Intertwining threshold settings, biological data and database knowledge to optimize the selection of differentially expressed genes from microarray

Abstract

Background: Many tools used to analyze microarrays in different conditions have been described. However, the integration of deregulated genes within coherent metabolic pathways is lacking. Currently no objective selection criterion based on biological functions exists to determine a threshold demonstrating that a gene is indeed differentially expressed.

Methodology/principal findings: To improve transcriptomic analysis of microarrays, we propose a new statistical approach that takes into account biological parameters. We present an iterative method to optimise the selection of differentially expressed genes in two experimental conditions. The stringency level of gene selection was associated simultaneously with the p-value of expression variation and the occurrence rate parameter associated with the percentage of donors whose transcriptomic profile is similar. Our method intertwines stringency level settings, biological data and a knowledge database to highlight molecular interactions using networks and pathways. Analysis performed during iterations helped us to select the optimal threshold required for the most pertinent selection of differentially expressed genes.

Conclusions/significance: We have applied this approach to the well documented mechanism of human macrophage response to lipopolysaccharide stimulation. We thus verified that our method was able to determine with the highest degree of accuracy the best threshold for selecting genes that are truly differentially expressed.

Figure 1. Comparative analysis of the most significant Canonical Pathways throughout the entire dataset, and across multiple datasets.

The first 10 canonical Pathways generating significant scores are displayed as a bar chart along the x-axis. The y-axis represents the IPA score: the taller the bar, the better the score for the indicated pathway. For each canonical pathway, we have compared the progression of this EV value for increasingly tolerant values by decreasing EV occurrence;  = 6/6: blue; ≥5/6: red; ≥4/6: green; ≥3/6: violet.

Figure 2. Interconnections between different networks.

From our 195 differentially expressed genes, and the applied parameters (EV = 1.28; EV occurrence≥4/6), the data base has identified 22 different networks. The first 13 networks are heavily inter-connected as shown by solid lines between the networks. The integer beside each line indicates the number of genes that two networks have in common. Networks from 14 to 22 do not share common genes.

Figure 3. Close up of network.

A maximum authorized number of 35 genes were used to generate a network. Direct interactions between each gene within a network were represented. Genes highlighted in green were down-regulated whereas genes in red were up-regulated. The number beside a gene name indicates its fold change expression. Genes in white, which were not found in the assay, were added by the data base as they are relevant to the network. Solid lines represent a direct interaction whereas a dashed line represents an indirect interaction.

Figure 4. Connection of network 2 with minor networks.

Networks are built as previously described in Figure 3. Genes that are in green were down-regulated whereas genes in red were up-regulated. The number beside a gene name indicates its fold change expression. Genes in white, which were not found in the assay, were added by the data base as they are relevant to the network. Solid lines represent direct interaction between gene products whereas dashed lines represents indirect interaction. Orange lines display interconnections between minor networks (N 20 and N 21) and major network 2.

Figure 5. Canonical pathway of differentially regulated genes after LPS stimulation mediated by the NF-kappaB pathway.

Graphical representation of the metabolic pathway LXR/RXR activation exhibited as the main metabolic pathway by the data base according to the best EV value selection. The Toll-like receptor signalling pathway enables the production of cytokines with activation of NF-kappaB.