Prediction of protein-protein interaction sites using support vector machines
Prediction of protein-protein interaction sites using support vector machines
复制标题
DOI：
10.1093/protein/gzh020
复制
发表时间：
2004-02-01
影响因子：
2.4
通讯作者：
Takagi, T
中科院分区：
文献类型：
--
作者：
Koike, A;Takagi, T
蛋白质相互作用位点的识别对于突变体设计和蛋白质网络预测是必不可少的。使用支持向量机（SVM）和序列/空间相邻残基的配置文件，加上额外的信息，预测残基单元的相互作用位点。当仅使用序列信息时，使用特征向量、顺序相邻概况和预测的相互作用位点比率（通过使用氨基酸组成的SVM回归计算）的预测性能最高。当还使用结构信息时，使用特征向量、空间相邻残基概况、可及表面积以及通过SVM回归和氨基酸组成预测的有/无蛋白质相互作用位点比率，预测性能最高。在后一种情况下，对于同质-异质混合测试集，召回率= 50%时的准确率为54-56%，比随机预测高20%以上。大约30%的残基被错误地预测为相互作用位点，是相互作用位点残基上最接近的顺序/空间相邻残基。预测的残基覆盖86-87%的实际接口（96-97%的接口超过20个残基）。这一预测性能似乎略高于先前报道的研究。比较每个分子的预测精度，似乎更容易预测稳定复合物的相互作用位点。
The identification of protein-protein interaction sites is essential for the mutant design and prediction of protein-protein networks. The interaction sites of residue units were predicted using support vector machines (SVM) and the profiles of sequentially/spatially neighboring residues, plus additional information. When only sequence information was used, prediction performance was highest using the feature vectors, sequentially neighboring profiles and predicted interaction site ratios, which were calculated by SVM regression using amino acid compositions. When structural information was also used, prediction performance was highest using the feature vectors, spatially neighboring residue profiles, accessible surface areas, and the with/without protein interaction sites ratios predicted by SVM regression and amino acid compositions. In the latter case, the precision at recall = 50% was 54-56% for a homo-hetero mixed test set and >20% higher than for random prediction. Approximately 30% of the residues wrongly predicted as interaction sites were the closest sequentially/spatially neighboring on the interaction site residues. The predicted residues covered 86-87% of the actual interfaces (96-97% of interfaces with over 20 residues). This prediction performance appeared to be slightly higher than a previously reported study. Comparing the prediction accuracy of each molecule, it seems to be easier to predict interaction sites for stable complexes.