Sampling-based Continuous Optimization for Messenger RNA Design

TL;DR

This paper introduces a sampling-based continuous optimization framework for mRNA design that iteratively improves sequence properties by sampling, evaluation, and updating, demonstrating strong results across various proteins and objectives.

Contribution

The proposed method is a novel, flexible sampling-based optimization approach that effectively balances multiple objectives in mRNA sequence design, outperforming existing methods.

Findings

Consistently improves target objectives across diverse proteins.

Achieves significant gains in unpaired probability and uridine accessibility.

Enables multi-objective trade-off control through COMBO formulation.

Abstract

Designing messenger RNA (mRNA) sequences for a fixed target protein requires searching an exponentially large synonymous space while optimizing properties that affect stability and downstream performance. This is challenging because practical mRNA design involves multiple coupled objectives beyond classical folding criteria, and different applications prefer different trade-offs. We propose a general sampling-based continuous optimization framework, inspired by SamplingDesign, that iteratively samples candidate synonymous sequences, evaluates them with black-box metrics, and updates a parameterized sampling distribution. Across a diverse UniProt protein set and the SARS-CoV-2 spike protein, our method consistently improves the chosen objective, with particularly strong gains on average unpaired probability and accessible uridine percentage compared to LinearDesign and EnsembleDesign. Moreover, our multi-objective COMBO formulation enables weight-controlled exploration of the design space and naturally extends to incorporate additional computable metrics.