Biologically grounded cell profiling across microscopy modalities
- 1Peking University
Abstract
Microscopy-based cell profiling has broad applications in biological discovery, disease characterization, and phenotypic drug screening. Modern microscopy continues to push the limits of resolution, speed, depth and throughput, but better imaging does not automatically lead to better biomedical discovery and translation. A key bottleneck is feature representation: existing features are either handcrafted or learned as black-box embeddings and often lack explicit biological meaning. Here we propose biological grounding as a first principle for cell profiling and implement it through MorphAgent, an AI agent framework in which each quantitative feature originates from a biological hypothesis and is anchored to a cellular structure or process. By integrating biological knowledge, multimodal reasoning and automated validation, MorphAgent makes biologically grounded feature design systematic and scalable. We show biological grounding fundamentally changes the properties of cell profiling features. Across three microscopy modalities, MorphAgent produces compact, expressive and transferable features for drug screening, cell state characterization and disease morphology analysis. In wide-field Cell Painting, a common assay for phenotypic drug screening, it improves perturbation-retrieval mean average precision by 48% over CellProfiler and 20% over DeepProfiler while using substantially fewer dimensions. In confocal mitochondrial imaging, biologically grounded features transfer across independently acquired datasets and imaging resolutions, supporting accurate aging-state classification. In structured illumination microscopy (SIM) imaging of Tau-labeled samples, biologically grounded super resolution features reveal nanoscale morphologies inaccessible at conventional resolution, enhancing the discrimination of disease-associated mutations. Moreover, biologically grounded features provide a hierarchical organization of cellular morphology, enabling multilevel alignment with transcriptomics data and facilitating mechanistic understanding. Biologically grounded cell profiling thus brings AI reasoning closer to biological mechanisms, advancing biomedical discovery and translation.
Related
- From Closed-Set Annotation to In-Context Discovery: Biologically Grounded LLMs for Cellular Profiling
- Biologically grounded locality priors close the data gap for vision transformers in neural prediction
- Physics-Grounded Simulation Enables Zero-Shot Molecular and Reaction Analysis in Scanning Tunneling Microscopy
- Neural effects of expectation violation generalise across sensory modalities
- HIPPIE: a generative model for electrophysiological analysis across species, technologies, and modalities
BibTeX
@misc{ye2026biologically,
title = {{Biologically grounded cell profiling across microscopy modalities}},
author = {E. Ye and X. Wu and R. Peng and W. Hu and X. Li and X. Zhang and M. Niu and Y. Guo and X. Sheng and J. Wang and L. Chen and H. Sun},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.23.753678},
url = {https://www.biorxiv.org/content/10.64898/2026.09.23.753678v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Biologically grounded cell profiling across microscopy modalities
AU - E. Ye
AU - X. Wu
AU - R. Peng
AU - W. Hu
AU - X. Li
AU - X. Zhang
AU - M. Niu
AU - Y. Guo
AU - X. Sheng
AU - J. Wang
AU - L. Chen
AU - H. Sun
PY - 2026
DA - 2026/09/23
PB - bioRxiv
DO - 10.64898/2026.09.23.753678
UR - https://www.biorxiv.org/content/10.64898/2026.09.23.753678v1
AB - Microscopy-based cell profiling has broad applications in biological discovery, disease characterization, and phenotypic drug screening. Modern microscopy continues to push the limits of resolution, speed, depth and throughput, but better imaging does not automatically lead to better biomedical discovery and translation. A key bottleneck is feature representation: existing features are either handcrafted or learned as black-box embeddings and often lack explicit biological meaning. Here we propose biological grounding as a first principle for cell profiling and implement it through MorphAgent, an AI agent framework in which each quantitative feature originates from a biological hypothesis and is anchored to a cellular structure or process. By integrating biological knowledge, multimodal reasoning and automated validation, MorphAgent makes biologically grounded feature design systematic and scalable. We show biological grounding fundamentally changes the properties of cell profiling features. Across three microscopy modalities, MorphAgent produces compact, expressive and transferable features for drug screening, cell state characterization and disease morphology analysis. In wide-field Cell Painting, a common assay for phenotypic drug screening, it improves perturbation-retrieval mean average precision by 48% over CellProfiler and 20% over DeepProfiler while using substantially fewer dimensions. In confocal mitochondrial imaging, biologically grounded features transfer across independently acquired datasets and imaging resolutions, supporting accurate aging-state classification. In structured illumination microscopy (SIM) imaging of Tau-labeled samples, biologically grounded super resolution features reveal nanoscale morphologies inaccessible at conventional resolution, enhancing the discrimination of disease-associated mutations. Moreover, biologically grounded features provide a hierarchical organization of cellular morphology, enabling multilevel alignment with transcriptomics data and facilitating mechanistic understanding. Biologically grounded cell profiling thus brings AI reasoning closer to biological mechanisms, advancing biomedical discovery and translation.
ER -