Co-Generative De Novo Functional Protein Design

TL;DR

This paper introduces CodeFP, a co-generative language model for de novo protein design that improves the simultaneous realization of protein functionality and foldability.

Contribution

It proposes a novel co-generative approach with functional local structures and auxiliary supervision to enhance protein design quality.

Findings

CodeFP achieves 6.1% higher functional consistency.

CodeFP improves foldability by 3.2%.

Extensive experiments validate the effectiveness of the approach.

Abstract

De novo functional protein design aims to generate protein sequences that realize specified biochemical functions without relying on evolutionary templates, enabling broad applications in biotechnology and medicine. Existing approaches adopt either direct function-to-sequence mapping or decoupled structure-sequence generation strategies but often fail to achieve functionality and foldability simultaneously. To address this, we propose CodeFP, a Co-generative protein language model for de novo Functional Protein design that simultaneously decodes sequence and structure tokens, thereby enabling superior simultaneous realization of functionality and foldability. CodeFP utilizes functional local structures to enrich functional semantic encodings, overcoming the suboptimal translation of flat encodings into structure tokens, while introducing auxiliary functional supervision to alleviate training ambiguity stemming from the one-to-many structure-to-token mapping. Extensive experiments show that CodeFP consistently achieves average improvements of 6.1% in functional consistency and 3.2% in foldability over the strongest baseline.