{
  "abstract": "Protein language models (pLMs) learn rich sequence semantics from vast volume of protein sequences, yet the information encoded in their high-dimensional embeddings remains largely a black box, posing an interpretability challenge. Here we show that semantic features learned by pLMs can be decoded to reveal biologically meaningful signals using coevolutionary analysis without downstream supervised-training. Building on this insight, we developed MaskNGly, a zero-shot framework that identifies protein N-glycosylation sites directly from PLM-embeddings while achieving performance comparable to state-of-the-art supervised predictors. MaskNGly is computationally efficient and intrinsically transferable, enabling omics-scale characterization of protein glycosylation landscape. Applied across proteomes, it reveals that canonical N-X-S/T motifs gain higher glycosylation propensities with increasing organismal complexity and that glycosylation preferentially occurs at structured, solvent-exposed regions. Mutations altering high-scoring motifs are more frequently disease-associated. The framework also captures signatures of glycosylation-mediated protein allostery. These results establish an interpretable and scalable route to study glycobiology from pLM-embeddings.",
  "abstract_shown": true,
  "affiliations": [
    "Nanjing University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "name": "X. Zhou"
    },
    {
      "name": "X. Guan"
    },
    {
      "name": "Y. Zhou"
    },
    {
      "name": "J. Wang"
    },
    {
      "name": "Z. Peng"
    },
    {
      "name": "W. Ren"
    },
    {
      "name": "W. Wang"
    },
    {
      "name": "R. Xie"
    },
    {
      "affs": [
        0
      ],
      "name": "W. Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b03skqtsya5ex.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.02.763593",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.02.763593v1.full",
  "id": "b03skqtsya5ex",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.02.763593v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.11.02.763593v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b03skqtsya5ex.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T00:21:58Z",
      "native_id": "10.64898/2026.11.02.763593",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.02.763593v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Omics-scale decoding of protein N-glycosylation using protein language model embeddings",
  "title_text": "Omics-scale decoding of protein N-glycosylation using protein language model embeddings",
  "type": "preprint",
  "updated_at": "2026-11-06T00:21:42Z",
  "url": "https://research.draconitic.com/paper/b03skqtsya5ex",
  "venue": "bioRxiv",
  "versions": []
}