{
  "abstract": "We introduce a general framework for predicting solution-phase quantum-mechanical (QM) properties of drug-like molecules directly from gas-phase geometries, without solvent-specific structural optimization or property calculations. Using current equivariant neural network (ENN) architectures, such as MACE and Allegro, we demonstrate that they can also predict extensive and intensive QM properties in implicit water at a high level of theory. Direct-and ∆-learning strategies are employed for this prediction task using the Aquamarine dataset, which provides QM properties for the same molecules in both environments. The developed models are systematically evaluated for scalability to larger molecules, transferability across chemical space, and generalization to out-of-equilibrium configurations. Our results show that, despite substantial differences between gas-and solution-phase conformational ensembles, the models can accurately reconstruct ensemble-averaged solution-phase properties from gas-phase molecular dynamics. We further integrate the learned QM properties into the QUEDsol framework (“QUantum Electronic Descriptors in SOLution”) as electronic descriptors for hydration free-energy prediction. A simple and interpretable quadratic regression model trained on the FreeSolv dataset achieves state-of-the-art performance on the challenging and chemically diverse FlexiSol benchmark, outperforming previously reported QM-and ML-based approaches. These results establish ENNs as a versatile approach for inter-phase molecular property prediction and demonstrate that environment-specific QM descriptors generated from gas-phase geometries can provide transferable inputs for complex thermodynamic modeling.",
  "abstract_shown": true,
  "affiliations": [
    "Molecular AI, Discovery Sciences",
    "R&D, AstraZeneca",
    "Department of Physics and Materials Science",
    "University of Luxembourg",
    "Computational Chemistry, Janssen R&D, C/ Jarama 75A, Toledo, Spain, 45007",
    "Drug Discovery Data Sciences, Janssen Pharmaceutica NV, Turnhoutseweg 30, Beerse, Belgium, 2340",
    "Department of Computer Science and Engineering",
    "Chalmers University of Technology and University of Gothenburg",
    "Institute for Materials Science and Max Bergmann Center of Biomaterials",
    "TUD Dresden University of Technology",
    "Center for Advanced Systems Understanding (CASUS), Conrad-Schiedt-Straße 20, Görlitz, Germany, 02826",
    "Helmholtz Zentrum Dresden-Rossendorf (HZDR), Bautzner Landstraße 400, Dresden, Germany, 01328"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Mathias Hilfiker",
      "orcid": "0009-0008-9401-3262"
    },
    {
      "affs": [
        4
      ],
      "name": "Lorenzo D’Amore",
      "orcid": "0000-0003-2245-1956"
    },
    {
      "affs": [
        5
      ],
      "name": "Dries Van Rompaey",
      "orcid": "0000-0003-0823-8235"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Marco Klähn",
      "orcid": "0000-0002-9369-4819"
    },
    {
      "affs": [
        0,
        1,
        6,
        7
      ],
      "name": "Ola Engkvist",
      "orcid": "0000-0003-4970-6461"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Alexandre Tkatchenko",
      "orcid": "0000-0002-1012-4854"
    },
    {
      "affs": [
        8,
        9,
        10,
        11
      ],
      "name": "Leonardo Medrano Sandonas",
      "orcid": "0000-0002-7673-3142"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/47jsb8q0y49bh.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010245/v1",
  "fulltext_url": null,
  "id": "47jsb8q0y49bh",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010245/v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "3107|Advanced Chemical Physics Studies"
    ]
  ],
  "openalex": "W7221562602",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010245/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-11",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/47jsb8q0y49bh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15010245",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010245/v1"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "openalex:3107|Advanced Chemical Physics Studies",
      "subfield": "amo"
    }
  ],
  "title": "From Vacuum Geometry to Solution-Phase Electronic Properties and Thermodynamics via Equivariant Neural Networks",
  "title_text": "From Vacuum Geometry to Solution-Phase Electronic Properties and Thermodynamics via Equivariant Neural Networks",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/47jsb8q0y49bh",
  "venue": "ChemRxiv",
  "versions": []
}