Scholarlink

<p>Whether graph neural network (GNN) attributions capture the reactive chemistry encoded in adverse outcome pathway (AOP) annotations for skin sensitization has not been tested under a label-permutation control. We trained AttentiveFP on a 436-molecule LLNA-labeled subset (81 sensitizers) of a curated skin-sensitization dataset and extracted atom-level attributions from seven methods (integrated gradients, GradCAM, attention, GNNExplainer, PGExplainer, GraphMask, and a rank-aggregated ensemble); GCN and GIN were retrained as architecture controls. Attributions were evaluated against 50 sensitization-specific SMARTS-based reactive-center annotations spanning six molecular initiating event (MIE) mechanism classes. The LLNA-trained model reached test AUC 0.73, compared with AUC 0.49 for a shuffled-label retraining control. Across all seven attribution methods, paired real-vs-shuffled atom-AUC differences crossed zero, indicating that most apparent attribution–mechanism correlation reflects structural priors of the attribution methods rather than learned sensitization chemistry. Mechanism-class stratification surfaced one candidate exception—pre-hapten autoxidation chemistry, with a <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(\Delta = +0.26\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mi mathvariant="normal">Δ</mi><mo>=</mo><mo>+</mo><mn>0.26</mn></mrow></math></EquationSource></InlineEquation> atom-AUC gap and non-overlapping confidence intervals—on a stratum of approximately two unique molecules, reported as a hypothesis pending replication on dedicated pre-hapten benchmarks. Per-element residual analysis converges on the same interpretation: alignment for gradient- and attention-based methods drops to chance once elemental identity is regressed out. <b>Scientific contribution</b> This work pairs a reproducible evaluation framework (50 skin-sensitization-specific SMARTS patterns scored against atom-level GNN attributions) with a label-permutation negative control that separates learned chemistry from structural priors of the attribution method.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Systematic validation of graph neural network explanations against adverse outcome pathway reactive centers for skin sensitization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月20日

查看全文
  • ByoungJun Jeon

摘要

Whether graph neural network (GNN) attributions capture the reactive chemistry encoded in adverse outcome pathway (AOP) annotations for skin sensitization has not been tested under a label-permutation control. We trained AttentiveFP on a 436-molecule LLNA-labeled subset (81 sensitizers) of a curated skin-sensitization dataset and extracted atom-level attributions from seven methods (integrated gradients, GradCAM, attention, GNNExplainer, PGExplainer, GraphMask, and a rank-aggregated ensemble); GCN and GIN were retrained as architecture controls. Attributions were evaluated against 50 sensitization-specific SMARTS-based reactive-center annotations spanning six molecular initiating event (MIE) mechanism classes. The LLNA-trained model reached test AUC 0.73, compared with AUC 0.49 for a shuffled-label retraining control. Across all seven attribution methods, paired real-vs-shuffled atom-AUC differences crossed zero, indicating that most apparent attribution–mechanism correlation reflects structural priors of the attribution methods rather than learned sensitization chemistry. Mechanism-class stratification surfaced one candidate exception—pre-hapten autoxidation chemistry, with a \(\Delta = +0.26\)Δ=+0.26 atom-AUC gap and non-overlapping confidence intervals—on a stratum of approximately two unique molecules, reported as a hypothesis pending replication on dedicated pre-hapten benchmarks. Per-element residual analysis converges on the same interpretation: alignment for gradient- and attention-based methods drops to chance once elemental identity is regressed out. Scientific contribution This work pairs a reproducible evaluation framework (50 skin-sensitization-specific SMARTS patterns scored against atom-level GNN attributions) with a label-permutation negative control that separates learned chemistry from structural priors of the attribution method.