Metraipolis › archive › dc_2cce183c0122

MolExplain: An Interactive Tool for Explainable Molecular Property Prediction — arXiv:2609.25355

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25355
License (as archived)
CC0-1.0
Archived
2026-10-08T15:07:02.688Z
SHA-256 of the archived text
99253afa7a97c239c8690d9e0d6f63bc0b0a75c9b4adabac0ad317d0df8cbdb2
Stable URL of this page
https://metraipolis.com/documento/dc_2cce183c0122

How to cite

MolExplain: An Interactive Tool for Explainable Molecular Property Prediction — arXiv:2609.25355 — arXiv (en), https://arxiv.org/abs/2609.25355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cce183c0122 (Metraipolis archive dc_2cce183c0122, sha256 99253afa7a97c239c8690d9e0d6f63bc0b0a75c9b4adabac0ad317d0df8cbdb2)
BibTeX
@misc{dc2cce183c0122,
  title = {MolExplain: An Interactive Tool for Explainable Molecular Property Prediction — arXiv:2609.25355},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25355},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cce183c0122; sha256 99253afa7a97c239c8690d9e0d6f63bc0b0a75c9b4adabac0ad317d0df8cbdb2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The application of machine learning to molecular property prediction has become increasingly prevalent in drug discovery, yet most models operate as black boxes, returning a prediction without revealing which structural features drive it. MolExplain addresses this gap by combining property prediction with sub-structure level visual explainability in an interactive web interface. The system featurizes molecules as Morgan fingerprints, classifies them using a trained XGBoost model, and applies SHAP attribution to produce a smooth heatmap overlay indicating which regions of the molecule contribute for or against the predicted property. Applied to cyclic peptide membrane permeability, the tool's attribution independently recovers the known role of backbone N-methylation in improving passive membrane diffusion, consistent with established chemistry. While demonstrated on cyclic peptides, the framework is designed to generalize to other molecular properties, positioning MolExplain as a platform for interactive, explainability-driven molecular design.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.HC).
Categorie arXiv: Chemical Physics (physics.chem-ph) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.25355 — 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 2026-10-08T14:34:31.486Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).