{
  "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.",
  "abstract_shown": true,
  "affiliations": [
    "The University of Texas at Dallas"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "X. Chen"
    },
    {
      "name": "X. Ju"
    },
    {
      "name": "M. Murali"
    },
    {
      "name": "H. Li"
    },
    {
      "name": "M. Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "M. Q. Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0jc2zz7yygtc2.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.24.754260",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754260v1.full",
  "id": "0jc2zz7yygtc2",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754260v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7215126305",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754260v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0jc2zz7yygtc2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:31Z",
      "native_id": "10.64898/2026.09.24.754260",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754260v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "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",
  "title_text": "CHACAM: a cell-cell interaction-guided hierarchical attention model for high-precision cell identity annotation of scRNA-seq data in early C. elegans embryogenesis",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:31Z",
  "url": "https://research.draconitic.com/paper/0jc2zz7yygtc2",
  "venue": "bioRxiv",
  "versions": []
}