{
  "abstract": "Self-supervised learning (SSL) enables scalable, label-free foundation models (FMs) that learn task-agnostic representations directly from images, bypassing cell segmentation and feature engineering inherent to classical morphological profiling. We present a large-scale evaluation of SSL FMs for image-based phenotypic profiling, covering contrastive (DINO), masked-based generative (MAE, iTPN) and hybrid (DINOv2) learning mechanisms, pretrained on all unannotated chemical perturbations from the Joint Undertaking for Morphological Profiling–Cell Painting (JUMP–CP) dataset (119,876 compounds, ~1.77 million images, 7 laboratories). Here we show that top-performing SSL models outperformed CellProfiler in compound-replicate retrieval on the held-out JUMP–Target2 set (302 annotated compounds, P ≤ 0.001). DINO and DINOv2 generalized across diverse perturbations and cell types, outperforming CellProfiler with 31–37% gains in site-averaged mean average precision for mechanism-of-action retrieval on EU-OPENSCREEN Bioactives (2,464 compounds), and consistently surpassing masked-based models across all benchmarks. This study provides a systematic assessment of SSL approaches for advancing morphological profiling and offers pretrained FMs to accelerate drug discovery.",
  "abstract_shown": true,
  "affiliations": [
    "Data Science and AI, Johnson & Johnson, Cambridge, MA USA",
    "Data Science and AI, Johnson & Johnson, Zug, Switzerland",
    "Discovery Technologies and Molecular Pharmacology, Johnson & Johnson, Beerse, Belgium",
    "Cognitive Automation and Technology, Johnson & Johnson, Beerse, Belgium",
    "Discovery Technologies and Molecular Pharmacology, Johnson & Johnson, Spring House, PA USA",
    "Data Science and AI, Johnson & Johnson, Titusville, NJ USA"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Walid M. Abdelmoula",
      "orcid": "0000-0003-3117-7389"
    },
    {
      "affs": [
        1
      ],
      "name": "Tomé Albuquerque",
      "orcid": "0000-0003-3246-7206"
    },
    {
      "affs": [
        2
      ],
      "name": "Steffen Jaensch"
    },
    {
      "affs": [
        1
      ],
      "name": "Pushpak Pati"
    },
    {
      "affs": [
        3
      ],
      "name": "Michiel Van Dyck",
      "orcid": "0000-0002-9097-7581"
    },
    {
      "affs": [
        4
      ],
      "name": "Samantha J. Allen"
    },
    {
      "affs": [
        4
      ],
      "name": "Litao Zhang"
    },
    {
      "affs": [
        5
      ],
      "name": "Tommaso Mansi"
    },
    {
      "affs": [
        5
      ],
      "name": "Rui Liao",
      "orcid": "0009-0006-7778-727X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2nafsbw9tzb64.bib",
  "cited_by": 0,
  "doi": "10.1038/s41592-026-03270-z",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13736651/",
  "id": "2nafsbw9tzb64",
  "issns": [
    "1548-7091",
    "1548-7105"
  ],
  "landing_url": "https://doi.org/10.1038/s41592-026-03270-z",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Article"
    ],
    [
      "openalex",
      "1304|Cell Image Analysis Techniques"
    ]
  ],
  "openalex": "W7224307277",
  "pdf_url": "https://www.nature.com/articles/s41592-026-03270-z.pdf",
  "pmcid": "PMC13736651",
  "pmid": "42957788",
  "published": "2026-10-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2nafsbw9tzb64.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T12:22:03Z",
      "native_id": "PMC13736651",
      "source": "pmc",
      "url": "https://doi.org/10.1038/s41592-026-03270-z"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1304|Cell Image Analysis Techniques",
      "subfield": "biophysics"
    }
  ],
  "title": "Advancing morphological profiling with self-supervised learning through comparative insights into representation learning of cellular perturbations",
  "title_text": "Advancing morphological profiling with self-supervised learning through comparative insights into representation learning of cellular perturbations",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T12:22:03Z",
  "url": "https://research.draconitic.com/paper/2nafsbw9tzb64",
  "venue": "Nature Methods",
  "versions": []
}