{
  "abstract": "Chemical datasets used in computational chemistry are often distributed across separate repositories, stored in dataset-specific formats, and accompanied by heterogeneous metadata, property definitions, and structure representations. This fragmentation increases the manual preprocessing required to reuse datasets for molecular property prediction, reaction modeling, benchmarking, and machine-learning workflows. Here, we present LCMD-db, a chemical data hosting and analysis platform for organizing molecular, fragment, and reaction datasets within a common framework. LCMD-db represents data as datasets and self-consistent subsets, with explicit metadata, property definitions, structure mappings, and standardized ingestion pipelines. The platform supports molecular structures, fragments, equilibrium geometries, transition states, reaction participants, and computed properties linked to SMILES strings, molecular graphs, and three-dimensional structure files. For reaction datasets, LCMD-db stores molecular participants together with their chemical roles and reaction-coordinate relationships, allowing intermediates, transition states, reactants, products, catalysts, and other species to be treated as connected chemical entities rather than isolated files. The platform provides interactive visualization, property inspection, filtering, export of selected entries, and Python-native access to structured molecular and reaction objects. We demonstrate LCMD-db using in-house and external datasets spanning small organic molecules, transition-metal complexes, molecular fragments, and reaction datasets with thermodynamic or kinetic annotations. LCMD-db connects data hosting with analysis and modeling workflows by providing structured, searchable, and directly loadable chemical datasets.",
  "abstract_shown": true,
  "affiliations": [
    "Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering",
    "École Polytechnique Fédérale de Lausanne (EPFL)",
    "National Centre for Computational Design and Discovery of Novel Materials (MARVEL)",
    "National Centre for Competence in Research-Catalysis (NCCR-Catalysis)"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Romain Graux"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Juliette Veronique Schleicher",
      "orcid": "0000-0001-9553-4491"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Thanapat Worakul",
      "orcid": "0000-0002-8031-1727"
    },
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Yannick Calvino Alonso",
      "orcid": "0009-0008-9573-7772"
    },
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Clémence Corminboeuf",
      "orcid": "0000-0001-7993-2879"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3apyesnbscrm8.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008334/v1",
  "fulltext_url": null,
  "id": "3apyesnbscrm8",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008334/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",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7208724206",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008334/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-04",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/3apyesnbscrm8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008334",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008334/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "LCMD[db]: The Unified Chemical Data Hosting and Analysis Platform",
  "title_text": "LCMD[db]: The Unified Chemical Data Hosting and Analysis Platform",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/3apyesnbscrm8",
  "venue": "ChemRxiv",
  "versions": []
}