蛋白质的进化与结构信息对亚叶绿体蛋白定位的预测.pdfVIP

中国科技论文在线 蛋白质的进化与结构信息对亚叶绿体蛋白 定位的预测# 项新媛，李前忠** 5 （内蒙古大学物理科学与技术学院，呼和浩特 010021） 摘要：亚叶绿体定位是蛋白质亚细胞定位更深层次的问题，对研究叶绿体蛋白质的功能及其 与其他大分子的相互作用具有重要的意义。本文计算了亚叶绿体蛋白质的化学位移关联信息 和蛋白质保守位点的进化信息，通过分析和讨论这些特征信息，并结合基于生物过程和分子 功能的 GO 注释，提出了最佳组合参数，利用支持向量机算法对蛋白质亚叶绿体定位进行了 10 预测，Jackknife 检验的预测成功率达到了 87.0%。同时在交叉检验和独立测试下都得到了较 好的预测效果。利用本文提出的最佳组合参数有助于对未知蛋白质序列的检验，特别是对类 囊体蛋白具有一定的影响。 关键词：亚叶绿体定位；化学位移；Gene Ontology；PSSM；支持向量机 中图分类号：Q61 15 Prediction of Protein Subchoroplast Locations Using Evolutionary and Structural Informations XIANG Xinyuan, LI Qianzhong (Physical Science and Technology School,Inner Mongolia University, Hohhot 010021) 20 Abstract: ISubchloroplast location is a deeper study than subcellular location. Knowing a protein’s subchloroplast location provides in-depth insights about the protein’s function and the microenvironment where it interacts with other molecules. In this study, based on the previously constructed database of chloroplast, an approach for predicting protein subchloroplast locations is proposed by combining the average chemical shift, evolutionary information, and gene ontology. 25 The overall prediction accuracy is 87.0% for the subchloroplast location by using the algorithm of the support vector machine in jackknife test. For the independent test and cross-validation, the good prediction results were also obtained, especially for the Tylakoid protein. Keywords: subchloroplast location; chemical shift; gene ontology; PSSM; support vector machine 30