Integrating explainable machine learning and transcriptomics data reveals cell-type specific immune signatures underlying macular degeneration.

Abstract

Genome-wide association studies (GWAS) have established key role of immune dysfunction in Age-related Macular Degeneration (AMD), though the precise role of immune cells remains unclear. Here, we develop an explainable machine-learning pipeline (ML) using transcriptome data of 453 donor retinas, identifying 81 genes distinguishing AMD from controls (AUC-ROC of 0.80, CI 0.70-0.92). Most of these genes were enriched in their expression within retinal glial cells, particularly microglia and astrocytes. Their role in AMD was further strengthened by cellular deconvolution, which identified distinct differences in microglia and astrocytes between normal and AMD. We corroborated these findings using independent single-cell data, where several ML genes exhibited differential expression. Finally, the integration of AMD-GWAS data identified a regulatory variant, rs4133124 at PLCG2, as a novel AMD association. Collectively, our study provides molecular insights into the recurring theme of immune dysfunction in AMD and highlights the significance of glial cell differences in AMD progression.