Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina, United States of America.
PLoS One. 2011;6(10):e25560. doi: 10.1371/journal.pone.0025560. Epub 2011 Oct 3.
Computational identification of heme-binding residues is beneficial for predicting and designing novel heme proteins. Here we proposed a novel method for heme-binding residue prediction by exploiting topological properties of these residues in the residue interaction networks derived from three-dimensional structures. Comprehensive analysis showed that key residues located in heme-binding regions are generally associated with the nodes with higher degree, closeness and betweenness, but lower clustering coefficient in the network. HemeNet, a support vector machine (SVM) based predictor, was developed to identify heme-binding residues by combining topological features with existing sequence and structural features. The results showed that incorporation of network-based features significantly improved the prediction performance. We also compared the residue interaction networks of heme proteins before and after heme binding and found that the topological features can well characterize the heme-binding sites of apo structures as well as those of holo structures, which led to reliable performance improvement as we applied HemeNet to predicting the binding residues of proteins in the heme-free state. HemeNet web server is freely accessible at http://mleg.cse.sc.edu/hemeNet/.
计算鉴定血红素结合残基有利于预测和设计新型血红素蛋白。在这里，我们提出了一种新的方法，通过利用从三维结构得出的残基相互作用网络中这些残基的拓扑性质来预测血红素结合残基。综合分析表明，位于血红素结合区域的关键残基通常与网络中具有较高度数、接近度和介数、但聚类系数较低的节点相关。HemeNet 是一种基于支持向量机（SVM）的预测器，通过将拓扑特征与现有序列和结构特征相结合，用于识别血红素结合残基。结果表明，结合网络特征显著提高了预测性能。我们还比较了血红素结合前后血红素蛋白的残基相互作用网络，发现拓扑特征可以很好地表征apo 结构以及 holo 结构的血红素结合位点，这使得我们将 HemeNet 应用于预测无血红素状态下蛋白质的结合残基时，能够可靠地提高性能。HemeNet 网络服务器可免费访问：http://mleg.cse.sc.edu/hemeNet/。
