Department of Biomedical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran.
Comput Methods Programs Biomed. 2010 Dec;100(3):237-47. doi: 10.1016/j.cmpb.2010.04.005. Epub 2010 May 15.
The supervised learning of recurrent neural networks well-suited for prediction of protein secondary structures from the underlying amino acids sequence is studied. Modular reciprocal recurrent neural networks (MRR-NN) are proposed to model the strong correlations between adjacent secondary structure elements. Besides, a multilayer bidirectional recurrent neural network (MBR-NN) is introduced to capture the long-range intramolecular interactions between amino acids in formation of the secondary structure. The final modular prediction system is devised based on the interactive integration of the MRR-NN and the MBR-NN structures to arbitrarily engage the neighboring effects of the secondary structure types concurrent with memorizing the sequential dependencies of amino acids along the protein chain. The advanced combined network augments the percentage accuracy (Q₃) to 79.36% and boosts the segment overlap (SOV) up to 70.09% when tested on the PSIPRED dataset in three-fold cross-validation.
研究了从潜在氨基酸序列预测蛋白质二级结构的循环神经网络的监督学习。提出了模块化递归神经网络（MRR-NN）来模拟相邻二级结构元素之间的强相关性。此外，还引入了多层双向递归神经网络（MBR-NN）来捕获二级结构形成过程中氨基酸之间的长程分子内相互作用。基于 MRR-NN 和 MBR-NN 结构的交互式集成，设计了最终的模块化预测系统，以任意参与二级结构类型的邻近效应，同时记忆沿蛋白质链的氨基酸的顺序依赖性。在 PSIPRED 数据集的三折交叉验证中，该先进的组合网络将准确率（Q₃）提高到 79.36%，将片段重叠率（SOV）提高到 70.09%。
