Metraipolis › archive › dc_13d6501905bb
Navigating Route Latent Space for Synthesizable Molecular Design — arXiv:2610.07560
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07560
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:18:47.960Z
- SHA-256 of the archived text
911b79841947594c455cd6b848f7d823417068cd2960281e4644db7a141428d5- Stable URL of this page
https://metraipolis.com/documento/dc_13d6501905bb
How to cite
Navigating Route Latent Space for Synthesizable Molecular Design — arXiv:2610.07560 — arXiv (en), https://arxiv.org/abs/2610.07560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_13d6501905bb (Metraipolis archive dc_13d6501905bb, sha256 911b79841947594c455cd6b848f7d823417068cd2960281e4644db7a141428d5)
BibTeX
@misc{dc13d6501905bb,
title = {Navigating Route Latent Space for Synthesizable Molecular Design — arXiv:2610.07560},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07560},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_13d6501905bb; sha256 911b79841947594c455cd6b848f7d823417068cd2960281e4644db7a141428d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Goal-directed molecular design has advanced rapidly, yet a substantial proportion of designed molecules remain difficult to synthesize in practice, limiting their real-world utility. Prior synthesizability-aware methods either project generated molecules back to synthesizable analogs that deviate from the intended target, or optimize directly in discrete synthesis spaces that lack a continuous landscape for efficient search. We argue that this limitation mainly comes from the search space rather than the optimizer. To address this, we propose RouteFlow, a framework that reformulates synthesizable molecular design as a search over a continuous route latent space, where each latent maps back to a complete synthesis route and synthesizability is inherently preserved. To navigate this space, we adopt reward-guided flow matching as an efficient sampler that steers toward high-property regions. Since reward optimization may push latents off the manifold of real synthesis routes, where decoding becomes unreliable, we further introduce a cycle-consistency mechanism to stabilize fine-tuning. Across 16 optimization tasks from Therapeutic Data Commons, RouteFlow achieves the best sample efficiency among synthesizability-aware baselines, with the best synthetic accessibility and the highest retrosynthesis success rate. Our results also confirm that the proposed cycle-consistency reliably keeps optimization on-manifold while improving target properties, supporting effective synthesizable molecular discovery. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE). Pagina del lavoro: https://arxiv.org/abs/2610.07560 — 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 2026-10-07T11:15:24.521Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).