分析和比较了五种蛋白质复合物预测的典型计算方法,并讨论了该领域一些有希望的研究方向。实验结果显示各种计算方法预测出的复合物能较好地匹配真实的复合物。如果恰当地考虑蛋白质相互作用数据的质量而将数据源的噪声最小化并将各种生物特征结合到预测过程中去,计算方法的性能将进一步改善。
This paper analysized and compared the five state-of-the-art techniques for computational prediction of protein complexes,and discussed some promising research directions in this field.Experimental results show that the complexs predicted by the five computational methods match well with actual protein complexes.Further improvements can be achieved if the quality of the underlying protein interaction data can be considered adequately to minimize noisy sources,and the various biological evidences can be better incorporated into the prediction process.