{
  "abstract": "Electron ionization mass spectrometry (EI-MS) is a sensitive, reproducible analytical technique, yet compound identification conventionally relies on reference databases that capture only a fraction of accessible chemical space. In silico prediction of EI-MS spectra can extend these libraries, but existing data-driven models generalize poorly beyond their training distribution, and physics-based simulations are too costly for library-scale use. Here, we present a fragment-grounded neural workflow that predicts an EI-MS spectrum by exhaustively enumerating the fragmentation graph of a molecule and then assigning intensities to the resulting substructures. By relating every predicted peak back to a candidate substructure, our model generalizes more reliably to unseen scaffolds and out-of-distribution chemistry than prior fingerprint-and black-box transformer-based predictors. On a scaffold split, it improves top-1 retrieval accuracy from formula-matched compounds by 32% relative to the strongest baseline, and it matches the accuracy of quantum-chemical simulation while being roughly seven orders of magnitude faster. To test the model’s capabilities under a harder, formula-agnostic setting, we further evaluate retrieval against a library of 87.3 million compounds from",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "Magdalena Lederbauer",
      "orcid": "0009-0008-0665-1839"
    },
    {
      "name": "Runzhong Wang"
    },
    {
      "name": "Connor W. Coley"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/40g7hvkth91sa.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008135/v1",
  "fulltext_url": null,
  "id": "40g7hvkth91sa",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008135/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1607|Mass Spectrometry Techniques and Applications"
    ]
  ],
  "openalex": "W7204924000",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008135/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/40g7hvkth91sa.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008135",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008135/v3"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:1607|Mass Spectrometry Techniques and Applications",
      "subfield": "physical"
    }
  ],
  "title": "Fragment-Grounded Neural Simulation of Electron Ionization Mass Spectra at Library Scale",
  "title_text": "Fragment-Grounded Neural Simulation of Electron Ionization Mass Spectra at Library Scale",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:26Z",
  "url": "https://research.draconitic.com/paper/40g7hvkth91sa",
  "venue": "ChemRxiv",
  "versions": []
}