Metraipolis › archive › dc_2ab540966ebf
ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction — arXiv:2608.30472
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30472
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:39:15.636Z
- SHA-256 of the archived text
36587bcc1d81e35a6f6822ffa1c51d2c437505a30884d502018901fcbc8df106- Stable URL of this page
https://metraipolis.com/documento/dc_2ab540966ebf
How to cite
ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction — arXiv:2608.30472 — arXiv (en), https://arxiv.org/abs/2608.30472 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ab540966ebf (Metraipolis archive dc_2ab540966ebf, sha256 36587bcc1d81e35a6f6822ffa1c51d2c437505a30884d502018901fcbc8df106)
BibTeX
@misc{dc2ab540966ebf,
title = {ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction — arXiv:2608.30472},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30472},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ab540966ebf; sha256 36587bcc1d81e35a6f6822ffa1c51d2c437505a30884d502018901fcbc8df106},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30472. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Molecular toxicity prediction is increasingly used to prioritise compounds before experimental testing, but conventional benchmark performance can overstate practical utility when structurally related molecules occur across training and test folds. We introduce ToxLens, a reproducible multi-task graph-learning framework for 11 toxicity endpoints spanning Ames mutagenicity, acute oral toxicity, hERG inhibition, and Tox21 nuclear-receptor and stress-response assays. The workflow combines conservative chemical curation, sphere-exclusion filtering, a leakage-aware UMAP-HDBSCAN split, parallel graph and global-feature encoders joined by late concatenation, temperature-scaled Monte Carlo dropout with conformal-style prediction sets, applicability-domain analysis, and SHAP-guided toxicophore discovery with occlusion controls. On the leakage-controlled test fold, a five-seed soft-voting ensemble achieved a Matthews correlation coefficient score of 0.44, an area under the receiver operating characteristic curve score of 0.83, and an area under the precision-recall curve score of 0.58. It exceeded four ECFP4-based shallow baselines on all 11 endpoints under the same split and validation-based threshold-selection protocol. Controlled ablations showed that the global pathway was important, whereas late concatenation outperformed the tested gated and feature-wise linear modulation fusion variants. Conformal-style prediction sets revealed substantial endpoint-specific variation in set efficiency, and discrimination and calibration improved with similarity to the training domain. Retraining on fixed published Tox21 Challenge and TDA folds produced competitive, but not uniformly state-of-the-art, performance. SHAP-guided occlusion and consensus subgraph mining yielded model-derived structural hypotheses, 44 of which contained at least one occurrence that passed the predefined counterfactual criteria. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.30472 — 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 2026-10-17T08:13:26.824Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).