基于机器学习的RNA编辑位点预测方法综述  

Review:prediction of RNA editing sites based on machine learning

作　　者：冷嘉承 吴凌云[1,2] LENG Jiacheng;WU Lingyun(Academy of Mathematics and Systems Science, Institute of Applied Mathematics, Chinese Academy of Science, Key Laboratory of Management, Decision and Information Systems, National Center for Mathematics and Interdisciplinary Sciences, Beijing 100190, China;School of Mathematics Sciences, University of Chinese Academy of Sciences, Beijing 100049, China)

机构地区：[1]中国科学院数学与系统科学研究院应用数学研究所,管理,决策与信息系统重点实验室,国家数学与交叉科学中心,北京100190 [2]中国科学院大学数学科学学院,北京100049

出　　处：《生物信息学》2019年第1期1-8,共8页Chinese Journal of Bioinformatics

基　　金：国家自然科学基金(No.11631014; No.91730301;No.11661141019)

摘　　要：RNA编辑是一个十分重要的生物细胞分子机制。作为转录后修饰的一步,它可以增加蛋白质组学多样性,改变转录产物的稳定性,调节基因表达等。RNA编辑失调会导致各种疾病,包括神经疾病和癌症。在动物中,腺苷到肌苷(A-to-I)的编辑是最普遍的。高通量测序技术的进步大大提高了在全局范围内检测和量化RNA编辑的能力,使得RNA编辑的大规模全基因组分析变得可行,产生了一系列基于高通量测序技术的RNA编辑位点预测方法。通过对这些方法进行介绍、总结和分析,为RNA编辑的进一步研究提供一些思路。RNA editing is an important molecular mechanism of biological cells. As a step of post-transcriptional modification, it can increase proteomic diversity, alter the stability of transcription products, regulate gene expression, and so on. RNA editing disorders can lead to a variety of diseases, including neurological diseases and cancer. Among animals, the editing of adenosine to inosine (A-to-I) is the commonest. Advances in high-throughput sequencing technology have greatly improved the ability to detect and quantify RNA editing globally, which can make large-scale genome-wide analysis of RNA editing feasible, thereby resulting in a series of prediction methods of RNA editing sites based on high-throughput sequencing technology. This article will introduce and summarize these methods and provide new perspectives for further research of RNA editing.

关 键 词：RNA编辑 高通量测序 A-to-I 机器学习 

分 类 号：Q522.6[生物学—生物化学]