正在加载图片...
第6期 刘晓燕，等：一种预测mRNA与疾病关联关系的矩阵分解算法 ·903· 可以看到，在>100时，AUC值基本趋于稳 regulation of cell death[J].Trends in genetics,2004, 定。而对=100维这样的子空间来说，单独的常 20(12):617-624 数维并不会对结果有很大的影响，于是删除了假 [8]YOU Zhuhong,HUANG Zhian,ZHU Zexuan,et al.PBM- 设的先验关联值，最终确定了预测模型。 DA:a novel and effective path-based computational mod- el for miRNA-disease association prediction[J].PLoS com- 6结论 putational biology,2017,13(3):e1005455. [9]SHI Hongbo,ZHANG Guangde,ZHOU Meng,et al.In- 本文基于矩阵分解和迭代最小二乘的方法 tegration of multiple genomic and phenotype data to infer (LMFMDA)对miRNAs和疾病的关联关系进行预 novel miRNA-disease associations[J].PLoS one,2016. 测。首先对miRNAs相似度矩阵、疾病相似度矩 11(2):e0148521. 阵和miRNAs-疾病关联关系进行数据融合，采用 [10]JIANG Qinghua,HAO Yangyang,WANG Guohua,et al. 迭代最小二乘法求解miRNAs和疾病的表达向 Prioritization of disease microRNAs through a human 量，最后利用miRNAs和疾病的表达向量完成对 phenome-microRNAome network[J].BMC systems bio- mmiRNA与疾病关联关系的预测。同时，通过引人 1ogy,2010,4S1):S2. 辅助miRNAs和疾病变量的方法，解决了收敛结 [11]JIANG Qinghua,WANG Guohua,WANG Yadong.An 果的最优问题。实验显示，LMFMDA在高关联疾 approach for prioritizing disease-related microRNAs 病和新疾病预测中相对于其他方法均取了较优的 based on genomic data integration[Cl//Proceedings of the 结果。 3rd International Conference on Biomedical Engineering 综上，本文提出的miRNA与疾病关联预测算 and Informatics.Yantai,China,2010:2270-2274. 法LMFMDA,一方面可以处理未知相关miRNAs [12]CHEN Xing,LIU Mingxi,YAN Guiying.RWRMDA: 的疾病、或者未知相关疾病的miRNAs;另一方 predicting novel human microRNA-disease associ- 面，实验结果也表明，LMFMDA算法在miRNAs ations[J].Molecular biosystems,2012,8(10):2792-2798. 和疾病的关联关系预测上相较其他算法有更好的 [13]CHEN Hailin,ZHANG Zuping.Similarity-based meth- 效果。 ods for potential human microRNA-disease association prediction[J].BMC medical genomics,2013,6:12 参考文献： [14]SHI Hongbo,XU Juan,ZHANG Guangde,et al.Walking the interactome to identify human miRNA-disease associ- [1]WANG Qianghu,SUN Jie,ZHOU Meng,et al.A novel ations through the functional link between miRNA tar- network-based method for measuring the functional rela- gets and disease genes[J].BMC systems biology,2013,7: tionship between gene sets[J].Bioinformatics,2011, 101. 27(11):1521-1528 [2]LV Sali,LI Yan,WANG Qianghu,et al.A novel method [15]XUAN Ping,HAN Ke,GUO Maozu,et al.Prediction of microRNAs associated with human diseases based on to quantify gene set functional association based on gene weighted k most similar neighbors[J].PLoS one,2013, ontology[J].Journal of the royal society interface,2012, 8(8):e70204. 9(70):1063-1072. [3]HRISTOVSKI D,FRIEDMAN C,RINDFLESCH T C,et [16]XU Chaohan,PING Yanyan,LI Xiang,et al.Prioritizing al.Exploiting semantic relations for literature-based dis- candidate disease miRNAs by integrating phenotype asso- covery[J].AMIA annual symposium proceedings,2006, ciations of multiple diseases with matched miRNA and 2006:349-353 mRNA expression profiles[J].Molecular biosystems, [4]KARP X,AMBROS V.Encountering microRNAs in cell 2014,10(11):2800-2809. fate signaling[J].Science,2005,310(5752):1288-1289. [17]MORK S.PLETSCHER-FRANKILD S.PALLEJA [5]CHENG A M.BYROM M W.SHELTON J,et al.Antis- CARO A,et al.Protein-driven inference of miRNA-dis- ense inhibition of human miRNAs and indications for an ease associations[J].Bioinformatics,2014,30(3): involvement of miRNA in cell growth and apoptosis[J]. 392-397. Nucleic acids research,2005,33(4):1290-1297. [18]PASQUIER C,GARDES J.Prediction of miRNA-dis- [6]MISKA E A.How microRNAs control cell division,dif- ease associations with a vector space model[J.Scientific ferentiation and death[J].Current opinion in genetics and reports,2016,6:27036. development,2005,15(5):563-568. [19]SUN Dongdong,LI Ao,FENG Huanging,et al.NTSM- [7]XU Peizhang,GUO Ming,HAY B A.MicroRNAs and the DA:prediction of miRNA-disease associations by integ-可以看到，在 k>100 时，AUC 值基本趋于稳 定。而对 k=100 维这样的子空间来说，单独的常 数维并不会对结果有很大的影响，于是删除了假 设的先验关联值，最终确定了预测模型。 