基于特征融合的选择性剪切外显子预测  

Prediction of Alternative Splicingof Exons Based on Multi-features Fusion

作　　者：袁芳[1] 范金坪[1] 

机构地区：[1]深圳信息职业技术学院,深圳518172

出　　处：《计算机与数字工程》2014年第11期2059-2062,2065,共5页Computer & Digital Engineering

基　　金：广东省自然科学基金(编号:S2012010010206)资助

摘　　要：基因在转录的过程中,mRNA前体常常会经过一个选择性剪切的过程,它包括多种选择性剪切形式。选择性剪切的鉴别在生命科学的研究和医学上都有重要意义。由于选择性剪切的内在限制,同类的预测选择性剪切的模型或者算法只能预测出特殊的选择性剪切事件的类别。本文在研究序列本身特征的基础上,考虑了碱基的保守性,并结合支持向量机建立的预测模型对选择性剪切外显子进行预测。性能测试结果显示,相比同类预测模型该方法在性能方面有了一定提高。Lternative splicing is a regulated process during gene expression that results in a single gene coding for multi- pie proteins. Identification of alternative splicing has important significance in the study of life and medical science. Due to the inherent limitations of alternative splicing, the existing method of predicting alternative splicing can only suit for special alternative splicing cases. Here, in addition to sequence inherent characteristics, the nucleotide conservation is studied based on the characteristics. Combined with support vector machine, a new model is established to predict the alternative splicing of exon. And, the test results show that the performance of CI^Miner is satisfactory.

关 键 词：选择性剪切外显子 支持向量机 保守性分值统计 

分 类 号：Q343.1[生物学—遗传学]