{
  "abstract": "Molecular formula assignment is the first step of metabolite identification from tandem mass spectra, yet deep-learning methods have repeatedly underperformed classical enumeration, reaching usable accuracy only through candidate generation and learned reranking. Here we present MStoic, a mass spectrum encoder that predicts molecular formulas directly and finalizes them with a deterministic, zero-parameter stoichiometric correction that selects a mass-consistent formula against the precursor mass (20 ppm; falling back to the closest-mass candidate when none qualifies). Every peak is embedded by soft Gaussian binning of log(m/z), Fourier features, pairwise-difference embeddings and an intensity embedding, and the encoder is trained with chemically grounded auxiliary tasks, including fragment-level supervision from computational fragmentation trees. On the multi-source Spectraverse benchmark (48,622 held-out spectra) MStoic achieves 77.8% top-1 exact-match accuracy, and 79.6% on the CASMI-2022 challenge, matching or exceeding specialized deep-learning, candidate-ranking, and rule-based baselines on every benchmark evaluated. Applying the same correction to a competing model shows that mass-based correction is a portable physical prior that amplifies rather than substitutes model capability. Factorial ablation shows that the hybrid encoding is selectively beneficial for rare-element-bearing formulas with information-dense spectra. And imposing mass conservation as a soft training loss reduces direct accuracy more than seven-fold, indicating that physical constraints in discrete chemical spaces belong in hard post-processing rather than in the training objective.",
  "abstract_shown": true,
  "affiliations": [
    "MoloGPI",
    "Dalian Customs District Technology Center",
    "Dongbei University of Finance and Economics"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Shang Zhang",
      "orcid": "0009-0000-8177-2886"
    },
    {
      "affs": [
        1
      ],
      "name": "Zhenlin Dong"
    },
    {
      "affs": [
        2
      ],
      "name": "Ming Gao",
      "orcid": "0000-0002-8502-1155"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2tven6ha023hv.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15011102/v1",
  "fulltext_url": null,
  "id": "2tven6ha023hv",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011102/v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Metabolomics and Mass Spectrometry Studies"
    ]
  ],
  "openalex": "W7224021174",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011102/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-27",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/2tven6ha023hv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:26Z",
      "native_id": "10.26434/chemrxiv.15011102",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011102/v1"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Metabolomics and Mass Spectrometry Studies",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Direct molecular formula prediction from tandem mass spectra with a multi-task-trained encoder and deterministic stoichiometric correction",
  "title_text": "Direct molecular formula prediction from tandem mass spectra with a multi-task-trained encoder and deterministic stoichiometric correction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:26Z",
  "url": "https://research.draconitic.com/paper/2tven6ha023hv",
  "venue": "ChemRxiv",
  "versions": []
}