Limits...
Sample entropy analysis of cervical neoplasia gene-expression signatures.

Botting SK, Trzeciakowski JP, Benoit MF, Salama SA, Diaz-Arrastia CR - BMC Bioinformatics (2009)

Bottom Line: Approximate entropy is applied here as a method to classify the complex gene expression patterns resultant of a clinical sample set.This may be measured in terms of the ApSE when compared to normal tissue.The success of the Approximate Sample Entropy approach in discerning alterations in complexity from biological system with such relatively small sample set, and extracting biologically relevant genes of interest hold great promise.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Obstetrics & Gynecology, University of Texas Medical Branch, Galveston, Texas, USA. shbarton@utmb.edu

ABSTRACT

Background: We introduce Approximate Entropy as a mathematical method of analysis for microarray data. Approximate entropy is applied here as a method to classify the complex gene expression patterns resultant of a clinical sample set. Since Entropy is a measure of disorder in a system, we believe that by choosing genes which display minimum entropy in normal controls and maximum entropy in the cancerous sample set we will be able to distinguish those genes which display the greatest variability in the cancerous set. Here we describe a method of utilizing Approximate Sample Entropy (ApSE) analysis to identify genes of interest with the highest probability of producing an accurate, predictive, classification model from our data set.

Results: In the development of a diagnostic gene-expression profile for cervical intraepithelial neoplasia (CIN) and squamous cell carcinoma of the cervix, we identified 208 genes which are unchanging in all normal tissue samples, yet exhibit a random pattern indicative of the genetic instability and heterogeneity of malignant cells. This may be measured in terms of the ApSE when compared to normal tissue. We have validated 10 of these genes on 10 Normal and 20 cancer and CIN3 samples. We report that the predictive value of the sample entropy calculation for these 10 genes of interest is promising (75% sensitivity, 80% specificity for prediction of cervical cancer over CIN3).

Conclusion: The success of the Approximate Sample Entropy approach in discerning alterations in complexity from biological system with such relatively small sample set, and extracting biologically relevant genes of interest hold great promise.

Show MeSH

Related in: MedlinePlus

Bayesian classification algorithm partitioned the genes into 10 subsets based on expression change patterns. Scatter plot of the change in log2 expression of Cancer from Normal, versus Perilesional from Normal, depicts the 10 possible subsets of genes differentiating the two groups. Subsets 1 and 2 displayed the best predictive value during validation.(A) Line plot of log2 expression of the 10 subsets, for the average change of Log2 expression of from Normal; for Normal, Perilesional and Cancer for each subset.(B).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2656476&req=5

Figure 2: Bayesian classification algorithm partitioned the genes into 10 subsets based on expression change patterns. Scatter plot of the change in log2 expression of Cancer from Normal, versus Perilesional from Normal, depicts the 10 possible subsets of genes differentiating the two groups. Subsets 1 and 2 displayed the best predictive value during validation.(A) Line plot of log2 expression of the 10 subsets, for the average change of Log2 expression of from Normal; for Normal, Perilesional and Cancer for each subset.(B).

Mentions: If an existing cluster was considered for further subdivision, two new cluster centers were located symmetrically along the principal axis (eigenvector) by a distance determined by the magnitude of the principal component (eigenvalue) computed from that cluster's covariance matrix. Bayesian distances were then estimated relative to the new clusters and the process was repeated. (Figure 2)


Sample entropy analysis of cervical neoplasia gene-expression signatures.

Botting SK, Trzeciakowski JP, Benoit MF, Salama SA, Diaz-Arrastia CR - BMC Bioinformatics (2009)

Bayesian classification algorithm partitioned the genes into 10 subsets based on expression change patterns. Scatter plot of the change in log2 expression of Cancer from Normal, versus Perilesional from Normal, depicts the 10 possible subsets of genes differentiating the two groups. Subsets 1 and 2 displayed the best predictive value during validation.(A) Line plot of log2 expression of the 10 subsets, for the average change of Log2 expression of from Normal; for Normal, Perilesional and Cancer for each subset.(B).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2656476&req=5

Figure 2: Bayesian classification algorithm partitioned the genes into 10 subsets based on expression change patterns. Scatter plot of the change in log2 expression of Cancer from Normal, versus Perilesional from Normal, depicts the 10 possible subsets of genes differentiating the two groups. Subsets 1 and 2 displayed the best predictive value during validation.(A) Line plot of log2 expression of the 10 subsets, for the average change of Log2 expression of from Normal; for Normal, Perilesional and Cancer for each subset.(B).
Mentions: If an existing cluster was considered for further subdivision, two new cluster centers were located symmetrically along the principal axis (eigenvector) by a distance determined by the magnitude of the principal component (eigenvalue) computed from that cluster's covariance matrix. Bayesian distances were then estimated relative to the new clusters and the process was repeated. (Figure 2)

Bottom Line: Approximate entropy is applied here as a method to classify the complex gene expression patterns resultant of a clinical sample set.This may be measured in terms of the ApSE when compared to normal tissue.The success of the Approximate Sample Entropy approach in discerning alterations in complexity from biological system with such relatively small sample set, and extracting biologically relevant genes of interest hold great promise.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Obstetrics & Gynecology, University of Texas Medical Branch, Galveston, Texas, USA. shbarton@utmb.edu

ABSTRACT

Background: We introduce Approximate Entropy as a mathematical method of analysis for microarray data. Approximate entropy is applied here as a method to classify the complex gene expression patterns resultant of a clinical sample set. Since Entropy is a measure of disorder in a system, we believe that by choosing genes which display minimum entropy in normal controls and maximum entropy in the cancerous sample set we will be able to distinguish those genes which display the greatest variability in the cancerous set. Here we describe a method of utilizing Approximate Sample Entropy (ApSE) analysis to identify genes of interest with the highest probability of producing an accurate, predictive, classification model from our data set.

Results: In the development of a diagnostic gene-expression profile for cervical intraepithelial neoplasia (CIN) and squamous cell carcinoma of the cervix, we identified 208 genes which are unchanging in all normal tissue samples, yet exhibit a random pattern indicative of the genetic instability and heterogeneity of malignant cells. This may be measured in terms of the ApSE when compared to normal tissue. We have validated 10 of these genes on 10 Normal and 20 cancer and CIN3 samples. We report that the predictive value of the sample entropy calculation for these 10 genes of interest is promising (75% sensitivity, 80% specificity for prediction of cervical cancer over CIN3).

Conclusion: The success of the Approximate Sample Entropy approach in discerning alterations in complexity from biological system with such relatively small sample set, and extracting biologically relevant genes of interest hold great promise.

Show MeSH
Related in: MedlinePlus