that provides a bridge for linking and searching drug-related literature. Our contributions here are two fold: (1) an efficient algorithm called HashPairMiner to address the run-time complexity issues demonstrated in its predecessor algorithm: HashnetMiner, and (2) a database of discoveries hosted on the web to facilitate literature search using the results produced by HashPairMiner. Though the K-H network model and the HashPairMiner algorithm are fairly young, their outcome is evidence of the considerable promise they offer to the biomedical science community in general and the drug research community in particular.
在生物医学文献中搜索药物相互作用和副作用的重要性是显而易见的。当前的数字图书馆（如PubMed）存在标签不频繁和元数据注释更新不及时的问题。这些限制导致文献与新的科学证据无法建立联系。这表明科学家在搜索生物医学知识库时面临诸多挑战。在本文中，我们提出了一种网络挖掘方法，为链接和搜索与药物相关的文献提供了一座桥梁。我们在此的贡献有两个方面：（1）一种名为HashPairMiner的高效算法，以解决其前身算法HashnetMiner中所展示的运行时复杂性问题；（2）一个托管在网络上的发现数据库，以便利用HashPairMiner产生的结果促进文献搜索。尽管K-H网络模型和HashPairMiner算法还相当年轻，但它们的成果证明了它们对整个生物医学科学界，尤其是药物研究界具有巨大的潜力。
