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

Ricci L, Del Vescovo V, Cantaloni C, Grasso M, Barbareschi M, Denti MA - BMC Bioinformatics (2015)

Bottom Line: 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.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.

View Article: PubMed Central - PubMed

Affiliation: Department of Physics, University of Trento, Trento, I-38123, Italy. leonardo.ricci@unitn.it.

ABSTRACT

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.

No MeSH data available.


Related in: MedlinePlus

Scatter plot of yopt=Δx205−0.8·Δx21. See Section “A classifier for ADC vs. SQC” and the caption of Fig. 2 for the color code of dots, lines and shaded areas. The values of the thresholds are reported in Table 4
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4559882&req=5

Fig4: Scatter plot of yopt=Δx205−0.8·Δx21. See Section “A classifier for ADC vs. SQC” and the caption of Fig. 2 for the color code of dots, lines and shaded areas. The values of the thresholds are reported in Table 4

Mentions: The reliability of the classifier based on yopt can be inferred by considering the confusion matrix of Table 5 (see also the scatter plot in Fig. 4). The accuracy is 94 %, similar to that provided by the classifier relying on Δx205 only, and equal to that provided by the classifier relying on yDV. However, if only high-reliability responses are considered, namely those with odds at least 90:10, the accuracy of the classifier based on yopt is still 91 %, slightly better than 88 % provided by yDV and definitely larger than 64 % given by the classifier relying on Δx205 only. The improvement with regard to a classifier based on this last measure is pointed out by the ROC curves that are also shown in Fig. 4.Fig. 4


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

Ricci L, Del Vescovo V, Cantaloni C, Grasso M, Barbareschi M, Denti MA - BMC Bioinformatics (2015)

Scatter plot of yopt=Δx205−0.8·Δx21. See Section “A classifier for ADC vs. SQC” and the caption of Fig. 2 for the color code of dots, lines and shaded areas. The values of the thresholds are reported in Table 4
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4559882&req=5

Fig4: Scatter plot of yopt=Δx205−0.8·Δx21. See Section “A classifier for ADC vs. SQC” and the caption of Fig. 2 for the color code of dots, lines and shaded areas. The values of the thresholds are reported in Table 4
Mentions: The reliability of the classifier based on yopt can be inferred by considering the confusion matrix of Table 5 (see also the scatter plot in Fig. 4). The accuracy is 94 %, similar to that provided by the classifier relying on Δx205 only, and equal to that provided by the classifier relying on yDV. However, if only high-reliability responses are considered, namely those with odds at least 90:10, the accuracy of the classifier based on yopt is still 91 %, slightly better than 88 % provided by yDV and definitely larger than 64 % given by the classifier relying on Δx205 only. The improvement with regard to a classifier based on this last measure is pointed out by the ROC curves that are also shown in Fig. 4.Fig. 4

Bottom Line: 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.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.

View Article: PubMed Central - PubMed

Affiliation: Department of Physics, University of Trento, Trento, I-38123, Italy. leonardo.ricci@unitn.it.

ABSTRACT

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.

No MeSH data available.


Related in: MedlinePlus