arXiv：cs.LG（机器学习，全量分类）· Tong Chen, Maximilian Holsman, Lin Zhao, Pranam Chatterjee·· 14 小时前AI 评分40
pCoMole：基于离散流的帕累托约束分子编辑
pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
AI 导读
研究者提出 pCoMole，一个基于离散流匹配的分子编辑框架，可将预训练 Edit Flow 引导至用户偏好并强制终端可行性。该方法通过增广 Tchebycheff 效用定义可行性门控终端分布，并用 Doob h-变换实现偏好倾斜，借助短 Monte Carlo rollout 近似调和函数。
正文
Abstract: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.
| Comments: | Published at NeurIPS 2026. (Proceedings of the 40th Conference on Neural Information Processing Systems, Sydney, Australia) |
| Subjects: | Machine Learning (cs.LG); Biomolecules (q-bio.BM) |
| Cite as: | arXiv:2610.01663 [cs.LG] |
| (or arXiv:2610.01663v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01663 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pranam Chatterjee [view email]
[v1]
Thu, 1 Oct 2026 13:24:24 UTC (18,194 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org