From genes to functional classes in the study of biological systems

Abstract

Background: With the popularization of high-throughput techniques, the need for procedures that help in the biological interpretation of results has increased enormously. Recently, new procedures inspired in systems biology criteria have started to be developed.

Results: Here we present FatiScan, a web-based program which implements a threshold-independent test for the functional interpretation of large-scale experiments that does not depend on the pre-selection of genes based on the multiple application of independent tests to each gene. The test implemented aims to directly test the behaviour of blocks of functionally related genes, instead of focusing on single genes. In addition, the test does not depend on the type of the data used for obtaining significance values, and consequently different types of biologically informative terms (gene ontology, pathways, functional motifs, transcription factor binding sites or regulatory sites from CisRed) can be applied to different classes of genome-scale studies. We exemplify its application in microarray gene expression, evolution and interactomics.

Conclusion: Methods for gene set enrichment which, in addition, are independent from the original data and experimental design constitute a promising alternative for the functional profiling of genome-scale experiments. A web server that performs the test described and other similar ones can be found at: http://www.babelomics.org.

Figure 1

Threshold-free functional analysis. A list of genes is ranked by their differential expression between two experimental conditions (A and B) using, for example, a t-test which is applied individually to each gene. Columns 1, 2 and 3 represent the position of the genes belonging to three different functional classes (e.g. GO terms, etc.) across the arrangement. The first functional class is completely uncorrelated with the arrangement, while functional classes 2 and 3 are clearly associated to high expression in the experimental conditions B and A, respectively. Dotted lines represent a threshold based on the individual t-tests with some adjustment for multiple testing. The arrow makes reference to the multi-functional character of the genes: a gene can belong to more than one functional class. In this case the gene pointed out by the arrow is in this position not because of its membership to functional class 1 but because is fulfilling the role corresponding to functional class 3, which is related to high expression in experimental condition A.

Figure 2

Interface to the FatiScan program displaying the available model organisms.

Figure 3

A general picture of the results of the FatiScan program. Over- and under-representations of functional classes in both tails of the list of arranged genes can be detected. U-arrow up: functional classes over-represented in the upper part of the list. U-arrow down: functional classes under-represented in the upper part of the list. L-arrow up: functional classes over-represented in the lower part of the list. L-arrow down: functional classes under-represented in the lower part of the list. See text for the different choices of tests that detect the different cases.

Figure 4

Graphical results of FatiScan. Upper part: a summarised view of all the functional classes found. In the case of GO, only the deepest significant terms in the hierarchy are displayed. Lower part, comparison of the distribution of the two GO terms found significantly over-represented in the upper part of the list with respect to the background of GO terms in the rest of genes.

Figure 5

A small segment of the DAG GO hierarchy connecting the top of the biological process category to the term negative regulation of neuron apoptosis.

Figure 6

FatiScan analysis of the comparison between the background distribution of GO terms (black and blue bars) and the distribution of sensory perception of smell GO term (grey and red bars). The last distribution is clearly shifted towards highest values of ω (horizontal axis). The colours black/blue and grey/red make reference to the ω values for which the partitions were found to be significant.