AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance
This addresses the problem of multi-objective sequence design for therapeutic and biomolecular engineering, offering a novel method with theoretical guarantees.
The paper tackled the challenge of designing sequences with multiple conflicting objectives in biomolecular engineering by introducing AReUReDi, a discrete optimization algorithm that outperformed evolutionary and diffusion-based baselines in optimizing up to five therapeutic properties for peptides and SMILES sequences.
Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single-objective guidance, while discrete approaches lack guarantees for multi-objective Pareto optimality. We introduce AReUReDi (Annealed Rectified Updates for Refining Discrete Flows), a discrete optimization algorithm with theoretical guarantees of convergence to the Pareto front. Building on Rectified Discrete Flows (ReDi), AReUReDi combines Tchebycheff scalarization, locally balanced proposals, and annealed Metropolis-Hastings updates to bias sampling toward Pareto-optimal states while preserving distributional invariance. Applied to peptide and SMILES sequence design, AReUReDi simultaneously optimizes up to five therapeutic properties (including affinity, solubility, hemolysis, half-life, and non-fouling) and outperforms both evolutionary and diffusion-based baselines. These results establish AReUReDi as a powerful, sequence-based framework for multi-property biomolecule generation.