Temporal AI model predicts drivers of cell state trajectories across human aging

Foundational AI models have recently shown promise for predicting the impact of perturbations on cell states. However, current models typically consider only one cell state at a time, limiting their ability to learn how cellular responses unfold over time, particularly across long trajectories such as diseases of aging. Here, we develop a temporal AI model, MaxToki, trained on nearly 1 trillion gene tokens including cell state trajectories across the human lifespan to generate cell states across long timelapses of human aging. MaxToki generalized to unseen trajectories through in-context learning and predicted novel age-modulating targets that were experimentally verified to influence age-related gene programs and functional decline in vivo. MaxToki represents a promising strategy for temporal modeling to accelerate the discovery of interventions for programming therapeutic cellular trajectories.

Authors

Institutions

Publication Details

Journal
bioRxiv (Cold Spring Harbor Laboratory)
Published
2026-04-01
DOI
https://doi.org/10.64898/2026.03.30.715396
Primary Topic
Pluripotent Stem Cells Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Temporal AI model predicts drivers of cell state trajectories across human aging

Sarp Kurtoglu, Sarah Ancheta, Thomas X. Lu, Christina V. Theodoris et al.
bioRxiv (Cold Spring Harbor Laboratory)
Pluripotent Stem Cells Research
article

Temporal AI model predicts drivers of cell state trajectories across human aging

Sarp Kurtoglu, Sarah Ancheta, Thomas X. Lu, Christina V. Theodoris, Javier Gómez Ortega, Akira Kunitomi, Madigan M. Reid, Neha Tadimeti, Lukas Zanders, Steven Kothen-Hill, Michael Alexanian, Rangarajan D. Nadadur, Alexis J. Combes, Shinya Yamanaka, Sara Lichtarge, Kaho Washizu, Julian U G Wagner, Bumjoon Kim, Andrew C Yang, William A Johnson, Han Chen, Chris Thompson, Dereck M Phan, Yujie Zhang, Stefanie Dimmeler
article en

Abstract

Foundational AI models have recently shown promise for predicting the impact of perturbations on cell states. However, current models typically consider only one cell state at a time, limiting their ability to learn how cellular responses unfold over time, particularly across long trajectories such as diseases of aging. Here, we develop a temporal AI model, MaxToki, trained on nearly 1 trillion gene tokens including cell state trajectories across the human lifespan to generate cell states across long timelapses of human aging. MaxToki generalized to unseen trajectories through in-context learning and predicted novel age-modulating targets that were experimentally verified to influence age-related gene programs and functional decline in vivo. MaxToki represents a promising strategy for temporal modeling to accelerate the discovery of interventions for programming therapeutic cellular trajectories.

bioRxiv (Cold Spring Harbor Laboratory)
Goethe University Frankfurt (DE), Gladstone Institutes (US), University of California, San Francisco (US), Kyoto University (JP), Nvidia (United States) (US), University Hospital Frankfurt (DE), Institute on Aging (US), Cardio-Pulmonary Institute (DE), University of California, Berkeley (US)
Openalex Percentile: Top 33%
Pluripotent Stem Cells Research
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.