Vitality Watch

Dossier pubmed preclinical 15-dec-2025
Animal model, organoid, or cell-culture result — not yet human

Discrimination of normal from slow-aging mice by plasma metabolomic and proteomic features.

Key claim: Plasma metabolomic and proteomic features trained with XGBoost can discriminate slow-aging from control mice and predict lifespan extension for held-out anti-aging interventions, sexes, and long-lived mutants, with longer-chain triglycerides enriched in slow-aging animals.

Abstract

Tests that can predict whether a drug is likely to extend mouse lifespan could speed up the search for anti-aging drugs. We have applied a machine learning algorithm, XGBoost regression, to seek sets of plasma metabolites (n = 12,000) and peptides (n = 17,000) that can discriminate control mice from mice treated with one of five anti-aging interventions (n = 278 mice). When the model is trained on any four of these five interventions, it predicts significantly higher lifespan extension in mice exposed to the intervention which was not included in the training set. Plasma peptide data sets also succeed at this task. Models trained on drug-treated normal mice also discriminate long-lived mutant mice from their respective controls, and models trained on males can discriminate drug-treated from control females. Triglycerides are over-represented among the most influential features in the regression models. Triglycerides with longer fatty acid chains tend to be higher in the slow-aging mice, while triglycerides with shorter fatty acid chains tend to decrease. Plasma metabolite patterns may help to select the most promising anti-aging drugs in mice or in humans and may give new leads into physiological and enzymatic targets relevant to the discovery of new anti-aging drugs.

Why this matters

Most proteomic and metabolomic aging signatures are trained on a single intervention or cross-sectional age data and rarely tested on held-out interventions. A classifier that transfers across unseen anti-aging drugs, both sexes, and long-lived mutants is the kind of generalization that would make a plasma readout usable as a preclinical geroprotector screen, and the longer-chain triglyceride enrichment gives a concrete biological handle rather than a black-box score — though discriminating slow-aging mice is still a classification task, not a demonstration that moving the signature extends lifespan.

Source

Link

Briefing card

Discrimination of normal from slow-aging mice by plasma metabolomic and proteomic features.
Stage: preclinical · pubmed · 15-dec-2025

Applies to preclinical geroprotector screening: candidate interventions in mice now have a plasma metabolomic/proteomic classifier reported to generalize across drugs, sexes, and long-lived mutants, with long-chain triglycerides as a specific feature to watch.

Plasma metabolomic and proteomic features trained with XGBoost can discriminate slow-aging from control mice and predict lifespan extension for held-out anti-aging interventions, sexes, and long-lived mutants, with longer-chain triglycerides enriched in slow-aging animals.

Cross-references (0)

None recorded — doctrine links and citations appear here as scans and citation sweeps find them.

External: doi:10.1007/s11357-025-02028-3

build build 880 · 2bcef25 · 2026-11-18