Metraipolis › archive › dc_ccc88cf71c2e

PairIT: Autoregressive Transformers for Low-Data Molecule Optimization — arXiv:2610.19123

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19123
License (as archived)
CC0-1.0
Archived
2026-10-15T14:15:04.956Z
SHA-256 of the archived text
64affd8f3fa56daf0c3515317cc1669d3918127079c57b929af44b676fafc55c
Stable URL of this page
https://metraipolis.com/documento/dc_ccc88cf71c2e

How to cite

PairIT: Autoregressive Transformers for Low-Data Molecule Optimization — arXiv:2610.19123 — arXiv (en), https://arxiv.org/abs/2610.19123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccc88cf71c2e (Metraipolis archive dc_ccc88cf71c2e, sha256 64affd8f3fa56daf0c3515317cc1669d3918127079c57b929af44b676fafc55c)
BibTeX
@misc{dcccc88cf71c2e,
  title = {PairIT: Autoregressive Transformers for Low-Data Molecule Optimization — arXiv:2610.19123},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19123},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccc88cf71c2e; sha256 64affd8f3fa56daf0c3515317cc1669d3918127079c57b929af44b676fafc55c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation, practical use cases require a more complex setting: conditioning on an initial seed molecule, optimizing multiple properties, and operating in data-sparse regimes. We introduce PairIT, a flexible training framework for autoregressive transformers over SMILES sequences that enables seeded generation by learning from pairs of structurally similar molecules. By leveraging matched pairs, the model learns to generate local, chemically meaningful edits that improve a property of the seed molecule. Prompt tokens extend this framework by specifying the target property, desired direction, and approximate magnitude of change. Multiple prompt tokens can be concatenated to enable multi-property optimization at inference time. For properties where pair supervision alone is insufficient, reinforcement learning post-training can further improve optimization, providing a tunable trade-off between proximity to the seed and the optimization objective. PairIT naturally supports pretraining on a large dataset and fine-tuning on a smaller dataset, which is critical for performance in data-sparse regimes. Surprisingly, we observe diminishing returns to the scale of the pretraining dataset. We demonstrate empirically on MoleculeNet and Therapeutics Data Commons datasets that, with appropriate paired-data curation, a standard transformer model of modest size (68M parameters) can achieve robust seeded molecular optimization in low-data regimes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Chemical Physics (physics.chem-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.19123 — 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 2026-10-15T13:53:35.529Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).