{
  "abstract": "Unanticipated toxicity accounts for ∼30% of clinical-phase drug failures, yet despite advances in computational toxicity prediction, predictive models typically offer scores without identifying the structural culprit. Here, we introduce an interpretable deep-learning framework that couples fingerprint-descriptor fusion with task-adaptive attention and a SHAP-guided bioisosteric ablation pipeline. Trained on 9,315 compounds spanning 14 end points (Tox21 + ClinTox) under scaffold-stratified split, the attention-fusion model achieves mean test ROC-AUC of 0.739 (Tox21) and 0.953 (ClinTox). The critical advance is a structure-guided validation protocol: predictive intervention ablation─computationally replacing toxicophores with bioisosteric equivalents─demonstrates that the model’s predictions are predictively dependent on specific substructures. Halogen → methyl substitution drops predicted toxicity from 0.659 to 0.101 (paired t = 22.66, p = 6.32 × 10–10, n = 11; Cohen’s d = 6.82), providing the primary structure-guided evidence. Cross-end point SHAP correlation reaches 0.333 (MTL) and 0.334 (STL; Welch’s p = 0.82), indicating that both paradigms extract coherent mechanistic structure above the label baseline (0.172). SMARTS-based toxicophore alignment identifies a strong positive logit differential for aniline on the clinically relevant CT_TOX end point (+0.76), and predictive-intervention ablation confirms model dependence on the identified substructures (halogen → methyl: n = 11, p < 10–9; aniline → methoxy: n = 2, directional check only). External validation on 1,427 SIDER adverse-drug-reaction compounds reveals significant toxicophore enrichment (aniline: 12.6% vs 0%, Fisher exact p = 4.5 × 10–12; halogenated aromatic: 29.8% vs 0%, p = 1.6 × 10–29), remaining significant after controlling for molecular weight and Log P. Three case studies illustrate how SHAP-guided attribution translates into actionable medicinal-chemistry mitigation strategies.",
  "abstract_shown": true,
  "affiliations": [
    "Yantai Institute of Science and Technology , , No.34 Xianjing West Road , Penglai District, , ,"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Jing Gao",
      "orcid": "0009-0004-7910-7712"
    },
    {
      "affs": [
        0
      ],
      "name": "Dong Lin"
    },
    {
      "affs": [
        0
      ],
      "name": "Jianfeng Hu",
      "orcid": "0000-0002-0669-4328"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ew8akrj65cj6a.bib",
  "cited_by": 0,
  "doi": "10.1021/acsomega.6c08546",
  "fulltext_url": null,
  "id": "ew8akrj65cj6a",
  "issns": [
    "2470-1343"
  ],
  "landing_url": "https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c08546/5465435/Quantitative-Toxicophore-Discovery-through",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://pubs.acs.org/doi/pdf/10.1021/acsomega.6c08546",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-06",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/ew8akrj65cj6a.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T12:21:00Z",
      "native_id": "10.1021/acsomega.6c08546",
      "source": "crossref",
      "url": "https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c08546/5465435/Quantitative-Toxicophore-Discovery-through"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "issn:2470-1343",
      "subfield": "general"
    }
  ],
  "title": "Quantitative Toxicophore Discovery through Interpretable Deep Learning: A Framework for Mechanism-Guided Toxicity Mitigation in Drug Safety Profiling",
  "title_text": "Quantitative Toxicophore Discovery through Interpretable Deep Learning: A Framework for Mechanism-Guided Toxicity Mitigation in Drug Safety Profiling",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T00:21:54Z",
  "url": "https://research.draconitic.com/paper/ew8akrj65cj6a",
  "venue": "ACS Omega",
  "versions": []
}