A neural network method for identification of RNA-interacting residues in protein.
A neural network method for identification of RNA-interacting residues in protein.
复制标题
DOI：
10.11234/gi1990.15.105
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Euna Jeong;I-Fang Chung;S. Miyano
中科院分区：
文献类型：
--
作者：
Euna Jeong;I-Fang Chung;S. Miyano
蛋白质中与RNA相互作用最强的残基的识别是分子识别领域中一个重要而又具有挑战性的问题。蛋白质-RNA复合物的结构分析揭示了相互作用残基与其结构之间的强相关性。基于这一观点，我们开发了一个神经网络预测器，从蛋白质序列及其结构信息中正确识别参与蛋白质-RNA相互作用的残基。该系统已被详尽的交叉验证与不同的输入编码，输入信息量和网络架构的各种策略。此外，我们已经评估了复杂的功能子集之间的性能。最后，为了反映蛋白质-RNA复合物的性质，我们采用了两种后处理方法。实验结果表明，我们的系统产生了不平凡的性能，虽然在相互作用位点的残基太少。
Identification of the most putative RNA-interacting residues in protein is an important and challenging problem in a field of molecular recognition. Structural analysis of protein-RNA complexes reveals a strong correlation between interaction residues and their structure. Building on this viewpoint, we have developed a neural network predictor to correctly identify residues involved in protein-RNA interactions from protein sequence and its structural information. The system has been exhaustedly cross-validated with various strategies differing in input encoding, amount of input information, and network architectures. In addition, we have evaluated performance among functional subsets of complexes. Finally, to reflect the properties of protein-RNA complexes in our dataset, two kinds of post-processing method are adopted. The experimental result shows that our system yields not-trivial performance although the residues in interaction sites are too scarce.