Meta-analysis of transcriptomic changes in optic nerve injury and neurodegenerative models reveals a fundamental response to injury throughout the central nervous system

Abstract

Purpose: Injury to the central nervous system (CNS) leads to transcriptional changes that effect tissue function and govern the process of neurodegeneration. Numerous microarray and RNA-Seq studies have been performed to identify these transcriptional changes in the retina following optic nerve injury and elsewhere in the CNS following a variety of insults. We reasoned that conserved transcriptional changes between injury paradigms would be important contributors to the neurodegenerative process. Therefore, we compared the expression results from heterogeneous studies of optic nerve injury and neurodegenerative models.

Methods: Expression data was collected from the Gene Expression Omnibus. A uniform method for normalizing expression data and detecting differentially expressed (DE) genes was used to compare the transcriptomes from models of acute optic nerve injury (AONI), chronic optic nerve injury (CONI) and brain neurodegeneration. DE genes were split into genes that were more or less prevalent in the injured condition than the control condition (enriched and depleted, respectively) and transformed into their human orthologs so that transcriptomes from different species could be compared. Biologic significance of shared genes was assessed by analyzing lists of shared genes for gene ontology (GO) term over-representation and for representation in KEGG pathways.

Results: There was significant overlap of enriched DE genes between transcriptomes of AONI, CONI and neurodegeneration studies even though the overall concordance between datasets was low. The depleted DE genes identified between AONI and CONI models were significantly overlapping, but this significance did not extend to comparisons between optic nerve injury models and neurodegeneration studies. The GO terms overrepresented among the enriched genes shared between AONI, CONI and neurodegeneration studies were related to innate immune processes like the complement system and interferon signaling. KEGG pathway analysis revealed that transcriptional alteration between JAK-STAT, PI3K-AKT and TNF signaling, among others, were conserved between all models that were analyzed.

Conclusions: There is a conserved transcriptional response to injury in the CNS. This transcriptional response is driven by the activation of the innate immune system and several regulatory pathways. Understanding the cellular origin of these pathways and the pathological consequences of their activation is essential for understanding and treating neurodegenerative disease.

Figure 1

Identifying Orthologous DE Genes Using the Rosetta Stone Ortholog Table. A: A list of DE genes from two rat and one zebrafish data sets being compared. The list has been shortened to facilitate this example of how the orthologs are identified by the common human ortholog. B: The Rosetta Stone Ortholog Table lists all of the orthologs of each human gene for each species in the table. It is important to note that an ortholog from a species may appear multiple times in the Rosetta Stone. If a species has no reported human ortholog, then that index in the table appears as “no orthologue.” C: The lists of DE genes from each data set shown in (A) are now translated into the corresponding human ortholog using an algorithm written in Python and then aligned to show common DE genes in each data set. This translation allows a direct comparison between data sets between species. In this table, nd refers genes that were not detected as DE genes in the data set.

Figure 2

Monte Carlo analysis of a pair-wise comparison of two data sets. The frequency distribution of outcomes from 10,000 Monte Carlo simulations comparing the overlap of genes between two data sets (Agudo 48 h crush enriched genes and McCurley 4 day crush enriched genes) observed by random chance (red bars). The number of genes shared by the two data sets in the empirical data are actually 79. The p value is the proportion of simulations that produce several randomly shared genes that is greater than, or equal to, the empirically observed number. In this comparison, the number of overlapping genes determined empirically between the two compared data sets is significantly greater than what would be expected by random chance, and we declare this to be a significant overlap for these data. Had the empirical data revealed 56 overlapping genes, then we would have declared no significant overlap of the data sets (p>0.05).

Figure 3

Hierarchical clustering of the complete transcriptomes of data sets using the Affymetrix Mouse Genome 430 2.0 Array. The relative level of every gene in the experimental sample was calculated for all the study data sets that had used this array chip. Hierarchical clustering was used to determine how similar the transcriptomes were from samples generated by different groups. Overall, the cluster shows two distinct distant branches, with optic nerve head (ONH) data sets segregating to the upper branch, and retina data sets segregating to the lower branch. The exceptions to this are the “No or Early” retina data sets from the Howell study, which have greater similarity to transcriptomes of the ONH, rather than pathologic retinas. Other data sets from studies of brain-related CNS neurodegeneration appear to distribute between both arms of the cluster.

Figure 4

Pair-wise comparison of acute (vertical) and chronic (horizontal) optic nerve injury data sets show moderate levels of overlapping DE genes for comparison of (A) enriched and (B) depleted genes. The total number of DE genes identified in the independent analysis is shown for each data set. In each cell, the total number of overlapping genes between two data sets is recorded. Based on Monte Carlo simulations, the cells are color-coded red for a non-significant overlap, or green for a significant overlap.

Figure 5

Pair-wise comparison of optic nerve injury (vertical) and brain-related CNS neurodegenerative disease (horizontal) data sets show widespread overlap of (A) enriched DE genes, but not (B) depleted DE genes. The total number of DE genes identified in the independent analysis is shown for each data set. In each cell, the total number of overlapping genes between two data sets is recorded. Based on Monte Carlo simulations, the cells are color-coded red for a non-significant overlap, or green for a significant overlap.