Skip to content
DraconiticResearch
Search Sources API
182,544 studies31 sourcesUpdated 10 min ago
PreprintCC BY-NC-NDbioRxiv

Microscope control with a natural language agent

  • Z. Marin1
  • A. Abouelezz
  • N. M. C. Duque de Estrada
  • S. V. Schweighofer
  • F. Hauser
  • L. T. Koestinger
  • A. Manjunath
  • N. Stuurman
  • F. Schueder
  • J. Ries
  1. 1Max Perutz Labs, University of Vienna
Read full textPDFDOICite

Abstract

Microscopy underpins modern biology, but acquiring high-quality data from complex experiments at scale remains challenging. Smart microscopy can standardize and automate data collection, but each experiment-specific solution requires coding expertise and development time. To address this, we present MicroClaw, an AI agent that advises on experiment- and system-specific parameters and approaches and collaboratively plans and executes diverse, complex, and reusable imaging workflows across microscope platforms, without requiring expert knowledge.

Related

  1. Programmable design of functional proteins from natural language
    Fengyuan Dai, Shiyang You, Yudian Zhu +30
    NaturePeer-reviewedLicence not statedFull text16 citedMolecular biology & gene regulationOpenAlex
  2. Designing Protein Structures from Natural Language
    Joseph Lee, Yanjing Li, Bo Qiang +7
    arXivPreprintCC BY 4.0Full textBiophysicsarXiv
  3. Metabolic control of methylation landscapes in cancer growth and plasticity: targeting the epigenetic-metabolic axis with natural compounds and emerging therapies.
    Qi Liu, Ying Yu, Wenbo Li +5
    Frontiers in cell and developmental biologyPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCPMC
  4. Characterizing the structure of 3D DNA origami in a transmission electron microscope
    Alyna Ong, Christoph Hadlich, Taekyu Jeong +5
    RSC advancesPeer-reviewedCC BY-NCFull textStructural biologyEurope PMCPMC
  5. MIMAS: An open-source microlens-array miniature microscope for accessible large-field cortical imaging in freely behaving mice
    Mian Xie, Jingyi Ma, Baoyi Zhang +10
    Science AdvancesPeer-reviewedCC BY-NCBiophysicsCrossref

Cite

BibTeXRIS
BibTeX
@misc{marin2026microscope,
  title = {{Microscope control with a natural language agent}},
  author = {Z. Marin and A. Abouelezz and N. M. C. Duque de Estrada and S. V. Schweighofer and F. Hauser and L. T. Koestinger and A. Manjunath and N. Stuurman and F. Schueder and J. Ries},
  howpublished = {bioRxiv},
  year = {2026},
  month = sep,
  doi = {10.64898/2026.09.15.751723},
  url = {https://www.biorxiv.org/content/10.64898/2026.09.15.751723v1},
  note = {CC BY-NC-ND},
}
RIS
TY  - UNPB
TI  - Microscope control with a natural language agent
AU  - Z. Marin
AU  - A. Abouelezz
AU  - N. M. C. Duque de Estrada
AU  - S. V. Schweighofer
AU  - F. Hauser
AU  - L. T. Koestinger
AU  - A. Manjunath
AU  - N. Stuurman
AU  - F. Schueder
AU  - J. Ries
PY  - 2026
DA  - 2026/09/15
PB  - bioRxiv
DO  - 10.64898/2026.09.15.751723
UR  - https://www.biorxiv.org/content/10.64898/2026.09.15.751723v1
AB  - Microscopy underpins modern biology, but acquiring high-quality data from complex experiments at scale remains challenging. Smart microscopy can standardize and automate data collection, but each experiment-specific solution requires coding expertise and development time. To address this, we present MicroClaw, an AI agent that advises on experiment- and system-specific parameters and approaches and collaboratively plans and executes diverse, complex, and reusable imaging workflows across microscope platforms, without requiring expert knowledge.
ER  -