{
  "abstract": "Accurate prediction of drug solubility in supercritical CO₂ remains challenging due to the limited generalizability of compound-specific correlations and the black-box nature of most machine learning models. This study proposes a domain-aware symbolic regression framework that discovers closed-form analytical expressions for ln(y), enabling interpretable and transferable solubility modeling across chemically diverse pharmaceutical compounds. A leave-one-drug-out (LODO) validation strategy is employed to rigorously assess extrapolation performance on unseen drug domains across a curated dataset of 196 experimental data points spanning 9 antihypertensive compounds. Under this evaluation, the domain-adversarial neural network (DANN) component of the proposed framework achieved RMSE = 0.33 ± 0.08, MAE = 0.24 ± 0.06, and R² = 0.89 ± 0.05, outperforming standard machine learning baselines including Random Forest, XGBoost, and Multi-Layer Perceptron in cross-domain generalization. The symbolic regression component additionally recovered compact closed-form analytical expressions that accurately represent the full experimental dataset (in-sample expression fit: R² = 0.962, RMSE = 0.031, MAE = 0.024) while remaining physically interpretable and analytically tractable. The combined framework demonstrates that domain-aware learning and symbolic discovery can jointly address the dual challenge of predictive robustness under domain shift and model interpretability in supercritical pharmaceutical solubility modeling.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Pharmaceutics and Industrial Pharmacy, College of Pharmacy, Taif University",
    "Institute of Research and Development, Duy Tan University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Sameer Alshehri"
    },
    {
      "affs": [
        1
      ],
      "name": "Mahboubeh Pishnamazi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0y7t9fqmk9hfv.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-62721-x",
  "fulltext_url": "https://doi.org/10.1038/s41598-026-62721-x",
  "id": "0y7t9fqmk9hfv",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://doi.org/10.1038/s41598-026-62721-x",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "Q"
    ],
    [
      "lcc",
      "R"
    ],
    [
      "openalex",
      "2204|Phase Equilibria and Thermodynamics"
    ]
  ],
  "openalex": "W7169723977",
  "pdf_url": "https://www.nature.com/articles/s41598-026-62721-x.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-01",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/0y7t9fqmk9hfv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:45:52Z",
      "native_id": "0c3a0c4a993c4496bd9fe46d450853cf",
      "source": "doaj",
      "url": "https://doi.org/10.1038/s41598-026-62721-x"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R",
      "subfield": "general"
    }
  ],
  "title": "Symbolic and domain-generalized machine learning for interpretable solubility modeling in supercritical CO₂",
  "title_text": "Symbolic and domain-generalized machine learning for interpretable solubility modeling in supercritical CO₂",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T14:20:43Z",
  "url": "https://research.draconitic.com/paper/0y7t9fqmk9hfv",
  "venue": "Scientific Reports",
  "versions": []
}