{
  "abstract": "Lipophilicity governs the uptake, distribution and toxicity of drug candidates, yet the experimental logP datasets used to build predictive models contain almost exclusively organic molecules. Here we present MetalLipoDB, a manually curated dataset of 5158 experimental logP and logD values of complexes of 23 metals from 1192 articles, including 556 entries for multinuclear and heterometallic complexes, annotated with the measurement conditions and counterions. The dataset quantifies the inter-study reproducibility of these measurements (0.56 log units) and serves as a benchmark for machine learning, with a mean absolute error of 0.72–0.75 for complexes from unseen articles. For articles with at least four measurements, anchoring the predictions to three measured complexes of the series reduced the error on the remaining complexes from 0.73 to 0.51. MetalLipoDB, the code and an interactive web application (https://biometaldb.streamlit.app/) are openly available to support the design of metal-based drugs.",
  "abstract_shown": true,
  "affiliations": [
    "N.S. Kurnakov Institute of General and Inorganic Chemistry, Russian Academy of Sciences, 119991 Leninskii pr. 31, Moscow, Russia",
    "Department of Chemistry, Lomonosov Moscow State University, Lenin’s hills 1/3, Moscow, Russia, 119991"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Lev Krasnov",
      "orcid": "0000-0003-3563-3839"
    },
    {
      "affs": [
        0
      ],
      "name": "Dmitriy Malikov",
      "orcid": "0009-0000-6966-4137"
    },
    {
      "affs": [
        0
      ],
      "name": "Marina A. Kiseleva",
      "orcid": "0000-0002-4522-0352"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Artem Lvov",
      "orcid": "0009-0001-5876-4236"
    },
    {
      "affs": [
        0
      ],
      "name": "Sergei V. Tatarin",
      "orcid": "0000-0002-1503-8189"
    },
    {
      "affs": [
        0
      ],
      "name": "Stanislav I. Bezzubov",
      "orcid": "0000-0002-2017-517X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/csecz7yd2fpwh.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010021/v1",
  "fulltext_url": null,
  "id": "csecz7yd2fpwh",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010021/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",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7220863078",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/csecz7yd2fpwh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15010021",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010021/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Beyond Organic Molecules: MetalLipoDB, a Lipophilicity Dataset for Metal Complexes and Machine Learning Benchmarks",
  "title_text": "Beyond Organic Molecules: MetalLipoDB, a Lipophilicity Dataset for Metal Complexes and Machine Learning Benchmarks",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/csecz7yd2fpwh",
  "venue": "ChemRxiv",
  "versions": []
}