Loading...
Loading...
Dataset URI:
10.1021/acs.jcim.6c02332.s001Attention-based graph neural networks (GNNs) are increasingly used for drug-induced liver injury (DILI) and other toxicity prediction tasks on the claimed strength of built-in interpretability, but this claim is almost always supported by a handful of hand-selected examples rather than being tested systematically. Using a curated, scaffold-split gold-standard DILI data set (1,079 compounds), we show that a graph attention network’s attention weights do not, in general, concentrate on seven literature-derived hepatotoxicity structural alerts across the full data set (pooled enrichment ratio of 0.35) and that the network itself does not outperform simple descriptor-based baselines under rigorous repeated-split evaluation (mean AUROC 0.625-0.649 vs. 0.714 for random forest, p = 0.011). We then show both gaps can be addressed: a chemistry-informed multitask extension, trained with an auxiliary structural-alert-recognition loss, improves attention alignment for two alerts by more than 5-fold (both Bonferroni/FDR-corrected p –14), confirmed across five independent scaffold splits, without a robust cost to classification performance. All curated data, trained models, and analysis code are released to support reproducibility and further benchmarking of both predictive and interpretability claims for molecular GNNs.
Keyword(s):
011 ).; 079 compounds ),; 649 vs; almost always supported; analysis code.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)