期刊论文

High-accuracy Splice Site Prediction Based on Statistical Difference Table and Weighted Voting

Yuan Zhe-Ming

中文

生物化学与生物物理进展

1000-3282

2019

46

5

496-503

10.16476/j.pibb.2018.0267

National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61701177]; Hunan Provincial Natural Science Foundation of ChinaNatural Science Foundation of Hunan Province [2018JJ3225]; Scientific Research Project of Hunan Province Education Office [17A096]

本校为第一且通讯机构

基于机器学习的高精度剪接位点识别是真核生物基因组注释的关键.本文采用卡方测验确定序列窗口长度,构建卡方统计差表提取位置特征,并结合碱基二联体频次表征序列;针对剪接位点正负样本高度不均衡这一情形,构建10个正负样本均衡的支持向量机分类器,进行加权投票决策,有效解决了不平衡模式分类问题. HS3D数据集上的独立测试结果显示,供体、受体位点预测准确率分别达到93.39%、90.46%,明显高于参比方法.基于卡方统计差表的位置特征能有效表征DNA序列,在分子序列信号位点识别中具有应用前景.

High-accuracy splice site recognition based on machine learning is the key to eukaryotic genome annotation. In this paper, we used chi-square test to determine the window size of sequences, and constructed a chi-square statistical difference table to extract the positional features, and combined with the frequencies of dinucleotides to characterize sequences. For the problem that the positive and negative samples of splice sites are extremely imbalanced, 10 SVM classifiers based on the equal proportion of positive and negative samples were buil...