{
  "abstract": "Graph neural networks (GNNs) are among the standard tools for molecular property prediction, but the atom-level explanations of their predictions are hard for medicinal chemists to act on. We propose a change of input representation rather than a new model: molecules are encoded as fragment-level graphs from BRICS decomposition, where each node is a synthetically meaningful fragment whose features are the element-wise sum of its atoms' features. Because only the representation changes, any message-passing GNN and any post-hoc attribution method produces explanations at the resolution of functional groups instead of single atoms. Across four architectures, four prediction tasks, and two explainers under scaffold splits, fragment-level encoding matches atom-level test accuracy on roughly five-fold smaller graphs. Integrated-Gradients attributions recover known pharmacophores above chance on two enzyme targets, namely BACE at 1.5 times the chance rate, and PTR1 at 3.2 times. A like-for-like comparison against an aggregated atom-level baseline shows that post-hoc aggregation is not a stable substitute: its BACE hit rate range both exceeds and falls below the fragment model's hit rate depending on two arbitrary aggregation choices, whereas fragment-level training yields a single convention-free attribution at no predictive cost. The code is available at: https://github.com/4D-Lab/frame",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.29589",
  "author_total": 2,
  "authors": [
    {
      "name": "Rafael Lopes Almeida"
    },
    {
      "name": "Ina Pöhner"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/22vqe3pg9n2vn.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.29589",
  "fulltext_url": null,
  "id": "22vqe3pg9n2vn",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.29589",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7223214442",
  "pdf_url": "https://arxiv.org/pdf/2610.29589",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/22vqe3pg9n2vn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:29Z",
      "native_id": "2610.29589",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.29589"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction",
  "title_text": "Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:29Z",
  "url": "https://research.draconitic.com/paper/22vqe3pg9n2vn",
  "venue": "arXiv",
  "versions": []
}