Discriminative random field approach to prediction of protein residue contacts
Discriminative random field approach to prediction of protein residue contacts
复制标题
DOI：
10.1109/isb.2011.6033167
复制
发表时间：
2011-10
期刊：
影响因子：
--
通讯作者：
M. Kamada;M. Hayashida;Jiangning Song;T. Akutsu
中科院分区：
文献类型：
--
作者：
M. Kamada;M. Hayashida;Jiangning Song;T. Akutsu
了解蛋白质的相互作用对于揭示分子网络和功能具有重要意义。已经进行了许多研究来分析残留物之间的相互作用和接触。支持相互作用位点的残基与伴侣蛋白中相应残基的残基共同进化以保持蛋白质之间的相互作用。因此，从同源蛋白质的多个序列比对计算的残基之间的互信息（MI）被认为是有用的识别相互作用蛋白质中的接触残基。在我们以前的工作中，我们提出了一种预测方法，蛋白质-蛋白质相互作用的互信息和条件随机场（CRF），并证实了它的实用性。判别随机场（DRF）是一种特殊的随机场，可以识别图像中的某些特定特征区域。由于两个相互作用的蛋白质中残基之间的互信息矩阵可以看作是一个图像，我们提出了一种预测方法，蛋白质残基接触的DRF模型与互信息。为了验证我们的方法，我们进行计算实验几个Pfam域之间的相互作用。结果表明，建议的DRF为基础的方法与MI是有用的预测蛋白质残基接触相比，使用相应的马尔可夫随机场（MRF）模型。
Understanding of interactions of proteins is important to reveal networks and functions of molecules. Many investigations have been conducted to analyze interactions and contacts between residues. It is supported that residues at interacting sites have co-evolved with those at the corresponding residues in the partner protein to keep the interactions between the proteins. Therefore, mutual information (MI) between residues calculated from multiple sequence alignments of homologous proteins is considered to be useful for identifying contact residues in interacting proteins. In our previous work, we proposed a prediction method for protein-protein interactions using mutual information and conditional random fields (CRFs), and confirmed its usefulness. The discriminative random field (DRF) is a special type of CRFs, and can recognize some specific characteristic regions in an image. Since the matrix consisted of mutual information between residues in two interacting proteins can be regarded as an image, we propose a prediction method for protein residue contacts using DRF models with mutual information. To validate our method, we perform computational experiments for several interactions between Pfam domains. The results suggest that the proposed DRF-based method with MI is useful for predicting protein residue contacts compared with that using the corresponding Markov random field (MRF) model.