Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 47 min ago
PreprintCC BY 4.0arXiv

Morpheus.AI: agents autonomously generate, execute and refine virtual tissue models

  • Prerana Chandratre
  • Anjali Sharma
  • Justin Bürger Michaelis
  • Diego Jahn
  • Jörn Starruß
  • Lutz Brusch
  • Simon Syga
Open at sourcePDFDOICite

Abstract

Virtual tissue models link observations to mechanistic hypotheses, but building them demands expertise in biology, mathematics and programming. Here, large language model (LLM) agents paired with the simulator Morpheus (Morpheus.AI) autonomously built such models from fifteen benchmark studies, five without a published model. With a frontier LLM, agents that ran their simulations met 83-86% of study-specific criteria in under two hours and for under US$4 per model. Such agents could make in silico modeling routine.

Related

  1. Caenorhabditis elegans DAF-18/PTEN non-autonomously prevents tumors by enhancing calcium sensitivity
    J. Deng, I. C. Djiomo Mbieda, A. M. Chaudhari +5
    bioRxivPreprintAll rights reservedFull textDevelopmental biologybioRxiv
  2. Paraventricular Thalamus Neurons Encode Early-life Stress and Execute Consequent Sex-specific Disruptions of Adult Reward Behaviors
    Cassandra L. Kooiker, Mason Hardy, Matthew T. Birnie +11
    Biological Psychiatry Global Open SciencePeer-reviewedCC BY-NC-NDFull text10 citedNeuroscienceOpenAlex
  3. Non-muscle myosin II acts non-cell autonomously to guide collective migration of the zebrafish polster cells
    Amélie Elouin, Arthur Boutillon, Nicolas David
    HALPreprintCC BY 4.0Full textCell biologyHAL
  4. Asymmetric Costs of Coordination Errors Generate Selection on Social and Sensorimotor Phenotypes in an Animal Collective
    L. C. Larter, M. J. Ryan, M. J. Fuxjager
    bioRxivPreprintAll rights reservedFull textZoology & animal behaviourbioRxiv
  5. Correlated traits generate the structure and stability of multiplex ecological networks
    K. R. S. Hale, E. Thebault, F. S. Valdovinos
    bioRxivPreprintCC BY-NCFull textEcologybioRxiv

Cite

BibTeXRIS
BibTeX
@misc{chandratre2026morpheusai,
  title = {{Morpheus.AI: agents autonomously generate, execute and refine virtual tissue models}},
  author = {Prerana Chandratre and Anjali Sharma and Justin Bürger Michaelis and Diego Jahn and Jörn Starruß and Lutz Brusch and Simon Syga},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.05413},
  eprint = {2611.05413},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.05413},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Morpheus.AI: agents autonomously generate, execute and refine virtual tissue models
AU  - Prerana Chandratre
AU  - Anjali Sharma
AU  - Justin Bürger Michaelis
AU  - Diego Jahn
AU  - Jörn Starruß
AU  - Lutz Brusch
AU  - Simon Syga
PY  - 2026
DA  - 2026/11/01
PB  - arXiv
DO  - 10.48550/arxiv.2611.05413
UR  - https://arxiv.org/abs/2611.05413
AB  - Virtual tissue models link observations to mechanistic hypotheses, but building them demands expertise in biology, mathematics and programming. Here, large language model (LLM) agents paired with the simulator Morpheus (Morpheus.AI) autonomously built such models from fifteen benchmark studies, five without a published model. With a frontier LLM, agents that ran their simulations met 83-86% of study-specific criteria in under two hours and for under US$4 per model. Such agents could make in silico modeling routine.
ER  -