Interpretable Aging Signatures in Human Retinal Cell Types Revealed by Single-Cell RNA Sequencing and Sparse Logistic Regression
Discuss this preprint
Start a discussion What are Sciety discussions?Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Purpose
To characterize cell type specific transcriptional changes during human retinal aging and develop machine learning model for cellular age discrimination in a Chinese cohort.
Design
Cross-sectional, laboratory-based observational study.
Participants
Eighteen unfrozen retinas from 12 Chinese donors (9 young, 34-55y; 9 old, 68-92 y).
Methods
Single-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 Measures
Age-related cellular composition shifts; cell-type-specific differentially expressed genes; machine-learning classifier accuracy and feature rankings; transcription factor regulon activity changes.
Results
Eleven major retinal cell populations were identified. Aging showed declining rod-to-cone ratios, reduced bipolar cell proportions among interneurons, and increased astrocyte abundance. Müller 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.
Conclusions
This 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.
