Limits...
Measuring similarities between gene expression profiles through new data transformations.

Kim K, Zhang S, Jiang K, Cai L, Lee IB, Feldman LJ, Huang H - BMC Bioinformatics (2007)

Bottom Line: Applying these algorithms to a simulation dataset, a developing mouse retina SAGE dataset, a small yeast sporulation cDNA dataset, and a maize root affymetrix microarray dataset, we found from the results that the algorithm associated with the first feature space, named TransChisq, showed clear advantages over other methods.The proposed TransChisq is very promising in capturing meaningful gene expression clusters.The clustering algorithms are available upon request.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Statistics, University of California, Berkeley, USA. kpkim@stat.berkeley.edu <kpkim@stat.berkeley.edu>

ABSTRACT

Background: Clustering methods are widely used on gene expression data to categorize genes with similar expression profiles. Finding an appropriate (dis)similarity measure is critical to the analysis. In our study, we developed a new measure for clustering the genes when the key factor is the shape of the profile, and when the expression magnitude should also be accounted for in determining the gene relationship. This is achieved by modeling the shape and magnitude parameters separately in a gene expression profile, and then using the estimated shape and magnitude parameters to define a measure in a new feature space.

Results: We explored several different transformation schemes to construct the feature spaces that include a space whose features are determined by the mutual differences of the original expression components, a space derived from a parametric covariance matrix, and the principal component space in traditional PCA analysis. The former two are the newly proposed and the latter is explored for comparison purposes. The new measures we defined in these feature spaces were employed in a K-means clustering procedure to perform analyses. Applying these algorithms to a simulation dataset, a developing mouse retina SAGE dataset, a small yeast sporulation cDNA dataset, and a maize root affymetrix microarray dataset, we found from the results that the algorithm associated with the first feature space, named TransChisq, showed clear advantages over other methods.

Conclusion: The proposed TransChisq is very promising in capturing meaningful gene expression clusters. This study also demonstrates the importance of data transformations in defining an efficient distance measure. Our method should provide new insights in analyzing gene expression data. The clustering algorithms are available upon request.

Show MeSH

Related in: MedlinePlus

Plots of 2092 maize genes on to the three different feature spaces. From top to bottom, the genes are plotted on to the subspaces of dimension 2 of the new spaces. Figures 1(a-c) correspond to the space used in TransChisq, Figures 1(d-f) correspond to the space determined by the parametric covariance matrix and Figures 1(g-i) correspond to the principal component space associated with the PCAChisq. PC1, PC2 and PC3 specify the subspaces. Blue/red dots represent RC up-/down-regulated genes, cyanide/pink dots represent PM up-/down-regulated genes, green/orange dots represent QC up-/down-regulated genes. The dotted lines in (e) are the centers of the six class separating regions determined by the second and third component from the parametric covariance matrix.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC1804284&req=5

Figure 1: Plots of 2092 maize genes on to the three different feature spaces. From top to bottom, the genes are plotted on to the subspaces of dimension 2 of the new spaces. Figures 1(a-c) correspond to the space used in TransChisq, Figures 1(d-f) correspond to the space determined by the parametric covariance matrix and Figures 1(g-i) correspond to the principal component space associated with the PCAChisq. PC1, PC2 and PC3 specify the subspaces. Blue/red dots represent RC up-/down-regulated genes, cyanide/pink dots represent PM up-/down-regulated genes, green/orange dots represent QC up-/down-regulated genes. The dotted lines in (e) are the centers of the six class separating regions determined by the second and third component from the parametric covariance matrix.

Mentions: Firstly, we applied the transformation employed in TransChisq to the data. Figures 1(a)–(c) plot the expression profiles of the genes in this new space. The blue and red genes are from the two dominant classes (RC up- or down-regulated genes account for 94% of all genes) and the other four colors (orange, green, pink, light blue) correspond to the other four small classes (up- or down-regulated genes in QC or PM account for 6% of all genes). The three plots show that the six classes can be recognized explicitly in any of the three subspaces of dimension 2.


