AI & data

Tue 29 Sep12 papers

bioRxivIn silicoPreprint

Tool maps spatial cell-cell signals in brain aging and cancer

Applied to over 5.8 million spatially profiled cells, the framework identified a T-cell-associated brain-aging program and signals that predicted age…Applied to over 5.8 million spatially profiled cells, the framework identified a T-cell-associated brain-aging program and signals that predicted age across regions. In spatially profiled tissue cells, researchers developed SpiderNet, a computational framework that identifies directed…

Machine learning
bioRxivIn silicoPreprint

Single-cell foundation models show task-dependent utility for aging biology research

A benchmark across 2.5 million single-cell transcriptomes reveals strengths in detecting rare cell states and gene networks, though simple gene sets…A benchmark across 2.5 million single-cell transcriptomes reveals strengths in detecting rare cell states and gene networks, though simple gene sets predicted age better. In a computational preprint analyzing more than 2.5 million single-cell transcriptomes, researchers benchmarked ten…

A round reddish granular cell stands beside a cluster of dark, irregularly shaped cells, contrasting with smaller cell clusters nearby.
Foundation models
Age and AgeingHumans

Immune cell profiles predict cognitive decline in older adults

In 4,464 cognitively normal older adults, a higher immune risk score predicted incident cognitive impairment or dementia with a hazard ratio of 1.63…In 4,464 cognitively normal older adults, a higher immune risk score predicted incident cognitive impairment or dementia with a hazard ratio of 1.63 over six years. In 9,008 older adults from the Health and Retirement Study, researchers measured 24 peripheral immune cell subsets using flow…

GDF-15
Alzheimer's & DementiaHumans

Biological aging clocks combined with genetics improve dementia risk prediction

Adding proteomic, metabolomic, and clinical aging measures to polygenic scores boosted prediction accuracy in two large human cohorts.Adding proteomic, metabolomic, and clinical aging measures to polygenic scores boosted prediction accuracy in two large human cohorts. Researchers evaluated 16,215 UK Biobank participants who were dementia-free at baseline over a median follow-up of 10.08 years.

Participant selection and study workflow.
Telomere length

Mon 28 Sep10 papers

medRxivHumansPreprint

Genetic scores add more predictive power at lower clinical risk

For atherosclerotic cardiovascular disease, polygenic risk expanded the clinically identified high-risk subgroup by 40%, revealing patients with…For atherosclerotic cardiovascular disease, polygenic risk expanded the clinically identified high-risk subgroup by 40%, revealing patients with 4.9-fold higher incidence than those remaining low-risk.

Development and validation of clinical disease-risk prediction models.
Polygenic risk score
International Journal of Medical InformaticsHumans

Sex-specific clinical history improves multimorbidity prediction

In about 155,000 PLCO cohort participants, adding sex-specific clinical history to models improved disease prediction and calibration, especially at…In about 155,000 PLCO cohort participants, adding sex-specific clinical history to models improved disease prediction and calibration, especially at higher multimorbidity burdens.

Graphical abstract
Multimorbidity
Archives of Gerontology and GeriatricsHumans

Calf size and physical function predict heart failure mortality

In 7,362 older patients hospitalized with heart failure, combining physical performance scores with calf circumference stratified one-year mortality…In 7,362 older patients hospitalized with heart failure, combining physical performance scores with calf circumference stratified one-year mortality risk across cohorts. In a multicenter study of 7,362 Japanese patients aged 65 and older hospitalized with heart failure, researchers…

Graphical abstract
Short Physical Performance Battery
Frontiers in EndocrinologyHumans

Six blood metabolites distinguish metabolic health in obesity

A combined clinical-metabolomic model discriminated healthy from unhealthy obesity with an AUC of 0.78, compared with 0.69 for clinical variables…A combined clinical-metabolomic model discriminated healthy from unhealthy obesity with an AUC of 0.78, compared with 0.69 for clinical variables alone. In 13,215 adults with obesity from the UK Biobank, researchers evaluated whether circulating metabolites could distinguish metabolically…

Study design and flow diagram of participant inclusion and exclusion.
HDL cholesterol

Sun 27 Sep1 paper

Sat 26 Sep25 papers

Aging CellHumans

Deep-learning SASP score predicts mortality and disease

Trained on UK Biobank proteomic data, a deep-learning senescence score independently predicted mortality risk and shifted during an 18-month exercise…Trained on UK Biobank proteomic data, a deep-learning senescence score independently predicted mortality risk and shifted during an 18-month exercise trial. In human data from the UK Biobank Pharma Proteomics Project, researchers developed a composite score to track systemic cellular…

Dense blood cells and granules under vital organs above standing figures contrast with a sparser cluster above active figures exercising.
Biomarkers
Nature AgingAnimals

Oral bacterium shifts aged mouse profiles toward younger states

Supplementing aged mice with heat-killed Neisseria flavescens restored their serum metabolome, liver transcriptome and gut microbiome toward younger…Supplementing aged mice with heat-killed Neisseria flavescens restored their serum metabolome, liver transcriptome and gut microbiome toward younger states. Analyzing human multi-modality data, researchers identified the oral commensal bacterium Neisseria flavescens as associated with…

A dark, mottled liver above a mouse, beside a reddish liver above a mouse facing paired bacterial cells.
Interventions
Nature AgingHumans

Kidney tubular epithelial cells drive accelerated epigenetic aging in disease

A cross-species single-cell atlas links injured human kidney cells and aged mouse kidneys to shared chromatin reorganization and impaired repair.A cross-species single-cell atlas links injured human kidney cells and aged mouse kidneys to shared chromatin reorganization and impaired repair. Analyzing healthy and injured human kidneys alongside aged mouse kidneys, researchers created a cross-species single-cell multiomics atlas…

Figure 1
Resources: datasets, atlases and tools
Nature CommunicationsHumans

Retinal imaging model predicts age and reveals sex differences in human aging

The retinal age gap correlates with mortality, disease risks, and sex-specific genetic pathways in more than 71,000 UK Biobank participants.The retinal age gap correlates with mortality, disease risks, and sex-specific genetic pathways in more than 71,000 UK Biobank participants. Researchers analyzed retinal fundus images from 71,343 human participants in the UK Biobank.

Two retinal fundus scans above two hearts, one paired with a cluster of fat cells and the other with a branching vascular network.
Metabolic syndrome
Experimental GerontologyHumans

Machine learning frailty index from healthcare claims predicts mortality and disability

Integrating diagnoses, medications, and procedures into a 63-item tool outperformed an established multimorbidity index in adults aged 50 and older.Integrating diagnoses, medications, and procedures into a 63-item tool outperformed an established multimorbidity index in adults aged 50 and older. Researchers evaluated middle-aged and older adults aged 50 and older by linking the Taiwan Longitudinal Study on Aging with the National…

Figure 1
Frailty index