Interpretable Aging Signatures in Human Retinal Cell Types Revealed by Single-Cell RNA Sequencing and Sparse Logistic Regression

PurposeTo characterize cell type specific transcriptional changes during human retinal aging and develop machine learning model for cellular age discrimination in a Chinese cohort. DesignCross-sectional, laboratory-based observational study. ParticipantsEighteen unfrozen retinas from 12 Chinese donors (9 young, 34-55y; 9 old, 68-92 y). MethodsSingle-cell RNA sequencing (10x, v3.1) generated 223612 cells, batch-corrected with scVI; age-related signatures were defined by intersecting single-cell and pseudo-bulk differentially expressed genes, then cell-type-specific panels were rank-ordered with L1-regularised logistic regression plus recursive feature elimination and interpreted through hallmark-pathway enrichment and transcription-factor regulon mapping. Main Outcome MeasuresAge-related cellular composition shifts; cell-type-specific differentially expressed genes; machine-learning classifier accuracy and feature rankings; transcription factor regulon activity changes. ResultsEleven major retinal cell populations were identified. Aging showed declining rod-to-cone ratios, reduced bipolar cell proportions among interneurons, and increased astrocyte abundance. Muller glial cells exhibited the most pronounced transcriptional changes, followed by bipolar cells and rods. Machine-learning classifiers achieved 80-96% accuracy across cell types (microglia 96%, horizontal cells 93%, bipolar cells 91%, cones 90%, rods 89%). Shared aging signatures included mitochondrial dysfunction and inflammatory activation. Cell specific vulnerabilities emerged: mitochondria-centric stress in rods/bipolar cells, proteostasis-retinoid metabolism in cones, and structural-RNA maintenance in horizontal cells. ConclusionsThis study provides the first machine learning derived, cell-type specific aging signatures for human retina in a Chinese cohort, revealing both conserved molecular hallmarks and distinctive cellular vulnerabilities that inform targeted therapeutic strategies for retinal aging.