{
  "id": 5646756,
  "title": "New AI tool maps the hidden universe of small molecules",
  "url": "https://urgent.news/2026/09/04/new-ai-tool-maps-the-hidden-universe-of-small-molecules",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-04T21:00:01.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-09-ai-tool-hidden-universe-small.html"
  },
  "original_language": "en",
  "account": "Scientists have developed a new AI tool called AIMe, or AI Molecule Explorer, that maps the hidden universe of small molecules in the human body and gut microbiome. These tiny molecules play a crucial role in various biological functions such as immunity and metabolism. However, identifying these molecules has been a major challenge due to limited experimental reference libraries. AIMe uses neuro-symbolic AI to predict, organize, and search the masses of over 100 million known small organic molecules, creating a vast searchable map of chemical space. This tool significantly expands the searchable chemical space compared to existing experimental libraries, which cover only a fraction of known compounds. By taking a computational approach, AIMe can predict spectra and organize them into a searchable resource called MS2KOSMOS. The researchers demonstrated AIMe's capabilities by applying it to a study comparing germ-free mice to mice with a normal gut microbiota. AIMe helped identify several thousand chemical features that could not be detected using standard methods. For some unidentified compounds, AIMe provided chemically interpretable leads for further investigation, while for others, it mapped the unknown spectra to molecular neighborhoods for hypothesis generation. One of the compounds studied produced spectra resembling polyamine derivatives, a well-known class of molecules. Through AIMe's output, the team was able to identify the compound as a structurally unusual macrocyclic polyamine, which was later confirmed through synthesis. This finding suggests that the catalog of microbiota-dependent polyamines is far less complete than previously thought, highlighting the potential of AI-guided structure elucidation in advancing our understanding of the complex interactions between diet, gut microbiome, and immune function.",
  "summary": "The human body and its gut microbiome produce thousands of small molecules that shape how the body functions—influencing immunity, metabolism and more. Identifying what those molecules actually are has been one of the biomedical sciences' most persistent bottlenecks. More than 80% of compounds detected in a typical biological sample cannot be matched to any known structure using current methods.",
  "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."
}