{
  "abstract": "Chemical identifiers serve as essential links between molecular structures, experimental measurements, biological activities, and regulatory information. Discrepancies can arise when independently curated databases assign different identifiers to the same substance, often due to curation inconsistencies or intentional differences in representing salts, solvates, protonation states, and stereochemistry. Here, we introduce ChemConnect, a provenanceaware graph framework designed to integrate chemical identifiers from NORMAN SusDat, EPA CompTox Chemicals Dashboard, and PubChem without resolving them to a single canonical chemical entity. The ChemConnect graph contains ∼8.5 million chemical identifier nodes and ∼7.5 million connections, of which ∼ 65 thousand are derived structural-parent and stereochemical relationships whose agreement with external references is systematically quantified. ChemConnect preserves the information supplied by each source and stores the derived relationships separately, so that users can see how each relationship was obtained. This allows users to compare sources, identify records whose identifiers contradict each other, and connect related records, such as a salt and its neutral form, that have no identifier in common.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computational Biology and Chemistry, Helmholtz Centre for Environmental Research - UFZ, Permoserstr. 15, Leipzig, Germany, 04318",
    "Department of Exposure Science, Helmholtz Centre for Environmental Research - UFZ, Permoserstr. 15, Leipzig, 04318",
    "Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, 6 Avenue du Swing, Belvaux, Luxembourg, 4367",
    "Department of Computer Science, Faculty of Mathematics and Computer Science",
    "Leipzig University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "İlhan Mutlu"
    },
    {
      "affs": [
        1
      ],
      "name": "Martin Krauss"
    },
    {
      "affs": [
        2
      ],
      "name": "Emma L. Schymanski"
    },
    {
      "affs": [
        0,
        3,
        4
      ],
      "name": "Jana Schor"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ca69wdc7j75ps.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010940/v1",
  "fulltext_url": null,
  "id": "ca69wdc7j75ps",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010940/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",
      "1702|Semantic Web and Ontologies"
    ]
  ],
  "openalex": "W7223300059",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010940/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-23",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/ca69wdc7j75ps.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:26Z",
      "native_id": "10.26434/chemrxiv.15010940",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010940/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "ChemConnect: Making chemical identifier relationships and disagreements explicit and actionable",
  "title_text": "ChemConnect: Making chemical identifier relationships and disagreements explicit and actionable",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:26Z",
  "url": "https://research.draconitic.com/paper/ca69wdc7j75ps",
  "venue": "ChemRxiv",
  "versions": []
}