Centre for Diabetes Research, The Western Australian Institute for Medical Research, Australia.
J Biomed Inform. 2011 Oct;44(5):824-9. doi: 10.1016/j.jbi.2011.04.010. Epub 2011 May 6.
We introduce a novel method for annotating protein function that combines Naïve Bayes and association rules, and takes advantage of the underlying topology in protein interaction networks and the structure of graphs in the Gene Ontology. We apply our method to proteins from the Human Protein Reference Database (HPRD) and show that, in comparison with other approaches, it predicts protein functions with significantly higher recall with no loss of precision. Specifically, it achieves 51% precision and 60% recall versus 45% and 26% for Majority and 24% and 61% for χ²-statistics, respectively.
我们介绍了一种新的蛋白质功能注释方法，该方法结合了朴素贝叶斯和关联规则，并利用蛋白质相互作用网络中的底层拓扑结构和基因本体论中的图结构。我们将该方法应用于人类蛋白质参考数据库（HPRD）中的蛋白质，并表明与其他方法相比，它可以以更高的召回率预测蛋白质功能，而不会降低精度。具体来说，它的精度为 51%，召回率为 60%，而多数法的精度为 45%，召回率为 26%；χ²统计量的精度为 24%，召回率为 61%。
