Recommendation system-inspired learning of crossmodal interaction patterns between chromatin accessibility and gene expression
Abstract
Despite the growing availability of crossmodal single-cell sequencing, existing approaches are limited by underutilization of biological attributes, sparse modality signals, and insufficient modeling of regulatory interactions, limiting generalization in data-scarce settings and the discovery of peak-gene-level relationships. Interestingly, such challenges mirror those in recommendation systems, where side information, high sparsity, binary interactions, and cold start problems are extensively studied. Inspired by recommender models that infer user-item preferences from incomplete interaction graphs, we present CrossRec, which reformulates scATAC and scRNA data as an interaction graph to learn regulatory patterns across single-cell tasks. Its biologically-driven bipartite graph transformer learns interpretable attention over ATAC-RNA pairs. CrossRec outperforms existing methods across various tasks, remains robust under data-scarce settings, generalizes to unseen cell types and datasets, and enhances prior-based methods. Its learned regulatory maps provide cell- and cell-type-specific insights, resolving dynamic regulatory rewiring during cortical neurogenesis and perturbation-specific rewiring of drug-induced regulation in melanoma resistance.
Related
- Cis-TERN: a graph-based method to integrate single-cell chromatin accessibility with gene expression data to infer the pseudotime ordering of cells
- PATZ1 remodels the nucleosome landscape to promote chromatin accessibility in injured neurons
- Cellular, chromatin-accessibility, and spatial contextualization of bulk transcriptional patterns linked to positive peritoneal cytology in endometrial cancer
- Genetic integration reveals causal effects of chromatin accessibility on nucleosome positioning across diverse muscle cells
- Protocol for profiling chromatin accessibility in human small-cell lung cancer FFPE-derived samples using Omni-ATAC-seq
BibTeX
@article{wang2026recommendation,
title = {{Recommendation system-inspired learning of crossmodal interaction patterns between chromatin accessibility and gene expression}},
author = {Xiaotang Wang and Xuanwei Lin and Qiaoyi Zhang and Xiaochen Bo and Hao Li and Yongqi Zhang},
journal = {Nature Communications},
year = {2026},
month = oct,
doi = {10.1038/s41467-026-78646-y},
url = {https://www.nature.com/articles/s41467-026-78646-y},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Recommendation system-inspired learning of crossmodal interaction patterns between chromatin accessibility and gene expression
AU - Xiaotang Wang
AU - Xuanwei Lin
AU - Qiaoyi Zhang
AU - Xiaochen Bo
AU - Hao Li
AU - Yongqi Zhang
PY - 2026
DA - 2026/10/24
JO - Nature Communications
DO - 10.1038/s41467-026-78646-y
UR - https://www.nature.com/articles/s41467-026-78646-y
AB - Despite the growing availability of crossmodal single-cell sequencing, existing approaches are limited by underutilization of biological attributes, sparse modality signals, and insufficient modeling of regulatory interactions, limiting generalization in data-scarce settings and the discovery of peak-gene-level relationships. Interestingly, such challenges mirror those in recommendation systems, where side information, high sparsity, binary interactions, and cold start problems are extensively studied. Inspired by recommender models that infer user-item preferences from incomplete interaction graphs, we present CrossRec, which reformulates scATAC and scRNA data as an interaction graph to learn regulatory patterns across single-cell tasks. Its biologically-driven bipartite graph transformer learns interpretable attention over ATAC-RNA pairs. CrossRec outperforms existing methods across various tasks, remains robust under data-scarce settings, generalizes to unseen cell types and datasets, and enhances prior-based methods. Its learned regulatory maps provide cell- and cell-type-specific insights, resolving dynamic regulatory rewiring during cortical neurogenesis and perturbation-specific rewiring of drug-induced regulation in melanoma resistance.
SN - 2041-1723
ER -