{
  "abstract": "Gene embeddings are vector representations of gene identity that provide machine-learning models with information from diverse biological sources. However, their use is hindered by a lack of standardization: inconsistent identifiers, formats, and preprocessing conventions. In this work, we present a unified resource of 67 human gene-embedding sets derived from protein, DNA and RNA sequences, biomedical text, bulk expression data, single-cell expression models, functional data, biological networks, knowledge graphs, regulatory genomics and multimodal models, covering up to 20,097 GENCODE-annotated protein-coding genes. The collection includes both published precomputed embeddings and representations generated or extracted from publicly available models and biological data. Each embedding set is organized in a folder containing the embedding matrix, the Ensembl gene identifiers, machine-readable metadata, and processing documentation. We validate the resource by measuring global and local similarity, cross-embedding consensus, and cross-embedding predictability. The collection is designed to allow community-contributed embeddings that meet predefined technical and documentation requirements, enables comparison of gene representations across modalities and provides standardized embeddings for training and downstream applications.",
  "abstract_shown": true,
  "affiliations": [
    "ETH Zurich"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "D. Tabares"
    },
    {
      "name": "M. Bohl"
    },
    {
      "affs": [
        0
      ],
      "name": "V. Boeva"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6dagfaap5kg4d.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.29.762818",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.29.762818v1.full",
  "id": "6dagfaap5kg4d",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.29.762818v1",
  "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",
      "genomics"
    ],
    [
      "openalex",
      "1312|Bioinformatics and Genomic Networks"
    ]
  ],
  "openalex": "W7225064121",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.29.762818v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6dagfaap5kg4d.ris",
  "sources": [
    {
      "first_seen": "2026-11-02T12:20:48Z",
      "native_id": "10.64898/2026.10.29.762818",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.29.762818v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:genomics",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "Gene Embedding Hub: a standardized resource for human gene representations",
  "title_text": "Gene Embedding Hub: a standardized resource for human gene representations",
  "type": "preprint",
  "updated_at": "2026-11-03T00:20:25Z",
  "url": "https://research.draconitic.com/paper/6dagfaap5kg4d",
  "venue": "bioRxiv",
  "versions": []
}