Systems pathology analysis identifies neurodegenerative nature of age-related vitreoretinal interface diseases

Abstract

Aging is a phenomenon that is associated with profound medical implications. Idiopathic epiretinal membrane (iEMR) and macular hole (MH) are the major vision-threatening vitreoretinal diseases affecting millions of aging people globally, making these conditions an important public health issue. iERM is characterized by fibrous tissue developing on the surface of the macula, which leads to biomechanical and biochemical macular damage. MH is a small breakage in the macula and is associated with many ocular conditions. Although several individual factors and pathways are suggested, a systems pathology level understanding of the molecular mechanisms underlying these disorders is lacking. Therefore, we performed mass spectrometry-based label-free quantitative proteomics analysis of the vitreous proteomes from patients with iERM and MH to identify the key proteins, as well as the multiple interconnected biochemical pathways, contributing to the development of these diseases. We identified a total of 1,014 unique proteins, many of which are linked to inflammation and the complement cascade, revealing the inflammation processes in retinal diseases. Additionally, we detected a profound difference in the proteomes of iEMR and MH compared to those of diabetic retinopathy with macular edema and rhegmatogenous retinal detachment. A large number of neuronal proteins were present at higher levels in the iERM and MH vitreous, including neuronal adhesion molecules, nervous system development proteins, and signaling molecules, pointing toward the important role of neurodegenerative component in the pathogenesis of age-related vitreoretinal diseases. Despite them having marked similarities, several unique vitreous proteins were identified in both iERM and MH, from which candidate targets for new diagnostic and therapeutic approaches can be provided.

Keywords: MS-based quantitative proteomics; aging; epiretinal membrane; macular hole; neurodegeneration; vitreous humor.

Figure 1

Patient characterization and quantitative proteomics pipeline. (a) Fundus photograph of the central and peripheral retina, optic disk, and macula from the patients with iERM or MH. The macula is located in the posterior pole of the eye. In the center of the macula, a shallow depression in the retina (the fovea) marks the area with the highest visual acuity. (b) An optical coherence tomography (OCT) scan through the fovea of the iERM eye reveals the abnormal organization of the retinal layers, including epiretinal fibrosis and secondary cystic macular edema. Key: RPE = retinal pigment epithelial cells; scale bar: 200 µm. (c) The demographics of the iERM, MH, and DME patients, showing the distributions of the age, body mass index (BMI), preoperative intraocular pressure (IOP), and protein concentration (mg/ml). No significance differences were found between the sample groups. (d) The experimental workflow used for identifying and quantifying the human vitreous proteins from the patients with iERM, MH or DME. Vitreous samples were collected in vitrectomy, proteins were extracted and digested with trypsin, and the resulting peptides were analyzed via LC‐MS/MS. The label‐free quantification was performed by using Progenesis LC‐MS analysis software, and the protein identification was performed using the SEQUEST search engine. Bioinformatics approaches were used to combine our proteome data with the existing knowledge in order to obtain a systems pathology view on the differences of the molecular etiologies of these eye diseases

Figure 2

The vitreous proteomes from patients with iERM, MH, or DME show differential compositions between the diseases. (a) The MS1 spectra alignment percentages for the iERM, MH and DME sample MS analysis runs compared to those of the MH reference run. (b) Cellular localizations of the detected proteins were predicted using Phobius predictor software and were found to be predominantly either extracellular or transmembrane. (c) Venn diagram of 100 of the most abundant proteins in the iERM, MH and DME sample groups shows good overlap between the disease groups, whereas (d) the disease groups separate well after hierarchical clustering of the global quantitative proteomes. Heat‐map analysis of the hierarchical cluster analysis was performed using log2‐normalized MS1 intensities of 934 quantified vitreous proteins. The columns represent individual samples, and the rows represent the individual proteins. Each cell in the matrix represents the expression level of protein in an individual sample. Red and blue in the cells reflect the maximum and minimum expression levels, respectively

Figure 3

iERM and MH vitreous proteomes differ clearly from DME vitreous proteomes. (a) The abundance of 240 and 351 proteins differed statistically significantly (q‐value ≤0.05) between the iERM and DME groups (left panel) and between the MH and DME groups (right panel), respectively. Eighty proteins were present at higher levels and 131 proteins at lower levels in the iERM proteome (abundance ratio difference >2‐fold), and 174 proteins were present at higher levels and 123 proteins at lower levels in the MH proteome when compared to the DME proteome. (b) 131 and 123 proteins that were more abundant in the DME group were categorized according to their involvement in biological processes (Gene Ontology, Biological Processes terms) via DAVID bioinformatics resources. Dark green indicates proteins that were upregulated in DME compared to iERM (131), and light green indicates those upregulated in DME compared to MH (123)

Figure 4

Systems level analysis highlights the interconnectivity of the upregulated proteins in iERM and MH. (a) Biological processes associated with the 80 and 174 proteins upregulated in the iERM and MH groups, respectively, compared to the DME group. (b) MS1 intensity (log‐scale) of the enriched group of adhesion molecules involved in the cadherin‐catenin complex illustrates their abundant presence in iERM and MH. (c) Hierarchical clustering of the iERM and MH sample upregulated proteins based on their gene expression profiles in healthy human tissues. The iERM and MH upregulated proteins are expressed clearly in separate clusters consisting of a majority of neuronal tissues

Figure 5

The iERM and MH vitreous proteomes display high abundance of neuronal proteins. (a) Interaction analysis of the differentially abundant neuronal proteins. Thirty‐seven neuronal proteins that were present at higher levels in the iERM and MH proteomes were analyzed using the PINA2 protein interaction public database (green nodes indicate proteins that were upregulated in the iERM samples; orange nodes indicate upregulated proteins in the MH samples; and yellow nodes indicate upregulated proteins in both of the samples). Interaction analysis reveals a total of 90 interacting proteins found in our vitreous analysis, and they are classified based on their biological processes. (b) SWATH MS analysis verifies the increased expression of neuronal proteins in the iERM and MH vitreous, including proteins associated with neurodegeneration (A4, APLP2, and TPP1), cell adhesion (CADH2 and NCHL1), or cell signaling (WIF1). The results are shown as the peak areas detected in the SWATH analysis. The spots represent individual samples, and the lines indicate the mean values

Figure 6

Comparison between iERM and MH reveals several potential iERM biomarkers. Volcano blot analysis of differentially expressed proteins in the iERM and MH samples. The short names of the proteins were given to proteins with a q‐value <0.05 and a fold change >3 (exception: ITA3, fold change: 2.8). Potential iERM biomarker candidates are highlighted