AtlasOT - The Fused Unbalanced Gromov-Wasserstein for Multimodal Integration of Disease Atlases
- 1RWTH Aachen University Hospital
Abstract
Single-cell and spatial multiomics technologies are transforming disease atlas construction, but computational integration of unpaired modalities remains challenging, as existing methods overlook two biological constraints of data with matching samples. First, cells should only be mapped across modalities within the same donor or biospecimen, and second, cell recovery frequently differs substantially between modalities. To address these gaps, we present AtlasOT, an optimal-transport framework based on the fused unbalanced Gromov-Wasserstein (FUGW) formulation for multi-modal integration. AtlasOT jointly models a shared cross-modality feature space and modality-specific geometric structures while restricting transport to within-sample cell pairs. Moreover, AtlasOT relaxes strict mass conservation of the balanced optimal transport optimization to accommodate unbalanced cell numbers. We benchmark AtlasOT against state-of-the-art methods on scRNA-scATAC and scRNA-spatial transcriptomics mapping scenarios. Our results indicate that AtlasOT outperforms baselines and state-of-the-art methods in all considered scenarios. Moreover, we demonstrate that AtlasOT's transport plan can be used to improve several relevant tasks such as the detection of rare cell populations, spot-level cell-type deconvolution, spatial gene imputation, and reconstruction of transcription-factor-driven spatial regulatory dynamics. These results establish AtlasOT as a unified, biologically constrained framework for multimodal integration in disease atlas studies, with broad applicability to label transfer, imputation, and regulatory network analysis.
Related
- Enhancement of gut-microbiome-based classification of prodromal Parkinson's Disease cases by hyperparameter tuning, integration of multimodal data, and meta-analysis.
- HESTIA: Scalable Multimodal Integration of Histology and High-Resolution Spatial Transcriptomics for Robust Spatial Domain Identification
- Engineering developmental transitions during human neurulation through modular integration of multimodal spatial cues
- The C. elegans Connectome Toolbox: an open, extensible framework for multimodal connectomic data integration and analysis
- Multimodal data integration to determine viral and innate immune kinetics in human airway epithelium
BibTeX
@misc{peng2026atlasot,
title = {{AtlasOT - The Fused Unbalanced Gromov-Wasserstein for Multimodal Integration of Disease Atlases}},
author = {K. Peng and M. Ruiz and B. Caron and C. Kuppe and J. Nagai and I. Gesteira Costa Filho},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.22.753496},
url = {https://www.biorxiv.org/content/10.64898/2026.09.22.753496v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - AtlasOT - The Fused Unbalanced Gromov-Wasserstein for Multimodal Integration of Disease Atlases
AU - K. Peng
AU - M. Ruiz
AU - B. Caron
AU - C. Kuppe
AU - J. Nagai
AU - I. Gesteira Costa Filho
PY - 2026
DA - 2026/09/22
PB - bioRxiv
DO - 10.64898/2026.09.22.753496
UR - https://www.biorxiv.org/content/10.64898/2026.09.22.753496v1
AB - Single-cell and spatial multiomics technologies are transforming disease atlas construction, but computational integration of unpaired modalities remains challenging, as existing methods overlook two biological constraints of data with matching samples. First, cells should only be mapped across modalities within the same donor or biospecimen, and second, cell recovery frequently differs substantially between modalities. To address these gaps, we present AtlasOT, an optimal-transport framework based on the fused unbalanced Gromov-Wasserstein (FUGW) formulation for multi-modal integration. AtlasOT jointly models a shared cross-modality feature space and modality-specific geometric structures while restricting transport to within-sample cell pairs. Moreover, AtlasOT relaxes strict mass conservation of the balanced optimal transport optimization to accommodate unbalanced cell numbers. We benchmark AtlasOT against state-of-the-art methods on scRNA-scATAC and scRNA-spatial transcriptomics mapping scenarios. Our results indicate that AtlasOT outperforms baselines and state-of-the-art methods in all considered scenarios. Moreover, we demonstrate that AtlasOT's transport plan can be used to improve several relevant tasks such as the detection of rare cell populations, spot-level cell-type deconvolution, spatial gene imputation, and reconstruction of transcription-factor-driven spatial regulatory dynamics. These results establish AtlasOT as a unified, biologically constrained framework for multimodal integration in disease atlas studies, with broad applicability to label transfer, imputation, and regulatory network analysis.
ER -