An embedded method for gene identification problems involving unwanted data heterogeneity
Tóm tắt
Modern applications such as bioinformatics collecting data in various ways can easily result in heterogeneous data. Traditional variable selection methods assume samples are independent and identically distributed, which however is not suitable for these applications. Some existing statistical models capable of taking care of unwanted variation were developed for gene identification involving heterogeneous data, but they lack model predictability and suffer from variable redundancy. By accounting for the unwanted heterogeneity effectively, our method have shown its superiority over several state-of-the art methods, which is validated by the experimental results in both unsupervised and supervised gene identification problems. Moreover, we also applied our method to a pan-cancer study where our method can identify the most discriminative genes best distinguishing different cancer types. This article provides an alternative gene identification method that can accounting for unwanted data heterogeneity. It is a promising method to provide new insights into the complex cancer biology and clues for understanding tumorigenesis and tumor progression.
Tài liệu tham khảo
Li J, Cheng K, Wang S, Morstatter F, Trevino RP, Tang J, Liu H. Feature selection: A data perspective. arXiv preprint arXiv:1601.07996. 2016.
Chen C, Grennan K, Badner J, Zhang D, Gershon E, Jin L, Liu C. Removing batch effects in analysis of expression microarray data: An evaluation of six batch adjustment methods. PLoS ONE. 2011; 6(2):17238.
Almeida A, Paul JT, Magdelenat H, Radvanyi F. Gene expression analysis by real-time reverse transcription polymerase chain reaction: influence of tissue handling. Anal Biochem. 2004; 328(2):101–8.
Ma Y, Dai H, Kong X. Impact of warm ischemia on gene expression analysis in surgically removed biosamples. Anal Biochem. 2012; 423(2):229–35.
Bakay M, Chen YW, Borup R, Zhao P, Nagaraju K, Hoffman EP. Sources of variability and effect of experimental approach on expression profiling data interpretation. BMC Bioinformatics. 2002; 3(1):4.
Boedigheimer MJ, et al.Sources of variation in baseline gene expression levels from toxicogenomics study control animals across multiple laboratories. BMC Genomics. 2008; 9(1):285.
Fare TL, et al.Effects of atmospheric ozone on microarray data quality. Anal Chem. 2003; 75(17):4672–5.
Glaab E, Schneider R. Repexplore: addressing technical replicate variance in proteomics and metabolomics data analysis. Bioinformatics. 2015; 31(13):2235–7.
Zhao Z, Liu H. Multi-source feature selection via geometry-dependent covariance analysis. JMLR Work Conf Proc. 2008; 4:36–47.
Tang J, Hu X, Gao H, Liu H. Unsupervised feature selection for multi-view data in social media. In: Proceedings of the 2013 SIAM International Conference on Data Mining.2013. p. 270–8.
Feng Y, Xiao J, Zhuang Y, Liu X. Adaptive unsupervised multi-view feature selection for visual concept recognition. In: Computer Vision–ACCV 2012. Berlin: Springer: 2013. p. 343–57.
Wang H, Nie F, Huang H. Multi-view clustering and feature learning via structured sparsity. In Proceedings of the 30th International Conference on Machine Learning. 2013:352–60.
Friedman J, Hastie T, Tibshirani R. A note on the group lasso and a sparse group lasso. arXiv preprint arXiv:1001.0736. 2010.
Peng J, et al.Regularized multivariate regression for identifying master predictors with application to integrative genomics study of breast cancer. Ann Appl Stat. 2010; 4(1):53.
d’Aspremont A, Ghaoui LE, Jordan MI, Lanckriet GR. A direct formulation for sparse pca using semidefinite programming. SIAM Rev. 2007; 49(3):434–48.
Lu M, Huang JZ, Qian X. Sparse exponential family principal component analysis. Pattern Recog. 2016; 60:681–91.
Leek JT, Store JD. Capturing heterogeneity in gene expression studies by surrogate variable analysis. PLoS Genet. 2007; 3:161.
Gagnon-Bartsch JA, Speed TP. Using control genes to correct for unwanted variation in microarray data. Biostatistics. 2012; 13(3):539–52.
Lu M. An embedded method for gene identification in heterogenous data involving unwanted heterogeneity. In Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine. 2018:242–7.
Trevor H, Robert T, Andreas B. Flexible discriminant analysis by optimal scoring. J Am Stat Assoc. 1994; 89(428):1255–70.
David W, Srikantan N. Iterative reweighted l1 and l2 methods for finding sparse solutions. IEEE J Sel Top Sign Process. 2010; 4(2):317–29.
Cope LM, Irizarry RA, Jaffee HA, Wu Z, Speed TP. A benchmark for affymetrix genechip expression measures. Bioinformatics. 2004; 20(3):323–31.
Irizarry RA, et al.Summaries of affymetrix genechip probe level data. Nucleic Acids Res. 2003; 31(4):e15.
Irizarry RA, Hobbs B, Collin F, Beazer-Barclay YD, Antonellis KJ, Scherf U, Speed TP. Exploration, normalization, and summaries of high density oligonucleotide array probe level data. Biostatistics. 2003; 4:249–64.
Vawter MP, et al.Gender-specific gene expression in post-mortem human brain: Localization to sex chromosomes. Neuropsychopharmacology. 2004; 29(2):373–84.
Eisenberg E, Levanon EY. Human housekeeping genes are compact. TRENDS Genet. 2003; 19(7):362–5.
Baird S, Fitch D, Kassem I, Emmons S. Pattern formation in the nematode epidermis: determination of the arrangement of peripheral sense organs in the c.elegans male tail. Development. 1991; 113:515–26.
Tan J, et al.Integrative epigenome analysis identifies a polycomb-targeted differentiation program as a tumor-suppressor event epigenetically inactivated in colorectal cancer. Cell Death Dis. 2014; 5(7):1324.
Agus DB, Bunn PA, Franklin W, et al.Her-2/neu as a therapeutic target in non-small cell lung cancer, prostate cancer, and ovarian cancer. Semin Oncol. 2000; 27(6):53–63.
Oh JJ, Grosshans DR, Wong SG, et al.Identification of differentially expressed genes associated with her-2/neu overexpression in human breast cancer cells. Nucleic Acids Res. 1999; 27(20):4008–17.
Pal P, Xi H, Sun G, Kaushal R, Meeks J, Thaxton C, et al.Tagging snps in the kallikrein genes 3 and 2 on 19q13 and their associations with prostate cancer in men of european origin. Hum Genet. 2007; 122:251–9.
Nam R, Zhang W, Trachtenberg J, Diamandis E, Toi A, Emami M, et al.Single nucleotide polymorphism of the human kallikrein-2 gene highly correlates with serum human kallikrein-2 levels and in combination enhances prostate cancer detection. J Clin Oncol. 2003; 21:2312–9.
Zhu C, Feng X, Ye G, Huang T. Meta-analysis of possible role of cadherin gene methylation in evolution and prognosis of hepatocellular carcinoma with a prisma guideline. Med (Baltimore). 2017; 96(16):6650.
Zhang B, Kirov S, Snoddy J. Webgestalt: an integrated system for exploring gene sets in various biological contexts. Nucleic Acids Res. 2005; 33(Web Server issue):741–8.