{
  "id": 2399370,
  "title": "DeepCyte Launches Single-Cell Metabolomic Reference Atlas of Drug Toxicity Mechanisms",
  "url": "https://urgent.news/2026/08/21/deepcyte-launches-single-cell-metabolomic-reference-atlas-of-drug",
  "topic": "health",
  "section": "Health & Medicine",
  "published": "2026-08-21T15:13:54.000Z",
  "source": {
    "name": "GEN Biotechnology",
    "slug": "gen-biotechnology",
    "url": "https://www.genengnews.com/topics/drug-discovery/deepcyte-launches-single-cell-metabolomic-reference-atlas-of-drug-toxicity-mechanisms/"
  },
  "original_language": "en",
  "account": "DeepCyte has introduced the DeeTox Atlas, a single-cell metabolomic reference atlas aimed at cataloging drug toxicity mechanisms. Global pharmaceutical firms are set to commence enterprise pilot programs utilizing the Atlas in the coming months. The Atlas is built from two independent single-cell metabolomics perturbation studies, encompassing about 100 toxicant compounds, 300,000 cells, and approximately 500 metabolites per cell—totaling over 3,000 single-cell measurements for each compound across six biological replicates. Each compound is associated with a curated four-tiered hierarchy of toxicity mechanisms, linked to established Adverse Outcome Pathways (AOPs), according to DeepCyte. Rather than producing new experimental data for each compound, the company trains a foundation model that can predict toxicity mechanisms for compounds it has never measured, according to Theodore Alexandrov, DeepCyte's co-founder and CEO. The Atlas's scalability improves as it expands, reducing reliance on laboratory testing while enhancing predictive accuracy. Alexandrov explained that AI in toxicology's effectiveness is contingent upon the biological data it learns from. DeeTox Atlas enables the discovery of subtle molecular patterns associated with critical toxicity mechanisms—patterns detectable only in small cell subpopulations and often missed by methods lacking single-cell resolution—transforming them into predictive models. The Atlas will continue to grow with additional compounds, mechanisms, and biochemical and clinical data, making predictions more practical for toxicologists, medicinal chemists, and safety scientists.",
  "summary": "Rather than generating new wet-lab data for every compound, DeepCyte trains a foundation model that is capable of predicting toxicity mechanisms for compounds that it has never measured. The post DeepCyte Launches Single-Cell Metabolomic Reference Atlas of Drug Toxicity Mechanisms appeared first on GEN - Genetic Engineering and Biotechnology News .",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}