Metraipolis › archive › dc_96a084cdbae3
SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion — arXiv:2609.28553
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28553
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:26:47.867Z
- SHA-256 of the archived text
24e3d9a195c194a3384322a6ad7c9f71e944a0ea3a93cfea6e7222753214a3df- Stable URL of this page
https://metraipolis.com/documento/dc_96a084cdbae3
How to cite
SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion — arXiv:2609.28553 — arXiv (en), https://arxiv.org/abs/2609.28553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96a084cdbae3 (Metraipolis archive dc_96a084cdbae3, sha256 24e3d9a195c194a3384322a6ad7c9f71e944a0ea3a93cfea6e7222753214a3df)
BibTeX
@misc{dc96a084cdbae3,
title = {SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion — arXiv:2609.28553},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28553},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96a084cdbae3; sha256 24e3d9a195c194a3384322a6ad7c9f71e944a0ea3a93cfea6e7222753214a3df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Drug toxicity prediction is critical for reducing late-stage attrition in drug discovery, yet remains challenging due to severe class imbalance, scaffold-based generalization, and the clinical need for interpretable predictions. Single-modality approaches-SMILES Transformers or graph neural networks capture complementary aspects of molecular structure, while sequence-only models cannot directly provide graph-attributed explanations. We present SMILESGNN, a multimodal architecture that fuses a SMILES Transformer encoder and a GATv2 graph encoder via cross-attention, and SMILESGNN-PT, a variant using a ChemBERTa-2 pretrained backbone. The design retains an explicit graph branch within the predictive pipeline, supporting GNNExplainer-based analysis of substructures associated with toxic predictions. On ClinTox, SMILESGNN achieves AUC-ROC 0.987 and F1 0.906 with only 0.4M parameters, performing competitively with a strong SMILESTransformer and a larger ChemBERTa-2/GATv2 concat-fusion baseline. On Tox21 (12 tasks), SMILESGNN-PT obtains mean AUC-ROC 0.750, comparable to ChemBERTa-2 alone and the same-backbone concat-fusion baseline. Overall, the results suggest that cross-attention is a practical fusion alternative that preserves competitive predictive performance while enabling graph-based interpretability support. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.28553 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T03:50:57.914Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).