MoTRUST: adaptive semantic protection for mosaic single-cell integration and molecular recovery
- 1University of Science and Technology Beijing
Abstract
Single-cell multi-omics reveals complementary aspects of cellular identity, but heterogeneous assays produce incomplete modality combinations. Integrating these mosaic measurements while preserving biological structure and recovering missing molecular information remains challenging. We present MoTRUST, combining neural representations, adaptive semantic protection, molecular prediction and conditional residual diffusion. MoTRUST ranked first in overall integration across 30 tasks spanning six scenarios and surpassed the strongest evaluated controls on six of eleven development recovery endpoints. Conditional residual diffusion reduced aggregate marginal prediction scores by 4.4-5.1% across three ATAC-to-RNA data sources while preserving point predictions. Together, these capabilities enable accurate mosaic integration and molecular recovery for multimodal characterization of cellular heterogeneity.
Related
- Dynamic Semantic–Prosodic Integration in Emotional Speech Perception: From Channel Dominance to Precision-Weighted Predictive Coding
- Multiscale harmonization, semantic integration, and immersive exploration of single-cell data in support of novel biological insights
- Integration of molecular and cellular immunity in sea cucumbers: a comprehensive review
- Multi-Omics Integration Drives Precision Breeding in Sorghum: Molecular Dissection and Breeding Practice
- Plant Responses to Heavy Metal Stress: Molecular Mechanisms, Transcriptomic Regulation, and Multi-Omics Integration in Crop Improvement
BibTeX
@misc{liu2026motrust,
title = {{MoTRUST: adaptive semantic protection for mosaic single-cell integration and molecular recovery}},
author = {Q. Liu and Y. Xu},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.18.752592},
url = {https://www.biorxiv.org/content/10.64898/2026.09.18.752592v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - MoTRUST: adaptive semantic protection for mosaic single-cell integration and molecular recovery
AU - Q. Liu
AU - Y. Xu
PY - 2026
DA - 2026/09/18
PB - bioRxiv
DO - 10.64898/2026.09.18.752592
UR - https://www.biorxiv.org/content/10.64898/2026.09.18.752592v1
AB - Single-cell multi-omics reveals complementary aspects of cellular identity, but heterogeneous assays produce incomplete modality combinations. Integrating these mosaic measurements while preserving biological structure and recovering missing molecular information remains challenging. We present MoTRUST, combining neural representations, adaptive semantic protection, molecular prediction and conditional residual diffusion. MoTRUST ranked first in overall integration across 30 tasks spanning six scenarios and surpassed the strongest evaluated controls on six of eleven development recovery endpoints. Conditional residual diffusion reduced aggregate marginal prediction scores by 4.4-5.1% across three ATAC-to-RNA data sources while preserving point predictions. Together, these capabilities enable accurate mosaic integration and molecular recovery for multimodal characterization of cellular heterogeneity.
ER -