{
  "id": 6945442,
  "title": "AI virtual cell uses protein dynamics to predict personalized breast cancer treatments",
  "url": "https://urgent.news/2026/09/12/ai-virtual-cell-uses-protein-dynamics-to-predict-personalized-breast",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-12T15:20:01.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-09-ai-virtual-cell-protein-dynamics.html"
  },
  "original_language": "en",
  "account": "In a study published in Nature, an AI tool called ProteinTalks has been developed to predict how breast cancer cells will respond to various drugs. Unlike existing AI models that focus on gene activity, ProteinTalks analyzes proteins and their levels over time. This approach allows the tool to simulate the complex, nonlinear changes that occur within a cell after drug treatment.\n\nResearchers collected data from over 38 million protein measurements, measuring the response of breast cancer cells to 63 FDA-approved anticancer drugs and 59 two-drug combinations. They tracked protein levels before treatment, as well as at 6, 24, and 48 hours after treatment. This time-resolved dataset helped ProteinTalks learn how protein levels shift as drugs take effect.\n\nThe AI model outperformed existing methods in predicting how cancer cells respond to drugs, accurately predicting responses to 81 unseen anticancer compounds during training. It also revealed four drug pairs that showed a stronger effect together than either drug alone against triple-negative breast cancer, an aggressive form of the disease.\n\nBy analyzing protein signatures in 501 triple-negative breast cancer tumors, ProteinTalks was able to group patients based on their treatment plans, considering the risk of recurrence and long-term survival outcomes. The tool also identified personalized drug candidates that could kill tumor cells at lower doses than standard chemotherapy.\n\nProteinTalks could revolutionize cancer treatment by providing interpretable AI models that predict drug responses based on dynamic changes in cells over time. This could help researchers identify promising treatments before conducting expensive lab trials and guide personalized treatment plans based on a patient's unique tumor protein profile.",
  "summary": "Not all cancer cells are the same, and neither are their responses to drugs. Finding the right drug for the right cancer cell is a long battle in drug development and in designing effective treatments. A new AI tool called ProteinTalks makes this task easier by accurately predicting whether a drug will be effective against a cancer cell line, finding new drug combinations and identifying proteins…",
  "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."
}