计算机科学 ›› 2018, Vol. 45 ›› Issue (2): 69-75.doi: 10.11896/j.issn.1002-137X.2018.02.012
• 2017年中国计算机学会人工智能会议 • 上一篇 下一篇
董红斌,石丽,李涛
DONG Hong-bin, SHI Li and LI Tao
摘要： 现有的microRNA预测方法往往存在数据集类不平衡和适用物种单一的问题。针对以上问题,所做主要工作如下:1)提出基于序列熵的分层采样算法,该算法可在保持样本总体分布的基础上,采样生成正样本和负样本数量平衡的训练集；2)提出基于信噪比和相关性的特征选择,用于缩小训练集规模,以达到提高训练速度的目的；3)提出DS-GA算法,用于缩短SVM分类器参数的优化时间,达到减少过拟合的目的；4)结合集成学习的思想,经采样、特征选择、分类器参数优化3个步骤,建立了一种物种间通用的microRNA预测模型。实验表明,该模型有效解决了类不平衡问题,且不局限于单一物种,对混合物种的测试集预测取得了较好效果。
| [1] ERSON-BENSAN A E.Introduction to microRNAs in biological systems[J].Methods in Molecular Biology,2014,1107(1107):1. [2] SAAR M D,ALLMER J.Current limitations for computationalanalysis of microRNA in cancer[J].Pakistan Journal of Clinical and Biomedical Research,2013,1(2):3-5. [3] 刘长征,余佳.microRNA鉴定与功能分析技术[M].北京:化学工业出版社. [4] HATA A,KASHIMA R.Dysregulation of microRNA biogenesis machinery in cancer[J].Critical Reviews in Biochemistry and Molecular Biology,2016,51(3):1-14. [5] REDDY K B.MicroRNA (miRNA) in cancer[J].Cancer Cell International,2015,15(1):1-6. [6] JIANG P,WU H,LU Z H,et al.MiPred:classification of real and pseudo microRNA precursors using random forest prediction model with combined features[J].Nucleic Acids Research,2007,35(Web Server issue):339-444. [7] BENTWICH I,AVNIEL A,KAROV Y,et al.Identification of hundreds of conserved and nonconserved human microRNAs[J].Nature Genetics,2005,7(7):766-870. [8] NG K L,MISHRA S K.De novo SVM classification of precursor microRNAs from genomic pseudo hairpins using global and intrinsic folding measures[J].Bioinformatics,2007,23(11):1321-1330. [9] HUANG Y,ZOU Q,SUN X H,et al.Computational identification of microRNAs and their targets in perennial Ryegrass (Lolium perenne)[J].Applied Biochemistry and Biotechnology,2014,173(4):1011-1122. [10] HUANG Y,CHENG J H,LUO F N,et al.Genome-wide identification and characterization of microRNA genes and their targets in large yellow croaker ( Larimichthys crocea )[J].Gene,2016,576(1):261-267. [11] ZHAO D,WANG Y,LUO D,et al.PMirP:a pre-microRNAprediction method based on structure-sequence hybrid features[J].Artificial Intelligence in Medicine,2010,49(2):127-132. [12] HUANG K Y,LEE T Y,TENG Y C,et al.ViralmiR:a support-vector-machine-based method for predicting viral microRNA precursors[J].BMC Bioinformatics,2015,6(1):1-7. [13] KHALIFA W,YOUSEF M,DEMIRCI M D S,et al.The impact of feature selection on one and two-class classification perfor-mance for plant microRNAs[J].Peerj,2016,4(2):e2135. [14] YOUSEF M,ALLMER J,KHALIFA W.Sequence Motif-Based One-Class Classifiers Can Achieve Comparable Accuracy to Two-Class Learners for Plant microRNA Detection[J].Journal of Biomedical Science & Engineering,2015,8(10):684-694. [15] YOUSEF M,ALLMER J,KHALIFA W.Feature Selection for MicroRNA Target Prediction-Comparison of One-Class Feature Selection Methodologies[C]∥International Conference on Bioinformatics Models,Methods and Algorithms.2016. [16] YOUSEF M,ALLMER J,KHALIFA W.Accurate Plant Mi-croRNA Prediction Can Be Achieved Using Sequence Motif Features[J].Journal of Intelligent Learning Systems & Applications,2016,8(1):9-22. [17] ZHONG L,WANG J T L,WEN D,et al.Effective Classification of MicroRNA Precursors Using Feature Mining and AdaBoost Algorithms[J].Omics A Journal of Integrative Biology,2013,17(9):486-493. [18] CEVIK N,SAKAR C O,KURSUN O.Analysis of Relations Between Shared miRNAs of Different Species Using Canonical Correlation Analysis[C]∥International Conference on Applied Informatics and Health and Life Sciences.2013:1980-1989. [19] CEVIK N,SAKAR C O,KURSUN O.Analysis of shared miRNAs of different species using ensemble CCA and genetic distance[J].Computers in Biology & Medicine,2015,64:261-267. [20] XU J C,LI T,SUN L,et al.Feature selection method based on signal-to-noise ratio and neighborhood rough set [J].Journal of Data Acquisition and Processing,2015,30(5):973-981.(in Chinese) 徐久成,李涛,孙林,等.基于信噪比与邻域粗糙集的特征基选择方法[J].数据采集与处理,2015,30(5):973-981. |
| No related articles found! |
|
||
首页