6 结论 本文基于矩阵分解和迭代最小二乘的方法 (LMFMDA) 对 miRNAs 和疾病的关联关系进行预 测。首先对 miRNAs 相似度矩阵、疾病相似度矩 阵和 miRNAs-疾病关联关系进行数据融合，采用 迭代最小二乘法求解 miRNAs 和疾病的表达向 量，最后利用 miRNAs 和疾病的表达向量完成对 miRNA 与疾病关联关系的预测。同时，通过引入 辅助 miRNAs 和疾病变量的方法，解决了收敛结 果的最优问题。实验显示，LMFMDA 在高关联疾 病和新疾病预测中相对于其他方法均取了较优的 结果。 综上，本文提出的 miRNA 与疾病关联预测算 法 LMFMDA，一方面可以处理未知相关 miRNAs 的疾病、或者未知相关疾病的 miRNAs；另一方 面，实验结果也表明，LMFMDA 算法在 miRNAs 和疾病的关联关系预测上相较其他算法有更好的 效果。 参考文献： WANG Qianghu, SUN Jie, ZHOU Meng, et al. A novel network-based method for measuring the functional relationship between gene sets[J]. Bioinformatics, 2011, 27(11): 1521–1528. [1] LV Sali, LI Yan, WANG Qianghu, et al. A novel method to quantify gene set functional association based on gene ontology[J]. Journal of the royal society interface, 2012, 9(70): 1063–1072. [2] HRISTOVSKI D, FRIEDMAN C, RINDFLESCH T C, et al. Exploiting semantic relations for literature-based discovery[J]. AMIA annual symposium proceedings, 2006, 2006: 349–353. [3] KARP X, AMBROS V. Encountering microRNAs in cell fate signaling[J]. Science, 2005, 310(5752): 1288–1289. [4] CHENG A M, BYROM M W, SHELTON J, et al. Antisense inhibition of human miRNAs and indications for an involvement of miRNA in cell growth and apoptosis[J]. Nucleic acids research, 2005, 33(4): 1290–1297. [5] MISKA E A. How microRNAs control cell division, differentiation and death[J]. Current opinion in genetics and development, 2005, 15(5): 563–568. [6] [7] XU Peizhang, GUO Ming, HAY B A. MicroRNAs and the regulation of cell death[J]. Trends in genetics, 2004, 20(12): 617–624. YOU Zhuhong, HUANG Zhian, ZHU Zexuan, et al. PBMDA: a novel and effective path-based computational model for miRNA-disease association prediction[J]. PLoS computational biology, 2017, 13(3): e1005455. [8] SHI Hongbo, ZHANG Guangde, ZHOU Meng, et al. Integration of multiple genomic and phenotype data to infer novel miRNA-disease associations[J]. PLoS one, 2016, 11(2): e0148521. [9] JIANG Qinghua, HAO Yangyang, WANG Guohua, et al. Prioritization of disease microRNAs through a human phenome-microRNAome network[J]. BMC systems biology, 2010, 4(S1): S2. [10] JIANG Qinghua, WANG Guohua, WANG Yadong. An approach for prioritizing disease-related microRNAs based on genomic data integration[C]//Proceedings of the 3rd International Conference on Biomedical Engineering and Informatics. Yantai, China, 2010: 2270–2274. [11] CHEN Xing, LIU Mingxi, YAN Guiying. RWRMDA: predicting novel human microRNA–disease associations[J]. Molecular biosystems, 2012, 8(10): 2792–2798. [12] CHEN Hailin, ZHANG Zuping. Similarity-based methods for potential human microRNA-disease association prediction[J]. BMC medical genomics, 2013, 6: 12. [13] SHI Hongbo, XU Juan, ZHANG Guangde, et al. Walking the interactome to identify human miRNA-disease associations through the functional link between miRNA targets and disease genes[J]. BMC systems biology, 2013, 7: 101. [14] XUAN Ping, HAN Ke, GUO Maozu, et al. Prediction of microRNAs associated with human diseases based on weighted k most similar neighbors[J]. PLoS one, 2013, 8(8): e70204. [15] XU Chaohan, PING Yanyan, LI Xiang, et al. Prioritizing candidate disease miRNAs by integrating phenotype associations of multiple diseases with matched miRNA and mRNA expression profiles[J]. Molecular biosystems, 2014, 10(11): 2800–2809. [16] MØRK S, PLETSCHER-FRANKILD S, PALLEJA CARO A, et al. Protein-driven inference of miRNA–disease associations[J]. Bioinformatics, 2014, 30(3): 392–397. [17] PASQUIER C, GARDÈS J. Prediction of miRNA-disease associations with a vector space model[J]. Scientific reports, 2016, 6: 27036. [18] SUN Dongdong, LI Ao, FENG Huanqing, et al. NTSMDA: prediction of miRNA–disease associations by integ- [19] 第 6 期 刘晓燕，等：一种预测 miRNA 与疾病关联关系的矩阵分解算法 ·903·