使用蛋白质和mRNA序列信息预测蛋白质亚线粒体定位  

Prediction of Protein Submitochondria Locations Using Protein and mRNA Sequence Information

作　　者：刘娟娟[1] 李前忠[1] 闫振河 薛济先 

机构地区：[1]内蒙古大学物理科学与技术学院,呼和浩特010021

出　　处：《内蒙古大学学报（自然科学版）》2017年第1期69-79,共11页Journal of Inner Mongolia University：Natural Science Edition

基　　金：国家自然科学基金(No.31460234和No.61361015)

摘　　要：线粒体是很重要的半自主性细胞器,主要为细胞提供能量,还承担了许多其他生理功能,而线粒体的某些功能只有在特定亚线粒体位置中才能实现.对亚线粒体定位的研究有助于进一步了解蛋白质的功能.文章计算了蛋白质的进化信息、同源序列的go信息、氨基酸指数信息、氨基酸粘性、氨基酸组分、平均化学位移,并结合mRNA序列的三联体频数,利用支持向量机算法和离散增量算法对蛋白质亚线粒体定位进行预测,在jackknife检验下准确率达到97.64%,同时用独立检验也取得较好的结果.Mitochondria, an important semi-autonomous organelle, mainly provides energy for cells and bears many other physiological functions. But some roles of mitochondria are performed only in a particular submitochondria location. An approach for predicting protein submitochondria locations is proposed by combining evolutionary information, gene ontology of homologous sequences,amino acid indices, stickiness, the average chemical shift, and the frequency of mRNA. The overall prediction accuracy is 97.64% for the submito chondria location by using the algorithm of the support vector machine and increment of diversity in the jackknife test. For the independent test, the good prediction results are also obtained.

关 键 词：亚线粒体定位 同源序列go信息 mRNA三联体频数 支持向量机 离散增量 

分 类 号：Q61[生物学—生物物理学]