{
  "abstract": "Compound identification and structure annotation from mass spectra are essential in drug detection, forensics, and small molecule discovery. Current approaches to compound identification from electron ionization mass spectra (EI-MS) are dependent on different forms of searching databases that are orders of magnitude smaller than the space of potential molecular structures they attempt to cover. We introduce SpecTUS: Spectral Translator for Unknown Structures, a deep learning model for de novo structural annotation, translating gas chromatography EI-MS spectra directly into molecular structures without requiring reference databases. This enables the identification of novel compounds absent from spectral libraries. In a rigorous evaluation, SpecTUS significantly outperformed standard database search techniques. On a held-out test set of 28,267 spectra from NIST 20, the model's single suggestion perfectly reconstructed 43% of the subset's compounds. On 76% of this test set, the single suggestion is strictly better, in terms of Tanimoto similarity of Morgan fingerprint, than the result of hybrid database search. With ten suggestions, SpecTUS achieved 65% perfect reconstructions, surpassing hybrid search on 84% of the test set.",
  "abstract_shown": true,
  "affiliations": [
    "Masaryk University , , Šumavská 525/33 , ,",
    "Technical University Munich , , Boltzmannstraße 3 , ,",
    "Masaryk University , , Kamenice 753/5 , ,",
    "Masaryk University , , Botanická 554/68a , ,"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Adam Hájek",
      "orcid": "0009-0008-3638-2959"
    },
    {
      "affs": [
        1
      ],
      "name": "Michal Starý"
    },
    {
      "affs": [
        2
      ],
      "name": "Elliott James Price",
      "orcid": "0000-0001-5691-7000"
    },
    {
      "affs": [
        3
      ],
      "name": "Filip Jozefov"
    },
    {
      "affs": [
        2
      ],
      "name": "Helge Hecht",
      "orcid": "0000-0001-6744-996X"
    },
    {
      "affs": [
        0
      ],
      "name": "Aleš Křenek",
      "orcid": "0000-0002-3395-3196"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4nd39ddmm2fz2.bib",
  "cited_by": 5,
  "doi": "10.1021/acs.analchem.6c02423",
  "fulltext_url": null,
  "id": "4nd39ddmm2fz2",
  "issns": [
    "0003-2700",
    "1520-6882"
  ],
  "landing_url": "https://doi.org/10.1021/acs.analchem.6c02423",
  "language": "en",
  "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": "W4407310549",
  "pdf_url": "https://pubs.acs.org/doi/pdf/10.1021/acs.analchem.6c02423?ref=article_openPDF",
  "pmcid": "PMC13425552",
  "pmid": "42441797",
  "published": "2026-07-13",
  "publisher": "American Chemical Society",
  "ris": "https://research.draconitic.com/paper/4nd39ddmm2fz2.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:03Z",
      "native_id": "W4407310549",
      "source": "openalex",
      "url": "https://doi.org/10.1021/acs.analchem.6c02423"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:1607|Mass Spectrometry Techniques and Applications",
      "subfield": "physical"
    }
  ],
  "title": "SpecTUS: Spectral Translator for Unknown Structures Annotation from EI-MS Spectra",
  "title_text": "SpecTUS: Spectral Translator for Unknown Structures Annotation from EI-MS Spectra",
  "type": "peer-reviewed",
  "updated_at": "2026-11-06T13:20:25Z",
  "url": "https://research.draconitic.com/paper/4nd39ddmm2fz2",
  "venue": "Analytical Chemistry",
  "versions": []
}