CHACAM: a cell-cell interaction-guided hierarchical attention model for high-precision cell identity annotation of scRNA-seq data in early C. elegans embryogenesis
- 1The University of Texas at Dallas
Abstract
Accurate cell identity annotation is essential for reconstructing cell lineages and gene-regulatory networks in embryogenesis. However, in Caenorhabditis elegans (C. elegans) single-cell RNA-sequencing (scRNA-seq) atlases, closely related sub-lineage cells often have near-identical transcriptomes, leading to merged labels and limiting downstream analyses. We present CHACAM (Cell-Cell Interaction-guided Hierarchical Attention-based Cell Allocation Model), a supervised machine learning framework that integrates gene expression, a curated C. elegans ligand-receptor (L-R) interaction database, and a high-resolution cell contact map to refine cell annotations. CHACAM learns interpretable "interaction signatures" that distinguish contacting vs. non-contacting neighbors and applies a triangulation strategy using reference cells to resolve ambiguous sister identities. Applied to the Tintori and Cole-Yanai embryo atlases, CHACAM achieves near-perfect annotation accuracy, resolving longstanding ambiguities of the AB lineage and other lineages. The model also identifies new discriminative marker genes and provides mechanistic hypotheses linking contact-specific signaling to fate specification.
Related
- PeTMiner: Mining plant endogenous target mimics via ternary interaction modeling with hierarchical attention and adaptive weighted loss
- HMVA-DDI: A Hierarchical Multi-View Attention Network for Drug-Drug Interaction and Severity Prediction
- A hierarchical Bayesian model for dynamic phenotypes in multi-environment trials with genotype by environment interaction
- Classifying tumors from broad category to hierarchical molecular subtype: an interpretable hierarchical framework for precision oncology
- Nuclear speckles comprise hierarchical nanoscale interaction networks that shape molecular dynamics
BibTeX
@misc{chen2026chacam,
title = {{CHACAM: a cell-cell interaction-guided hierarchical attention model for high-precision cell identity annotation of scRNA-seq data in early C. elegans embryogenesis}},
author = {X. Chen and X. Ju and M. Murali and H. Li and M. Chen and M. Q. Zhang},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.754260},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.754260v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - CHACAM: a cell-cell interaction-guided hierarchical attention model for high-precision cell identity annotation of scRNA-seq data in early C. elegans embryogenesis
AU - X. Chen
AU - X. Ju
AU - M. Murali
AU - H. Li
AU - M. Chen
AU - M. Q. Zhang
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.754260
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.754260v1
AB - Accurate cell identity annotation is essential for reconstructing cell lineages and gene-regulatory networks in embryogenesis. However, in Caenorhabditis elegans (C. elegans) single-cell RNA-sequencing (scRNA-seq) atlases, closely related sub-lineage cells often have near-identical transcriptomes, leading to merged labels and limiting downstream analyses. We present CHACAM (Cell-Cell Interaction-guided Hierarchical Attention-based Cell Allocation Model), a supervised machine learning framework that integrates gene expression, a curated C. elegans ligand-receptor (L-R) interaction database, and a high-resolution cell contact map to refine cell annotations. CHACAM learns interpretable "interaction signatures" that distinguish contacting vs. non-contacting neighbors and applies a triangulation strategy using reference cells to resolve ambiguous sister identities. Applied to the Tintori and Cole-Yanai embryo atlases, CHACAM achieves near-perfect annotation accuracy, resolving longstanding ambiguities of the AB lineage and other lineages. The model also identifies new discriminative marker genes and provides mechanistic hypotheses linking contact-specific signaling to fate specification.
ER -