Combining Gene–Disease Associations with Single-Cell Gene Expression Data Provides Anatomy-Specific Subnetworks in Age-Related Macular Degeneration

Abstract

Background: Age-related macular degeneration (AMD) is the most common cause of visual impairment in the developed world. Despite some treatment options for late AMD, there is no intervention that blocks early AMD proceeding to the late and blinding forms. This is partly due to the lack of precise drug targets, despite great advances in genetics, epidemiology, and protein-protein interaction (PPI) networks proposed to be driving the disease pathology. A systems approach to narrow down PPI networks to specific protein drug targets would provide new therapeutic options. Materials and Methods: In this study we analyzed single cell RNAseq (RNA sequencing) datasets of 17 cell types present in choroidal, retinal pigment epithelium (RPE), and neural retina (NR) tissues to explore if a more granular analysis incorporating different cell types exposes more specific pathways and relationships. Furthermore, we developed a novel and systematic gene ontology database (SysGO) to explore if a subcellular classification of processes will further enhance the understanding of the pathogenesis of this complex disorder and its comorbidities with other age-related diseases. Results: We found that 57% of the AMD (risk) genes are among the top 25% expressed genes in *1 of the 17 choroidal/RPE/NR cell types, and 9% were among the top 1% of expressed genes. Using SysGO, we identified an enrichment of AMD genes in cell membrane and extracellular anatomical locations, and we found both functional enrichments (e.g., cell adhesion) and cell types (e.g., fibroblasts, microglia) not previously associated with AMD pathogenesis. We reconstructed PPI networks among the top expressed AMD genes for all 17 choroidal/RPE/NR cell types, which provides molecular and anatomical definitions of AMD phenotypes that can guide therapeutic approaches to target this complex disease. Conclusion: We provide mechanism-based AMD endophenotypes that can be exploited in vitro, using computational models and for drug discovery/repurposing.

The Ins and Outs of RAS Effector Complexes

“…While the actin meshwork is likely to cause prolonged residence times for all effectors once they are recruited to RAS•GTP via their RBD, effectors may also directly bind to proteins localized in the actin meshwork. Information obtained from the HuRI database that stores direct binary protein-protein interactions obtained from genome-wide yeast two hybrid experiments [35], reports direct physical interactions between four effectors and interactors localized to the actin cytoskeleton (based on SysGO [36]) ( Figure 3B). These binary interactions are between (i) the effector RIN1 and CIP4/TRIP10, a CDC42 interacting protein [37]; (ii) the effector RASSF10 and TNNI3, a cardiac muscle protein that is an inhibitory subunit of troponin [38]; (iii) the effector RAPGEF4 and DEF6, a guanine nucleotide exchange factor for Rho GTPases [39]; and (iv) the effector GRB10 and KANK2, involved in actin stress fibers formation through the regulation of Rho signaling [40].…”

“…In addition to domains directly binding to the PM, effectors often contain typical domains involved in intermolecular protein-protein interactions, such as SH2 (SMART accession number: SM00252), SH3 (SM00326), PDZ (SM00228), PTB (SM00462), ANK (SM00248), and FHA (SM00240) domains [17]. Information obtained from the HuRI database [35] reports direct binary interactions between nine effectors and interactors localized to the PM (based on SysGO [36]) ( Figure 3D). Those effectors are RIN1 (binding to PICK1, ANKS1B), RASSF10 (binding to GNG13 and FAM171A1), RASSF3 (binding to TFRC and ITPRIP), RASSF8 (binding to FRMD6), RGS12 (binding to GNAI1 and GNAI3), GRB7 (binding to PICK1, TGM5, LAX1, ERBB2, ERBB3, KIT, RET, and INSR), GRB10 (binding to PICK1, BLK, IGF1R, RET, INSR, EGFR, and KIT), and GRB14 (binding to FGFR1, and INSR).…”

The Ins and Outs of RAS Effector Complexes

“…While the actin meshwork is likely to cause prolonged residence times for all effectors once they are recruited to RAS•GTP via their RBD, effectors may also directly bind to proteins localized in the actin meshwork. Information obtained from the HuRI database that stores direct binary protein-protein interactions obtained from genome-wide yeast two hybrid experiments [33] reports direct physical interactions between four effectors and interactors localized to the actin cytoskeleton (based on SysGO [34]) ( Fig. 3B).…”

“…7A). A functional analysis of RAS interaction partners using the SysGO database [34] shows that the 'subcellular localization' category is enriched for cell-cell junctions, endosomes, vesicles, cytosol, PM, actin microfilaments, and the Golgi apparatus (Fig. 7B, left).…”

“…In addition to domains directly binding to the PM, effectors often contain typical domains involved in intermolecular protein-protein interactions, such as SH2 (SMART accession number: SM00252), SH3 (SM00326), PDZ (SM00228), PTB (SM00462), ANK (SM00248), and FHA (SM00240) domains [15]. Information obtained from the HuRI database [33] reports direct binary interactions between nine effectors and interactors localized to the PM (based on SysGO [34]) ( Fig. 3D).…”