基于隐Markov模型的RNA二级结构预测新方法

A Method of RNA Secondary Structure Prediction Based on Hidden Markov Model

有效预测RNA二级结构是生物信息学中的重要研究领域.提出一种基于隐Markov模型预测RNA二级结构的新方法.首先,应用前后缀匹配算法快速找到所有可能(包括假结)的茎区,建立RNA-HMM,寻找最优的茎区组合方法,得到包含假结的RNA二级结构.实验结果表明,提出的新方法降低了计算复杂性,提高了预测的特异性和敏感性,具有较高的准确率,可以预测RNA的假结结构.

The effective prediction of RNA secondary structure is an important research field of bioinformatics.We propose a new method based on hidden Markov model to predict the RNA secondary structure.We appliy the matching algorithm of prefix and suffix to find all the possible（including the pseudo-knot） stem zones quickly,establish the RNA-HMM,find the optimal method of the combination of stem zones,and obtain the RNA secondary structure including the pseudo-knot.The experiment results show that this method can reduce the computational complexity and improve the specificity and sensitivity of prediction with high accuracy,and can also predict the pseudo-knot structure.