🧪 Test?View on arXiv
SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
Not provided in the abstract
multimodaltoxicity predictiongraph neural networksinterpretability
2609.28553
Builder Relevance
1h ago80%
Abstract
SMILESGNN is a multimodal architecture that improves drug toxicity prediction by fusing SMILES and graph representations while enabling interpretable predictions.
Reality Card
Core Claim
SMILESGNN achieves competitive predictive performance on toxicity prediction tasks while providing graph-based interpretability.
Method / Result
Achieved AUC-ROC of 0.987 on ClinTox with only 0.4M parameters.
Limitations
The paper does not specify the authors or provide detailed reproducibility instructions.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.