{
  "abstract": "Electrostatic embedding allows a local machine-learning potential to respond to an extended molecular environment without including every environmental atom in its message-passing graph. We construct a fixed-charge machine-learning/molecular-mechanics (ML/MM) interface for the pretrained MACE-POLAR-1-M model. Analytic Gaussian monopole and dipole operators supply the environmental potential, the internal electrostatic features, and the interaction energy. Differentiation through both field-conditioned density updates gives forces on the model fragment and the environment, which are combined with a subtractive classical energy and exact link-atom force redistribution. A reciprocal-space extension treats three-dimensional periodicity at fixed cell. We assess the implementation using fixed-geometry numerical checks and 24 matched QM/MM reference calculations for a 2589-atom rhodopsin model, with 54 atoms in the neural-network graph. The analytic model gives a relative-energy root-mean-square error of 8.62 kJ mol−1 after one constant energy shift, and force-component errors of 0.07345 and 0.00797 eV Å−1 on the 53 real high-level atoms and 2536 environmental atoms, respectively. Analytic operators substantially reduce rotational errors while leaving the QM/MM accuracy essentially unchanged. A nearby water accounts for approximately 74% of the environmental squared force error. Matched charge-density and frozen-density force comparisons identify limitations of both the local multipole representation and its predicted coefficients. The results establish the numerical consistency of the embedding implementation and delimit the single-point accuracy of the transferred pretrained model.",
  "abstract_shown": true,
  "affiliations": [
    "Independent Researcher"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Jianxin Cheng",
      "orcid": "0009-0004-1065-2392"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2cvwab5smyymc.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15011059/v1",
  "fulltext_url": null,
  "id": "2cvwab5smyymc",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011059/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": "W7223677371",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011059/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/2cvwab5smyymc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:26Z",
      "native_id": "10.26434/chemrxiv.15011059",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011059/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "ML/MM",
  "title_text": "ML/MM",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:26Z",
  "url": "https://research.draconitic.com/paper/2cvwab5smyymc",
  "venue": "ChemRxiv",
  "versions": []
}