pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
cs.LG, q-bio.BM
Submitted: 2026-10-01
Updated: 2026-10-04
Comments: Published at NeurIPS 2026. (Proceedings of the 40th Conference on Neural Information Processing Systems, Sydney, Australia)
Code: https://github.com/datagrok-ai/admetica
License: http://creativecommons.org/licenses/by/4.0/
The gist: Biomolecular therapeutics often start from known sequences and require targeted editing to improve multiple properties while satisfying hard biochemical and manufacturability constraints.
Terminology
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.
Sources
- A Diffusion Model to Shrink Proteins While Maintaining Their Function
- Multi-Constrained Evolutionary Molecular Design Framework: An Interpretable Drug Design Method Combining Rule-Based Evolution and Molecular Crossover
- Simple Guidance Mechanisms for Discrete Diffusion Models
- AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance
- TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
- Edit Flows: Flow Matching with Edit Operations
- Constrained Discrete Diffusion
- Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
- ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks