{
  "abstract": "IntroductionAdverse drug reaction (ADR) prediction remains challenging because spontaneous reporting data leave many exposure unit–ADR associations unobserved and provide limited support for candidate prioritization and mechanistic interpretation.MethodsWe developed MEG-HHGN, a mechanistic evidence-guided hyperbolic heterogeneous graph neural network. It represents exposure units as combinations of standardized drug names and routes of administration and integrates spontaneous reports with compounds, drug targets, ADR-related targets, and protein–protein interactions. Using 73,530 spontaneous reports collected in Jiangsu Province from 2010 to 2023, we evaluated MEG-HHGN against eight baseline methods through five-fold cross-validation.ResultsMEG-HHGN achieved AUC/AP/MCC values of 0.9550/0.9537/0.7917 in known-exposure-unit completion and 0.9090/0.9064/0.6587 in side-information-supported exposure-unit cold-start evaluation. Global scoring of unobserved exposure unit–ADR pairs produced a ranked candidate pool for pharmacovigilance review. Representative cases involving intravenous vinorelbine tartrate–myelosuppression and oral aspirin–proteinuria illustrated PPI-bridged and shared-target pathways, respectively.DiscussionMEG-HHGN integrates route-aware prediction, candidate prioritization, and pathway-based interpretation in a unified framework to support signal triage, mechanistic hypothesis generation, and evidence review in post-marketing pharmacovigilance.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Original Research",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "Ru Lv"
    },
    {
      "name": "Xiaoyu Xu"
    },
    {
      "name": "Yulin Ji"
    },
    {
      "name": "Jianxiang Wei"
    },
    {
      "name": "Zuojian Zhou"
    },
    {
      "name": "Kankan She"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/29b929cf8ye6k.bib",
  "cited_by": 0,
  "doi": "10.3389/fphar.2026.1985523",
  "fulltext_url": null,
  "id": "29b929cf8ye6k",
  "issns": [
    "1663-9812"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fphar.2026.1985523",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "feed-journal",
      "medicine/pharmacology-toxicology"
    ]
  ],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/29b929cf8ye6k.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:20:20Z",
      "native_id": "10.3389/fphar.2026.1985523",
      "source": "feed-frontiers",
      "url": "https://www.frontiersin.org/articles/10.3389/fphar.2026.1985523"
    },
    {
      "first_seen": "2026-11-03T12:21:33Z",
      "native_id": "10.3389/fphar.2026.1985523",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fphar.2026.1985523/full"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "feed-journal:medicine/pharmacology-toxicology",
      "subfield": "pharmacology-toxicology"
    }
  ],
  "title": "Hyperbolic heterogeneous graph learning for adverse drug reaction prediction, candidate prioritization, and pathway-based interpretation in pharmacovigilance",
  "title_text": "Hyperbolic heterogeneous graph learning for adverse drug reaction prediction, candidate prioritization, and pathway-based interpretation in pharmacovigilance",
  "type": "peer-reviewed",
  "updated_at": "2026-11-05T00:21:10Z",
  "url": "https://research.draconitic.com/paper/29b929cf8ye6k",
  "venue": "Frontiers in Pharmacology",
  "versions": []
}