Protein-protein interactions are important for most biological processes and have been studied for decades. However, the detailed formation mechanism of protein-protein interaction interface is still ambiguous, which makes it difficult to accurately predict the protein-protein interaction interface residue pairs. Here, we extract the interface residue-residue contacts from the decoys in the ZDOCK protein-protein complex decoy set with RMSD mostly larger than 3 Å. To accurately compute the interface residue-residue contacts, we define a new constant called interface residue pairs frequency, which counts the atom contact numbers between two interface residues. We normalize interface residue pairs frequency to pick out the top residue-residue pairs from all the possible pairs preferential to be on correct protein-protein interaction interface. When tested on 37 protein dimers from the decoy set where most decoys are incorrect, our method successfully predicts 30 protein dimers with a success rate of up to 81.1%. Higher accuracy than some other state-of-the-art methods confirmed the performance of our method.

中文翻译：

---

来自噪声蛋白质-蛋白质相互作用数据的新型接触频率指数有助于准确预测界面残基对。

蛋白质-蛋白质相互作用对于大多数生物过程都很重要，并且已经研究了数十年。然而，蛋白质-蛋白质相互作用界面的详细形成机制仍不清楚，这使得难以准确预测蛋白质-蛋白质相互作用界面残基对。在这里，我们从ZDOCK蛋白质-蛋白质复合物诱饵组中的诱饵中提取出界面残基-残基触点，其中RMSD大多大于3Å。为了准确计算界面残基-残基接触，我们定义了一个新的常数，称为界面残基对频率，该常数计算两个界面残基之间的原子接触数。我们对接口残基对频率进行归一化，以从优先在正确的蛋白质-蛋白质相互作用界面上的所有可能对中挑选出顶部残基-残基对。当对大多数诱饵不正确的诱饵组中的37个蛋白二聚体进行测试时，我们的方法成功预测了30个蛋白二聚体，成功率高达81.1％。比其他一些最新方法更高的准确性证实了我们方法的性能。