HESTIA: Scalable Multimodal Integration of Histology and High-Resolution Spatial Transcriptomics for Robust Spatial Domain Identification
- 1BGI Research
Abstract
Spatial omics has revolutionized molecular biology by providing invaluable insights into how native tissue microenvironments regulate cellular functions and disease mechanisms. Accurately capturing this structural complexity and decoding the underlying biological processes requires effectively integrating data from multiple modalities. However, transitioning to subcellular resolutions introduces massive data scales and severe transcriptomic sparsity, which challenge current analytical frameworks. To address this, we present HESTIA (Histology-Enhanced Scalable cross-Resolution inTegration for spatial trAnscriptomics), a highly efficient multimodal algorithm designed for identifying spatial domains in large-scale, high-resolution spatial omics data. By circumventing memory-intensive computations, HESTIA efficiently processes massive datasets on which existing algorithms fail due to memory constraints. HESTIA outperforms current multimodal methods in clustering accuracy and spatial continuity, accurately delineating fine structural boundaries. Furthermore, applying HESTIA to large-scale pathological samples successfully dissects clinically relevant intratumoral heterogeneity and maps distinct immune microenvironments in lung and colorectal cancers.
Versions
Related
- VGL-stGen: Learning a shared multimodal model for lung histology and spatial transcriptomics
- The SWAN atlas: an open multimodal resource combining neuroimaging and high-resolution histology of the human brain in stereotactic space
- MorphoProt: RNA-Conditioned Integration of Multiscale Histology for Spatial Protein Inference
- Probabilistic uncertainty in virtual spatial transcriptomics from histology is largely redundant with the predicted mean
- Multiscale, Survey-and-Target Optical Super-Resolution Histology
BibTeX
@misc{zhong2026hestia,
title = {{HESTIA: Scalable Multimodal Integration of Histology and High-Resolution Spatial Transcriptomics for Robust Spatial Domain Identification}},
author = {Z. Zhong and X. Zhu and J. Guo and S. Liao and A. Chen},
howpublished = {bioRxiv},
year = {2026},
month = may,
doi = {10.64898/2026.05.14.723098},
url = {https://www.biorxiv.org/content/10.64898/2026.05.14.723098v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - HESTIA: Scalable Multimodal Integration of Histology and High-Resolution Spatial Transcriptomics for Robust Spatial Domain Identification
AU - Z. Zhong
AU - X. Zhu
AU - J. Guo
AU - S. Liao
AU - A. Chen
PY - 2026
DA - 2026/05/14
PB - bioRxiv
DO - 10.64898/2026.05.14.723098
UR - https://www.biorxiv.org/content/10.64898/2026.05.14.723098v2
AB - Spatial omics has revolutionized molecular biology by providing invaluable insights into how native tissue microenvironments regulate cellular functions and disease mechanisms. Accurately capturing this structural complexity and decoding the underlying biological processes requires effectively integrating data from multiple modalities. However, transitioning to subcellular resolutions introduces massive data scales and severe transcriptomic sparsity, which challenge current analytical frameworks. To address this, we present HESTIA (Histology-Enhanced Scalable cross-Resolution inTegration for spatial trAnscriptomics), a highly efficient multimodal algorithm designed for identifying spatial domains in large-scale, high-resolution spatial omics data. By circumventing memory-intensive computations, HESTIA efficiently processes massive datasets on which existing algorithms fail due to memory constraints. HESTIA outperforms current multimodal methods in clustering accuracy and spatial continuity, accurately delineating fine structural boundaries. Furthermore, applying HESTIA to large-scale pathological samples successfully dissects clinically relevant intratumoral heterogeneity and maps distinct immune microenvironments in lung and colorectal cancers.
ER -