Statistical analysis of a Bayesian classifier based on the expression of miRNAs

BMC Bioinformatics

Leonardo Ricci¹  Valerio Del Vescovo³  Chiara Cantaloni²  Margherita Grasso³  Mattia Barbareschi²  Michela Alessandra Denti³ 

[1] Department of Physics, University of Trento, Trento I-38123, Italy

[2] Unit of Surgical Pathology, Trento I-38122, Italy

[3] Centre for Integrative Biology, University of Trento, Trento I-38123, Italy

关键词: qRT-PCR gene expression measurement;    Lung cancer;    Bayesian classifiers;    microRNA;   

Others  :  1229465
DOI  :  10.1186/s12859-015-0715-9

 received in 2015-04-10, accepted in 2015-08-24,  发布年份 2015

【 摘 要 】

Background

During the last decade, many scientific works have concerned the possible use of miRNA levels as diagnostic and prognostic tools for different kinds of cancer. The development of reliable classifiers requires tackling several crucial aspects, some of which have been widely overlooked in the scientific literature: the distribution of the measured miRNA expressions and the statistical uncertainty that affects the parameters that characterize a classifier. In this paper, these topics are analysed in detail by discussing a model problem, i.e. the development of a Bayesian classifier that, on the basis of the expression of miR-205, miR-21 and snRNA U6, discriminates samples into two classes of pulmonary tumors: adenocarcinomas and squamous cell carcinomas.

Results

We proved that the variance of miRNA expression triplicates is well described by a normal distribution and that triplicate averages also follow normal distributions. We provide a method to enhance a classifiers’ performance by exploiting the correlations between the class-discriminating miRNA and the expression of an additional normalized miRNA.

Conclusions

By exploiting the normal behavior of triplicate variances and averages, invalid samples (outliers) can be identified by checking their variability via chi-square test or their displacement by the respective population mean via Student’s t-test. Finally, the normal behavior allows to optimally set the Bayesian classifier and to determine its performance and the related uncertainty.

【 授权许可】

   
2015 Ricci et al.

【 图 表 】

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

【 参考文献 】

• [1]Farazi TA, Spitzer JI, Morozov P, Tuschl T. MiRNAs in human cancer. J Pathol. 2011; 223:102-15.
• [2]Del Vescovo V, Grasso M, Barbareschi M, Denti MA. MicroRNAs as lung cancer biomarkers. World J Clin Oncol. 2014; 5:604-20.
• [3]Xi Y, Nakajima G, Gavin E, Morris CG, Kudo K, Hayashi K et al.. Systematic analysis of microRNA expression of RNA extracted from fresh frozen and formalin-fixed paraffin-embedded samples. RNA. 2007; 13:1668-1674.
• [4]Gilad S, Meiri E, Yogev Y, Benjamin S, Lebanony D, Yerushalmi N et al.. Serum MicroRNAs are promising novel biomarkers. PLoS One. 2008; 3:3148.
• [5]Grasso M, Piscopo P, Confaloni A, Denti MA. Circulating miRNAs as biomakers for neurodegenerative diseases. Molecules. 2014; 19:6891-910.
• [6]Shen J, Stass SA, Jiang F. MicroRNAs as potential biomarkers in human solid tumors. Cancer Lett. 2013; 329:125-36.
• [7]Benes V, Castoldi M. Expression profiling of microRNA using real-time quantitative PCR, how to use it and what is available. Methods. 2010; 50:244-9.
• [8]Gallardo E, Navarro A, Vinolas N, Marrades RM, Diaz T, Gel B et al.. miR-34a as a prognostic marker of relapse in surgically resected non-small-cell lung cancer. Carcinogenesis. 2012; 30:1903-1909.
• [9]Landi MT, Zhao Y, Rotunno M, Koshiol J, Liu H, Bergen AW et al.. MicroRNA expression differentiates histology and predicts survival of lung cancer. Clin Cancer Res. 2010; 16:430-41.
• [10]Patnaik SK, Kannisto E, Knudsen S, Yendamuri S. Evaluation of microRNA expression profiles that may predict recurrence of localized stage I non-small cell lung cancer after surgical resection. Cancer Res. 2010; 70:36-45.
• [11]Navarro A, Diaz T, Gallardo E, Vinolas N, Marrades RM, Gel B et al.. Prognostic implications of miR-16 expression levels in resected non-small-cell lung cancer. J Surg Oncol. 2011; 103:411-5.
• [12]Gilad S, Lithwick-Yanai G, Barshack I, Benjamin S, Krivitsky I, Edmonston TB et al.. Classification of the four main types of lung cancer using a microRNA-based diagnostic assay. J Mol Diagn. 2012; 14:510-7.
• [13]Lebanony D, Benjamin H, Gilad S, Ezagouri M, Dov A, Ashkenazi K et al.. Diagnostic assay based on hsa-miR-205 expression distinguishes squamous from nonsquamous non-small-cell lung carcinoma. J Clin Oncol. 2009; 27(12):2030-037.
• [14]Tan X, Qin W, Zhang L, Hang J, Li B, Zhang C et al.. A 5-microRNA signature for lung squamous cell carcinoma diagnosis and hsa-miR-31 for prognosis. Clin Cancer Res. 2011; 17:6802-811.
• [15]Lee HW, Lee EH, Ha SY, Lee CH, Chang HK, Chang S et al.. Altered expression of microRNA miR-21, miR-155, and let-7a and their roles in pulmonary neuroendocrine tumors. Pathol Int. 2012; 62:583-91.
• [16]Huang W, Hu J, Yang DW, Fan XT, Jin Y, Hou YY et al.. Two microRNA panels to discriminate three subtypes of lung carcinoma in bronchial brushing specimens. Am J Respir Crit Care Med. 2012; 186:1160-1167.
• [17]Del Vescovo V, Cantaloni C, Cucino A, Girlando S, Silvestri M, Bragantini E et al.. miR-205 expression levels in nonsmall cell lung cancer do not always distinguish adenocarcinomas from squamous cell carcinomas. Am J Surg Pathol. 2011; 35(2):268-75.
• [18]Peltier HJ, Latham GJ. Normalization of microRNA expression levels in quantitative RT-PCR assays: identification of suitable reference RNA targets in normal and cancerous human solid tissues. RNA. 2008; 14:844-52.
• [19]Vilardi A, Tabarelli D, Ricci L. Tailoring a psychophysical discrimination experiment upon assessment of the psychometric function: Predictions and results. AIP Adv. 2015; 5:027121.
• [20]Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC et al.. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinforma. 2011; 12:77.