Back

The End of Aging Clocks: Training Foundation Models to Reason in Aging and Longevity

Zhavoronkov, A.; Aladinskyi, V.; Aliper, A.; Miftakhutdinov, Z.; Reymond, M.; Naumov, V.; Zagirova, D.; Pushkov, S.; Sidorenko, D.; Shayakhmetov, R.; Galkin, F.

2026-03-30 bioinformatics
10.64898/2026.03.28.714980 bioRxiv
Show abstract

The aging clock paradigm has yielded dozens of specialist models that can estimate chronological age or mortality from virtually any biodata type. Yet each such model operates within a fixed modality, relies on a predetermined feature set, and produces limited biological interpretation. Here, we report Longevity-LLM v0.1, a Qwen3-14B model fine-tuned through supervised and reinforcement learning regimes on DNA methylation, proteomics, clinical biomarker, and RNA expression data. Longevity-LLM achieves high ranks in the recently announced Longevity Bench, including such tasks as cancer survival and RNA- or proteome-based age prediction. After reinforcement fine-tuning, the model achieved a 4.34-year MAE in epigenetic age prediction, surpassing the Horvath multi-tissue clock. In addition to age prediction, Longevity-LLM can carry out numerous other tasks, including proteomic profile generation, for which it significantly outperforms all frontier LLMs. These results demonstrate that a single modestly sized LLM can match or replace purpose-built aging clocks across data modalities. This work constitutes an interim report from the initial sprint of our Multi-Modal AI Gym for Science (MMAI), an initiative dedicated to building foundation models for drug discovery and aging research.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Aging Cell
144 papers in training set
Top 0.6%
12.3%
2
Nature Aging
51 papers in training set
Top 0.1%
10.1%
3
Nature Communications
4913 papers in training set
Top 28%
6.4%
4
Advanced Science
249 papers in training set
Top 3%
6.4%
5
Nature Machine Intelligence
61 papers in training set
Top 0.4%
6.3%
6
Cell Systems
167 papers in training set
Top 2%
4.9%
7
Cell Genomics
162 papers in training set
Top 0.8%
4.9%
50% of probability mass above
8
Nature
575 papers in training set
Top 7%
3.7%
9
Nature Medicine
117 papers in training set
Top 0.8%
3.6%
10
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 23%
3.1%
11
npj Aging
15 papers in training set
Top 0.4%
2.1%
12
eLife
5422 papers in training set
Top 38%
1.9%
13
Briefings in Bioinformatics
326 papers in training set
Top 4%
1.8%
14
Cell Reports
1338 papers in training set
Top 24%
1.7%
15
Nucleic Acids Research
1128 papers in training set
Top 11%
1.7%
16
PLOS Computational Biology
1633 papers in training set
Top 18%
1.5%
17
Frontiers in Genetics
197 papers in training set
Top 6%
1.5%
18
Patterns
70 papers in training set
Top 1%
1.3%
19
Bioinformatics Advances
184 papers in training set
Top 3%
1.3%
20
Aging
69 papers in training set
Top 2%
1.2%
21
Computational and Structural Biotechnology Journal
216 papers in training set
Top 7%
1.1%
22
Nature Methods
336 papers in training set
Top 5%
0.9%
23
Science Advances
1098 papers in training set
Top 25%
0.9%
24
GeroScience
97 papers in training set
Top 1%
0.9%
25
Nature Metabolism
56 papers in training set
Top 2%
0.8%
26
Bioinformatics
1061 papers in training set
Top 9%
0.7%
27
Scientific Reports
3102 papers in training set
Top 75%
0.7%
28
iScience
1063 papers in training set
Top 32%
0.7%
29
Genomics, Proteomics & Bioinformatics
171 papers in training set
Top 7%
0.7%
30
Genome Research
409 papers in training set
Top 4%
0.7%