Generative Neuromorphic Programming of Mammalian Cells
- 1Massachusetts Institute of Technology
Abstract
Cells make decisions through densely interconnected regulatory networks that compute graded, analog responses. Synthetic biology has made cells programmable, but the field's dominant abstractions poorly match the analog nature of cells. Designing analog circuits that work in cells is challenging: predicting how components combine remains difficult, and the vast combinatorial space of parts, weights and topologies exceeds what experiments can explore. Here we establish generative programming of mammalian cells through a neuromorphic framework that compiles desired behavior into DNA. Composable regulatory devices built from RNA-targeting endoribonucleases (ERNs) supply signed weights and nonlinear activation, enabling multi-layer circuits with diverse multi-input analog responses. To predict and design such circuits, we develop biomorphic neural networks (BMNs): a compositional architecture that mirrors biological interactions, in which each basic process (transcription, translation, cleavage) is captured by a reusable neural block learned from the behavior of whole circuits that contain it. Recomposed into architectures absent from training, these models predict responses with errors often comparable to variability between experimental repeats. Inverting this process, our software package, the biocompiler, jointly optimizes topology, parts, and weights to realize specified target behaviors. Challenged with three target behaviors, the biocompiler proposed three previously unseen architectures; we built all three, and each reproduced its target behavior in mammalian cells in a single design pass without manual tuning. Generative neuromorphic programming thus offers a systematic route to engineering the analog computation native to living cells.
Related
- Synthetic reaction-diffusion patterning in mammalian cells
- Universal donor plasmids for biallelic degron-tagging in mammalian cells and organoids
- Functional roles for viral RNA ribosylation in mammalian cells
- stem.MAP: Identification of cell-type-specific protein complexes in mammalian embryonic stem cells.
- A step toward synthetic endosymbiosis: introducing Escherichia coli and the trypanosomatid endosymbiont Candidatus Kinetoplastibacterium crithidii into mammalian cells using a polyethylene glycol-based fusion protocol
BibTeX
@misc{disset2026generative,
title = {{Generative Neuromorphic Programming of Mammalian Cells}},
author = {J. Disset and C. Van De Mark and G. K. A. Wachter and S.-H. Kuo and A. Moorman and W. Xu and E. Palanques Tost and A. Buritica Monroy and C. Belta and R. Weiss},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.18.752793},
url = {https://www.biorxiv.org/content/10.64898/2026.09.18.752793v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Generative Neuromorphic Programming of Mammalian Cells
AU - J. Disset
AU - C. Van De Mark
AU - G. K. A. Wachter
AU - S.-H. Kuo
AU - A. Moorman
AU - W. Xu
AU - E. Palanques Tost
AU - A. Buritica Monroy
AU - C. Belta
AU - R. Weiss
PY - 2026
DA - 2026/09/18
PB - bioRxiv
DO - 10.64898/2026.09.18.752793
UR - https://www.biorxiv.org/content/10.64898/2026.09.18.752793v1
AB - Cells make decisions through densely interconnected regulatory networks that compute graded, analog responses. Synthetic biology has made cells programmable, but the field's dominant abstractions poorly match the analog nature of cells. Designing analog circuits that work in cells is challenging: predicting how components combine remains difficult, and the vast combinatorial space of parts, weights and topologies exceeds what experiments can explore. Here we establish generative programming of mammalian cells through a neuromorphic framework that compiles desired behavior into DNA. Composable regulatory devices built from RNA-targeting endoribonucleases (ERNs) supply signed weights and nonlinear activation, enabling multi-layer circuits with diverse multi-input analog responses. To predict and design such circuits, we develop biomorphic neural networks (BMNs): a compositional architecture that mirrors biological interactions, in which each basic process (transcription, translation, cleavage) is captured by a reusable neural block learned from the behavior of whole circuits that contain it. Recomposed into architectures absent from training, these models predict responses with errors often comparable to variability between experimental repeats. Inverting this process, our software package, the biocompiler, jointly optimizes topology, parts, and weights to realize specified target behaviors. Challenged with three target behaviors, the biocompiler proposed three previously unseen architectures; we built all three, and each reproduced its target behavior in mammalian cells in a single design pass without manual tuning. Generative neuromorphic programming thus offers a systematic route to engineering the analog computation native to living cells.
ER -