Measuring similarities between gene expression profiles through new data transformations.

Kim K, Zhang S, Jiang K, Cai L, Lee IB, Feldman LJ, Huang H - BMC Bioinformatics (2007)

Plots of 2092 maize genes on to the three different feature spaces. From top to bottom, the genes are plotted on to the subspaces of dimension 2 of the new spaces. Figures 1(a-c) correspond to the space used in TransChisq, Figures 1(d-f) correspond to the space determined by the parametric covariance matrix and Figures 1(g-i) correspond to the principal component space associated with the PCAChisq. PC1, PC2 and PC3 specify the subspaces. Blue/red dots represent RC up-/down-regulated genes, cyanide/pink dots represent PM up-/down-regulated genes, green/orange dots represent QC up-/down-regulated genes. The dotted lines in (e) are the centers of the six class separating regions determined by the second and third component from the parametric covariance matrix.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC1804284&req=5

Figure 1: Plots of 2092 maize genes on to the three different feature spaces. From top to bottom, the genes are plotted on to the subspaces of dimension 2 of the new spaces. Figures 1(a-c) correspond to the space used in TransChisq, Figures 1(d-f) correspond to the space determined by the parametric covariance matrix and Figures 1(g-i) correspond to the principal component space associated with the PCAChisq. PC1, PC2 and PC3 specify the subspaces. Blue/red dots represent RC up-/down-regulated genes, cyanide/pink dots represent PM up-/down-regulated genes, green/orange dots represent QC up-/down-regulated genes. The dotted lines in (e) are the centers of the six class separating regions determined by the second and third component from the parametric covariance matrix.
Mentions: Firstly, we applied the transformation employed in TransChisq to the data. Figures 1(a)–(c) plot the expression profiles of the genes in this new space. The blue and red genes are from the two dominant classes (RC up- or down-regulated genes account for 94% of all genes) and the other four colors (orange, green, pink, light blue) correspond to the other four small classes (up- or down-regulated genes in QC or PM account for 6% of all genes). The three plots show that the six classes can be recognized explicitly in any of the three subspaces of dimension 2.

Bottom Line: Applying these algorithms to a simulation dataset, a developing mouse retina SAGE dataset, a small yeast sporulation cDNA dataset, and a maize root affymetrix microarray dataset, we found from the results that the algorithm associated with the first feature space, named TransChisq, showed clear advantages over other methods.The proposed TransChisq is very promising in capturing meaningful gene expression clusters.The clustering algorithms are available upon request.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Statistics, University of California, Berkeley, USA. kpkim@stat.berkeley.edu <kpkim@stat.berkeley.edu>

ABSTRACT

Background: Clustering methods are widely used on gene expression data to categorize genes with similar expression profiles. Finding an appropriate (dis)similarity measure is critical to the analysis. In our study, we developed a new measure for clustering the genes when the key factor is the shape of the profile, and when the expression magnitude should also be accounted for in determining the gene relationship. This is achieved by modeling the shape and magnitude parameters separately in a gene expression profile, and then using the estimated shape and magnitude parameters to define a measure in a new feature space.

Results: We explored several different transformation schemes to construct the feature spaces that include a space whose features are determined by the mutual differences of the original expression components, a space derived from a parametric covariance matrix, and the principal component space in traditional PCA analysis. The former two are the newly proposed and the latter is explored for comparison purposes. The new measures we defined in these feature spaces were employed in a K-means clustering procedure to perform analyses. Applying these algorithms to a simulation dataset, a developing mouse retina SAGE dataset, a small yeast sporulation cDNA dataset, and a maize root affymetrix microarray dataset, we found from the results that the algorithm associated with the first feature space, named TransChisq, showed clear advantages over other methods.

Conclusion: The proposed TransChisq is very promising in capturing meaningful gene expression clusters. This study also demonstrates the importance of data transformations in defining an efficient distance measure. Our method should provide new insights in analyzing gene expression data. The clustering algorithms are available upon request.

Show MeSH
Related in: MedlinePlus