RocSampler: Regularizing overlapping protein complexes in protein-protein interaction networks
RocSampler: Regularizing overlapping protein complexes in protein-protein interaction networks
复制标题
RocSampler：规范蛋白质-蛋白质相互作用网络中的重叠蛋白质复合物
DOI：
10.1109/iccabs.2016.7802774
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Osamu Maruyama and Yuki Kuwahara
中科院分区：
文献类型：
--
作者：
Osamu Maruyama;Osamu Maruyama and Yuki Kuwahara
研究背景蛋白质相互作用（Protein-protein interaction，PPI）网络是研究多种生物学过程和细胞机制的重要资源。在本文中，我们解决了从PPI网络预测蛋白质复合物的问题。这个问题有两个难点。一种是与包含两个或三个组分的小络合物有关。由于它们的内部结构较简单，识别它们相对困难，但不幸的是，这种大小的复合物在主要的蛋白质复合物数据库中占主导地位，如CYC 2008。另一个困难是如何对预测复合物之间的重叠进行建模，即如何评估共享共同蛋白质的不同预测复合物，因为CYC 2008和其他数据库包括此类蛋白质复合物。因此，它是至关重要的，如何建模预测复合物之间的重叠，以确定它们同时。ResultsIn本文中，我们提出了一种基于采样的蛋白质复合物预测方法，RocSampler（正则化重叠复合物），它利用，作为整个评分函数的一部分，预测复合物的重叠和预测复合物的大小分布的正则化项。我们已经在MATLAB中实现了RocSampler，其Windows可执行文件可在网站上获得， http://imi.kyushu-u.ac.jp/~om/software/RocSampler/ 结论我们将RocSampler应用于5个酵母PPI网络，并表明它上级其他现有的方法。这意味着包含正则化项的评分函数的设计是一种有效的蛋白质复合物预测方法。
BackgroundIn recent years, protein-protein interaction (PPI) networks have been well recognized as important resources to elucidate various biological processes and cellular mechanisms. In this paper, we address the problem of predicting protein complexes from a PPI network. This problem has two difficulties. One is related to small complexes, which contains two or three components. It is relatively difficult to identify them due to their simpler internal structure, but unfortunately complexes of such sizes are dominant in major protein complex databases, such as CYC2008. Another difficulty is how to model overlaps between predicted complexes, that is, how to evaluate different predicted complexes sharing common proteins because CYC2008 and other databases include such protein complexes. Thus, it is critical how to model overlaps between predicted complexes to identify them simultaneously.ResultsIn this paper, we propose a sampling-based protein complex prediction method, RocSampler (Regularizing Overlapping Complexes), which exploits, as part of the whole scoring function, a regularization term for the overlaps of predicted complexes and that for the distribution of sizes of predicted complexes. We have implemented RocSampler in MATLAB and its executable file for Windows is available at the site, http://imi.kyushu-u.ac.jp/~om/software/RocSampler/ .ConclusionsWe have applied RocSampler to five yeast PPI networks and shown that it is superior to other existing methods. This implies that the design of scoring functions including regularization terms is an effective approach for protein complex prediction.