Expression profiling in reference bacteria: dreams and reality

Abstract

Profiling of gene expression in bacteria is now being used to uncover unknown genes expressed in particular genetic backgrounds or environmental conditions. Obtaining the best possible information from the expected avalanche of such experiments will require standardization of both experimental approach and statistical analysis. The first such experiments reveal challenges, pitfalls and reasonable solutions.

Figure 1

A typical transcriptome analysis of Bacillus subtilis grown on methionine as sulfur source.The black dots are genes most strongly expressed, gray less so, and so on.

Figure 2

Distribution of hybridization values from the data points taken from Figure 1. (a) Histogram of the direct hybridization values. The curve is the best approach to a normal distribution that fits the histogram (note the poor fit). (b) Histogram of the logarithm of the hybridization values. Note that the normal distribution exhibits a much better fit (the excess of points at the low end of the curve corresponds to the excess of blank points in Figure 1, which show the background level of the hybridization signal). Note that this behavior should be verified before any interpretation of transcriptome data.