Clustering gene-expression data with repeated measurements

Abstract

Clustering is a common methodology for the analysis of array data, and many research laboratories are generating array data with repeated measurements. We evaluated several clustering algorithms that incorporate repeated measurements, and show that algorithms that take advantage of repeated measurements yield more accurate and more stable clusters. In particular, we show that the infinite mixture model-based approach with a built-in error model produces superior results.

Figure 1

Expression profiles of the classes in typical completely synthetic datasets with four repeated measurements. (a) Low noise level; (b) high noise level. For each class, the log ratios are plotted against the experiment numbers, and each class is shown in a different color. There are four sine (periodic) classes with different phase shifts and two linear (non-periodic) classes. Only four (out of six) classes are shown in (b) for clarity.

Figure 2

Distribution of the fraction of gene pairs against correlation coefficient. Correlation coefficients are computed from averaging over repeated measurements and using SD over repeated measurements as weights on the yeast galactose data. There are more gene pairs with correlation coefficients around 0 and fewer gene pairs with correlation coefficients near 1 when SD-weighted correlation is used.

Figure 3

Distribution of the fraction of gene pairs against Euclidean distance. Euclidean distances are computed from averaging over repeated measurements and using SD over repeated measurements as weights on the yeast galactose data. There are more gene pairs with Euclidean distances near 0 when SD-weighted distance is used.

Figure 4

Distribution of error plotted against intensity. The SDs over the log ratios from repeated measurements are plotted against the average intensities over repeated measurements in a typical experiment on the yeast galactose data.