Metraipolis › archive › dc_7922d434e20e

On the limitations of molecular representations — arXiv:2611.08420

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08420
License (as archived)
CC0-1.0
Archived
2026-11-06T14:50:59.816Z
SHA-256 of the archived text
b09c05cc4d6487a8560fff94ba16090e74e784a54c2d65c4c0eb0ada312a7fda
Stable URL of this page
https://metraipolis.com/documento/dc_7922d434e20e

How to cite

On the limitations of molecular representations — arXiv:2611.08420 — arXiv (en), https://arxiv.org/abs/2611.08420 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7922d434e20e (Metraipolis archive dc_7922d434e20e, sha256 b09c05cc4d6487a8560fff94ba16090e74e784a54c2d65c4c0eb0ada312a7fda)
BibTeX
@misc{dc7922d434e20e,
  title = {On the limitations of molecular representations — arXiv:2611.08420},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08420},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7922d434e20e; sha256 b09c05cc4d6487a8560fff94ba16090e74e784a54c2d65c4c0eb0ada312a7fda},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08420. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Molecular representations such as fingerprints and learned embeddings play a central role in cheminformatics and small-molecule machine learning. They serve as the primary input for a diverse array of tasks, including clustering, dataset splitting, and virtual screening, yet their evaluation is often limited to downstream model performance on narrow benchmark tasks. We carried out a systematic investigation of the quality of molecular representations, finding that none of the state-of-the-art molecular embedding models capture graph structure, 3D shape, or ADMET endpoint similarity better than fingerprints or physicochemical descriptors. However, classical fingerprints also revealed their own material limitations. For example, we show that depending on the representation, between 225M and $\sim$4B molecules have non-unique representations in the 10.8B Enamine REAL database, with implications for virtual screening. Our findings provide an insight into the current limitations of molecular representations, outlining future research directions for the development of more robust encodings of small molecules.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.08420 — 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 2026-11-06T14:21:42.649Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).