RamiGlyph Captures Microglial Morphological Diversity and Predicts Functional States in Ischemia Reperfusion and Amyloid Pathology
- 1Zhejiang University
Abstract
Microglia are resident immune cells of the central nervous system, whose ramified processes rapidly remodel in response to injury. However, how to capture subtle morphological changes and whether functional state can be predicted from morphology remain open questions. Here, we present RamiGlyph, a contrastive learning framework integrating topological and structural features, trained on more than 20,000 reconstructed microglia. RamiGlyph not only distinguishes physiological and pathological states of microglia but also generalizes to neuronal cell type classification. Projection of microglia morphological embeddings revealed a continuum rather than discrete classes, from which a morphology score was derived to quantify dynamic process remodeling. To link morphology with function, Gromov Wasserstein optimal transport was used to align unpaired morphological and functional data across stages of ischemia reperfusion injury and amyloid pathology. These alignment results enable prediction of microglial functional states using RamiGlyph embeddings alone, with prediction reliability increasing upon cell aggregation. In summary, RamiGlyph provides a robust framework for resolving continuous microglial morphological variation and linking morphology to functional states across acute and chronic neuropathological contexts.
Related
- Integrated morphological, multi-omics, and functional profiling reveals microglial plasticity driven by AD risk genes
- Evaluation of morphological diversity of wild Iris species in Hatay Province, Türkiye
- Integrated analysis of morphological and molecular diversity in tomato (Solanum lycopersicum L.) cultivated under protected environment
- Genetic and morphological insights reveal the hidden and colorful diversity in Oscarella sponges
- Cryptic diversity in groundwater amphipods of Iran: insights from morphological and molecular approaches
BibTeX
@misc{qu2026ramiglyph,
title = {{RamiGlyph Captures Microglial Morphological Diversity and Predicts Functional States in Ischemia Reperfusion and Amyloid Pathology}},
author = {Y. Qu and Y. Xiao and T. Lan and J. Xu and J. Liu and Q. Qian and J. Liu and Y. Chi},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.10.750561},
url = {https://www.biorxiv.org/content/10.64898/2026.09.10.750561v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - RamiGlyph Captures Microglial Morphological Diversity and Predicts Functional States in Ischemia Reperfusion and Amyloid Pathology
AU - Y. Qu
AU - Y. Xiao
AU - T. Lan
AU - J. Xu
AU - J. Liu
AU - Q. Qian
AU - J. Liu
AU - Y. Chi
PY - 2026
DA - 2026/09/10
PB - bioRxiv
DO - 10.64898/2026.09.10.750561
UR - https://www.biorxiv.org/content/10.64898/2026.09.10.750561v1
AB - Microglia are resident immune cells of the central nervous system, whose ramified processes rapidly remodel in response to injury. However, how to capture subtle morphological changes and whether functional state can be predicted from morphology remain open questions. Here, we present RamiGlyph, a contrastive learning framework integrating topological and structural features, trained on more than 20,000 reconstructed microglia. RamiGlyph not only distinguishes physiological and pathological states of microglia but also generalizes to neuronal cell type classification. Projection of microglia morphological embeddings revealed a continuum rather than discrete classes, from which a morphology score was derived to quantify dynamic process remodeling. To link morphology with function, Gromov Wasserstein optimal transport was used to align unpaired morphological and functional data across stages of ischemia reperfusion injury and amyloid pathology. These alignment results enable prediction of microglial functional states using RamiGlyph embeddings alone, with prediction reliability increasing upon cell aggregation. In summary, RamiGlyph provides a robust framework for resolving continuous microglial morphological variation and linking morphology to functional states across acute and chronic neuropathological contexts.
ER -