Benchmarking single-cell foundation models for aging biology
Ni, X.; Liang, Y.; Zhu, J.; Zhang, L.; Shen, X.; Yang, M.; Xu, R.; Li, H.; Ji, R.; Jin, C.; Ni, S.
Show abstract
Single cell foundation models (scFMs) provide representations of cellular states, but their utility across biological questions in aging research remains unclear. We established a benchmark of cellular representations for aging research, evaluating ten general-purpose scFMs, three aging-specific models and conventional methods across five biological questions using more than 2.5 million single cell transcriptomes. Using frozen pretrained representations, Geneformer performed best among scFMs for chronological age prediction and age pseudotime concordance, although 2,000 highly variable genes achieved higher mean performance. Several scFMs captured positive molecular age shifts across three disease contexts, consistent with reported aging-associated changes. SCimilarity performed well for rare cellular state identification across out-of-distribution datasets, exceeding aging specific models and conventional baselines. At the gene level, scGPT showed the highest recovery of reference TF target interactions, including aging-related regulatory hubs. Overall, scFMs supported diverse aging analyses, but performance depended on the biological question, highlighting their utility for rare cellular state identification and regulatory analysis.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Precision Estimates of Longitudinal Brain Aging Capture Unexpected Individual Differences in One Year 96%
- Spinal cord structural and functional architecture and its shared organization with the brain across the adult lifespan 95%
- Integrative epigenetics and transcriptomics identify aging genes in human blood 95%
Similar papers in this journal
- scAgeClock: a single-cell transcriptome based human aging clock model using gated multi-head attention neural networks 97%
- Divergent patterns of healthy aging across human brain regions at single-cell resolution reveal links to neurodegenerative disease 95%
- LinAge2: Providing actionable insights and benchmarking with epigenetic clocks 95%
Similar papers in this journal
- ORANGE: A Machine Learning Approach for Modeling Tissue-Specific Aging from Transcriptomic Data 95%
- Age-specific gene signatures underlying the transcriptomes and functional connectomes of human cerebral cortex 91%
- Causal differential expression analysis under unmeasured confounders with causarray 90%
Similar papers in this journal
- A Trans-Omic Mendelian Randomization Study of Parental Lifespan Uncovers Novel Aging Biology and Drug Candidates for Human Healthspan Extension 96%
- A transcriptome based aging clock near the theoretical limit of accuracy 95%
- Epistemic uncertainty challenges aging clock reliability in predicting rejuvenation effects 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.