Sharan Roded, Karp Richard M
Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel.
J Comput Biol. 2013 Mar;20(3):249-57. doi: 10.1089/cmb.2012.0241. Epub 2013 Jan 3.
Since the first emergence of protein-protein interaction networks more than a decade ago, they have been viewed as static scaffolds of the signaling-regulatory events taking place in cells, and their analysis has been mainly confined to topological aspects. Recently, functional models of these networks have been suggested, ranging from Boolean to constraint-based methods. However, learning such models from large-scale data remains a formidable task, and most modeling approaches rely on extensive human curation. Here we provide a generic approach to learning Boolean models automatically from data. We apply our approach to growth and inflammatory signaling systems in humans and show how the learning phase can improve the fit of the model to experimental data, remove spurious interactions, and lead to better understanding of the system at hand.
自十多年前首次出现蛋白质-蛋白质相互作用网络以来，它们一直被视为细胞中发生的信号调节事件的静态支架，对其分析主要局限于拓扑方面。最近，有人提出了这些网络的功能模型，范围从布尔方法到基于约束的方法。然而，从大规模数据中学习此类模型仍然是一项艰巨的任务，并且大多数建模方法都依赖于广泛的人工编目。在这里，我们提供了一种从数据中自动学习布尔模型的通用方法。我们将我们的方法应用于人类的生长和炎症信号系统，并展示学习阶段如何提高模型与实验数据的拟合度，去除虚假相互作用，并有助于更好地理解手头的系统。
