SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
The results suggest that cross-attention is a practical fusion alternative that preserves competitive predictive performance while enabling graph-based interpretability support.
Quang Minh Nguyen, Thuy Quynh Nguyen, Đức Minh Lê et al.
· International Conference on... · 0 citations