pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
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.
Related
- Short TALE-binding domains enable mitochondrial genome editing in Arabidopsis thaliana
- Molecular triage and isoform protection safeguard ubiquitin chain editing on DNA
- Prime editing for precise genome engineering and modulation of fungal metabolism
- Iterative genome editing of Escherichia coli for 3-hydroxypropionic acid production
- GESV: a bioinformatic pipeline for genome editing sequence variants analysis
BibTeX
@misc{chen2026pcomole,
title = {{pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows}},
author = {Tong Chen and Maximilian Holsman and Lin Zhao and Pranam Chatterjee},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.01663},
eprint = {2610.01663},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.01663},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
AU - Tong Chen
AU - Maximilian Holsman
AU - Lin Zhao
AU - Pranam Chatterjee
PY - 2026
DA - 2026/10/04
PB - arXiv
DO - 10.48550/arxiv.2610.01663
UR - https://arxiv.org/abs/2610.01663
AB - 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.
ER -