Gene Expression Data

Each data point produced by a DNA microarray hybridization experiment represents the ratio of expression levels of a particular gene under two different experimental conditions. The result, from an experiment with n genes on a single chip, is a series of n expression-level ratios. Typically, the numerator of each ratio is the expression level of the gene in the varying condition of interest, whereas the denominator is the expression level of the gene in some reference condition. The data from a series of m such experiments may be represented as a gene expression matrix, in which each of the n rows consists of an m-element expression vector for a single gene. The expression measurement is positive if the gene is induced (turned up) with respect to the reference state and negative if it is repressed (turned down). Experiments are carried out using a set of 79-element gene expression vectors for 2467 annotated yeast genes. The data were collected at various time points during the diauxic shift, the mitotic cell division cycle, sporulation, and temperature and reducing shocks, and is available here via the Stanford web site.

Class definitions made by the MIPS Yeast Genome Database that we used to train SVMs include six functional classes: tricarboxylic acid cycle (TCA), respiration, cytoplasmic ribosomes, proteasome, histones and helix-turn-helix proteins. The MYGD class definitions come from biochemical and genetic studies of gene function, while the microarray expression data measures mRNA levels of genes. Many classes in MYGD, especially structural classes such as protein kinases, will be unlearnable from expression data by any classifier. The first five classes were selected because they represent categories of genes that are expected, on biological grounds, to exhibit similar expression profiles. Furthermore, Eisen et al. suggested that the mRNA expression vectors for these classes cluster well using hierarchical clustering. The sixth class, the helix-turn-helix proteins, is included as a control group. Since there is no reason to believe that the members of this class are similarly regulated, we did not expect any classifier to learn to recognize members of this class based upon mRNA expression measurements.

An interesting observation upon looking at the raw expression data shows that genes in the TCA and respiration classes are regulated very similarily, as shown in the figure below.




  

Similarity between the average expression profiles of the tricarboxylic-acid pathway and respiration chain complexes. Each series represents the average log expression ratio for all genes in the given family plotted as a function of DNA microarray experiment. Ticks along the X-axis represent the beginnings of experimental series.



• The target gene labels from the MIPS database for six functional classes.

• A web page for plotting gene expression data used for cross-validation tests against a plot of the genes in a single MIPS class.

• A web page for plotting gene expression data used for predictions against a plot of the genes in a single MIPS class.

• A web page for plotting gene expression data used for predictions for any set of genes.