{
  "id": "2020-02-halicin",
  "title": "Halicin: deep learning identifies an antibiotic",
  "summary": "A model trained on about 2,500 molecules screened the roughly 6,000 compounds in the Broad Institute’s Drug Repurposing Hub and identified halicin, which killed many resistant bacteria in the lab and cleared A. baumannii infections in mice within 24 hours. Cell-culture and mouse results, not human studies; the mechanism remains preliminary.",
  "field": "medicine",
  "ai_technology": "Graph neural network for predicting antibacterial activity",
  "organization": "MIT",
  "source_url": "https://news.mit.edu/2020/artificial-intelligence-identifies-new-antibiotic-0220",
  "source_type": "press release",
  "publication_date": "2020-02-20",
  "added_date": "2026-11-11",
  "verification_status": "verified",
  "paper_url": "https://doi.org/10.1016/j.cell.2020.01.021",
  "relevance": {
    "impact": 4,
    "validation": 3,
    "novelty": 5
  },
  "evidence": {
    "publication_status": "Peer-reviewed paper",
    "tested": "Bactericidal activity against a wide range of pathogens, including M. tuberculosis and carbapenem-resistant Enterobacteriaceae; halicin treated C. difficile and pan-resistant A. baumannii infections in mice. Of 23 tested predictions from over 107 million ZINC15 molecules, eight were antibacterial.",
    "unknown": "Human safety and efficacy are not reported in the abstract.",
    "ai_role": "A deep neural network predicted antibacterial activity across chemical libraries; candidates were then tested experimentally.",
    "evidence_urls": [
      "https://doi.org/10.1016/j.cell.2020.01.021"
    ],
    "test_type": "direct test"
  },
  "source_review": {
    "date": "2026-11-16",
    "scope": "Original institutional announcement checked for the specific results, AI contribution and limitations cited in the antibiotic dossier or mathematical follow-up pilot. Full-paper reanalysis, external replication and an exhaustive follow-up search were not performed."
  },
  "follow_up": [
    {
      "id": "abaucin-program-extension",
      "kind": "same-team extension",
      "date": "2023-05-25",
      "date_precision": "day",
      "note": "MIT describes abaucin as a subsequent application of the antibiotic-screening program to A. baumannii. This is a different candidate and target-specific study, not replication of halicin.",
      "source_urls": [
        "https://news.mit.edu/2023/using-ai-scientists-combat-drug-resistant-infections-0525"
      ],
      "recorded_date": "2026-11-16"
    },
    {
      "id": "generative-design-program-extension",
      "kind": "same-team extension",
      "date": "2025-08-14",
      "date_precision": "day",
      "note": "MIT identifies halicin and abaucin as earlier screening results motivating generative design of new NG1/DN1 candidates. The later study does not establish clinical efficacy of these earlier candidates.",
      "source_urls": [
        "https://news.mit.edu/2025/using-generative-ai-researchers-design-compounds-kill-drug-resistant-bacteria-0814"
      ],
      "recorded_date": "2026-11-16"
    }
  ],
  "follow_up_review": {
    "date": "2026-11-16",
    "scope": "Bounded check of the original announcements cited by the events recorded here, including explicit links to later program work. This is not an exhaustive literature search or ongoing monitoring commitment."
  }
}
