Metraipolis › archive › dc_a7bec0578f71
pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows — arXiv:2610.01663
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01663
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:25:51.586Z
- SHA-256 of the archived text
e11af3d82fd97bc4983eb7869803848ca2ca52d2fa4dad84a57861f69d2de90f- Stable URL of this page
https://metraipolis.com/documento/dc_a7bec0578f71
How to cite
pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows — arXiv:2610.01663 — arXiv (en), https://arxiv.org/abs/2610.01663 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7bec0578f71 (Metraipolis archive dc_a7bec0578f71, sha256 e11af3d82fd97bc4983eb7869803848ca2ca52d2fa4dad84a57861f69d2de90f)
BibTeX
@misc{dca7bec0578f71,
title = {pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows — arXiv:2610.01663},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01663},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7bec0578f71; sha256 e11af3d82fd97bc4983eb7869803848ca2ca52d2fa4dad84a57861f69d2de90f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01663. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Biomolecular therapeutics often start from known sequences and require targeted editing to improve multiple properties while satisfying hard biochemical and manufacturability constraints. However, existing generative methods do not jointly support multi-objective optimization, hard feasibility, and sequence editing in discrete, variable-length biological spaces. In this work, we introduce Pareto-Constrained Molecule Editing (pCoMole), a framework built on discrete flow matching that steers a pre-trained Edit Flow toward user-specified preferences while enforcing terminal feasibility. pCoMole defines a feasibility-gated terminal distribution using an augmented Tchebycheff utility and realizes the resulting preference tilt through a Doob-h transform of the underlying edit process. To make this construction practical, we approximate the required harmonic function using short Monte Carlo rollouts over candidate edits, yielding an efficient guided editor with provable preference consistency. We validate pCoMole by shrinking GFP while retaining fluorescence-related properties, shortening diverse Cas9 orthologs while preserving PAM specificity, and compressing peptide binders into short peptidomimetics that optimize seven drug-related properties under hard constraints. In wet lab testing, two 229-residue pCoMole-designed eGFP variants retained clear green fluorescence in BL21 cells after 10 deletions, with either one or two substitutions. Together, pCoMole enables constraint-aware, Pareto-aligned editing of biomolecular sequences in discrete, variable-length spaces. Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-10-02 in q-bio.BM). Categorie arXiv: Machine Learning (cs.LG) ; Biomolecules (q-bio.BM). Pagina del lavoro: https://arxiv.org/abs/2610.01663 — 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 2026-10-07T11:58:41.692Z dalla pagina https://arxiv.org/catchup/q-bio.BM/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).