RNA二级结构预测的支持向量机模型研究  

The Model Research of Support Vector Machines in the RNA Secondary Structure Prediction

作　　者：何静媛[1] 何中市[1] 邹东升[1] 

机构地区：[1]重庆大学计算机学院,重庆400044

出　　处：《计算机科学》2008年第4期181-183,共3页Computer Science

摘　　要：RNA二级结构预测问题是生物信息学的一个研究重点,本文主要利用支持向量机(SVM)模型来研究RNA二级结构预测问题。通过改进NSSEL标签[4],形成了能表示平面伪结结构的E-NSSEL标签,该标签作为SVM模型输出端的类别标识,因此,测试序列经过SVM模型预测后得到相应的E-NSSEL序列,该序列可以恢复为二级结构。此算法能有效地解决传统算法中存在的时间复杂性的问题和长链分子的预测问题。One of the most important research areas in bioinformatics is RNA secondary structure prediction This paper introduces a new representation of the RNA structure information by emending NSSEL labels, the new labels （E-NSSEL） can express plane pseudoknot. A SVM model is presented to predict RNA secondary structures based on E-NSSEL labels , using this algorithm ,test sequences can be converted to E-NSSEL sequences which can be revert to RNA secondary structures. Experiment shows that this model can solve too long computational time problem of traditional algorithms, at the same time, it can predict long RNA sequences which are difficult with traditional folding algorithms.

关 键 词：SVM E-NSSEL标签 RNA二级结构 平面伪结 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] Q522[自动化与计算机技术—控制科学与工程]