结合多数据源预测蛋白质复合物

Predicting protein complex via integration of multiply data sources

蛋白质相互作用数据具有较高的假阳性率和假阴性率,这直接导致计算方法从中预测蛋白质复合物会产生较大的误差。为了弥补数据的这种先天性不足,通过结合多数据源,一种新的蛋白质复合物预测算法被提出。匹配分析和GO功能富集分析被用于评估算法的性能。测试结果表明,新算法远优于以前的其他算法。

The computational methods used to predict protein complexes from the protein interaction network have a great error because of the high false positive rate and false negative rate of protein interaction data. To compensate for this, a new protein complex prediction approach is proposed via the integration of multiply data sources. Match- ing analysis and GO functional enrichment analysis are performed as so to estimate the performance of the algo- rithm. The results show that the new algorithm is much better than previous ones.