Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment

TL;DR

ProtAlign is a multi-objective framework that fine-tunes inverse folding models to optimize multiple developability properties of proteins while maintaining structural accuracy, addressing a key challenge in protein design.

Contribution

It introduces ProtAlign, a novel semi-online preference optimization method that balances multiple protein developability objectives during inverse folding model fine-tuning.

Findings

MoMPNN improves developability metrics without losing designability.

The framework is effective across various protein design tasks.

ProtAlign enhances practical protein sequence design applications.

Abstract

Protein sequence design must balance designability, defined as the ability to recover a target backbone, with multiple, often competing, developability properties such as solubility, thermostability, and expression. Existing approaches address these properties through post hoc mutation, inference-time biasing, or retraining on property-specific subsets, yet they are target dependent and demand substantial domain expertise or careful hyperparameter tuning. In this paper, we introduce ProtAlign, a multi-objective preference alignment framework that fine-tunes pretrained inverse folding models to satisfy diverse developability objectives while preserving structural fidelity. ProtAlign employs a semi-online Direct Preference Optimization strategy with a flexible preference margin to mitigate conflicts among competing objectives and constructs preference pairs using in silico property predictors. Applied to the widely used ProteinMPNN backbone, the resulting model MoMPNN enhances developability without compromising designability across tasks including sequence design for CATH 4.3 crystal structures, de novo generated backbones, and real-world binder design scenarios, making it an appealing framework for practical protein sequence design.