A foundation model for brain organoid network dynamics uncovers intrinsic computation and convergent disease phenotypes
- 1University of California Santa Cruz
Abstract
Brain organoids develop self-organizing neural networks that can be used to model neurodevelopment and disease. Here we introduce PULSE, a foundation model developed using over 900 hours of high-density microelectrode array recordings of in vitro and ex vivo neural tissue. We show that this single model can address two open questions: how disease-associated variants alter network development, and how naive circuits encode information. PULSE revealed accelerated network maturation in held-out human 16p11.2-deletion organoids. It also revealed a change in network coordination shared with SHANK3 deficiency. Because organoids develop without sensory input, they let us ask how circuits encode information before any representation is learned. Closed-loop control of a virtual inverted pendulum engaged existing spontaneous activity patterns rather than creating new ones. PULSE provides a common reference frame for neural circuits across genotypes, protocols and tasks.
Related
- Diverse genetic pathways drive convergent fluconazole and caspofungin resistance phenotypes in Candida albicans
- Activated macrophages restrict invasive bacterial infection in a human intestinal organoid co-culture model
- Multicellular Perturb-seq Reveals Lineage-Specific Transcriptional Control During Human Cardiac Organoid Development
- Emergent topological structure in spontaneous brain-organoid activity
- CORE: Deterministic alignment for bias-free organoid histology
BibTeX
@misc{schweiger2026foundation,
title = {{A foundation model for brain organoid network dynamics uncovers intrinsic computation and convergent disease phenotypes}},
author = {H. E. Schweiger and A. Robbins and S. Hernandez and A. Moreno-Ochando and I. Cline and K. Doganyigit and M. Mouzaya and K. Hussain and Z. P. Pang and J. Duan and S. R. Salama and A. A. Pollen and A. Bhaduri and D. Haussler and M. Teodorescu and M. A. Mostajo-Radji},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.11.758231},
url = {https://www.biorxiv.org/content/10.64898/2026.10.11.758231v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - A foundation model for brain organoid network dynamics uncovers intrinsic computation and convergent disease phenotypes
AU - H. E. Schweiger
AU - A. Robbins
AU - S. Hernandez
AU - A. Moreno-Ochando
AU - I. Cline
AU - K. Doganyigit
AU - M. Mouzaya
AU - K. Hussain
AU - Z. P. Pang
AU - J. Duan
AU - S. R. Salama
AU - A. A. Pollen
AU - A. Bhaduri
AU - D. Haussler
AU - M. Teodorescu
AU - M. A. Mostajo-Radji
PY - 2026
DA - 2026/10/11
PB - bioRxiv
DO - 10.64898/2026.10.11.758231
UR - https://www.biorxiv.org/content/10.64898/2026.10.11.758231v1
AB - Brain organoids develop self-organizing neural networks that can be used to model neurodevelopment and disease. Here we introduce PULSE, a foundation model developed using over 900 hours of high-density microelectrode array recordings of in vitro and ex vivo neural tissue. We show that this single model can address two open questions: how disease-associated variants alter network development, and how naive circuits encode information. PULSE revealed accelerated network maturation in held-out human 16p11.2-deletion organoids. It also revealed a change in network coordination shared with SHANK3 deficiency. Because organoids develop without sensory input, they let us ask how circuits encode information before any representation is learned. Closed-loop control of a virtual inverted pendulum engaged existing spontaneous activity patterns rather than creating new ones. PULSE provides a common reference frame for neural circuits across genotypes, protocols and tasks.
ER -