Co-design protein sequence and structure in discrete space via generative flow.

Abstract

Generative models have demonstrated considerable promise in de novo protein design. Traditional approaches typically focus on either sequence or structure in isolation, limiting the capacity to explore the intricate sequence-structure landscape and achieve optimal designs. However, joint protein sequence and structure co-design remains a largely underexplored challenge. We present CoFlow, a discrete model for protein co-design from scratch or given constraints. CoFlow employs a joint discrete flow and integrates a multi-modal protein masked language model to facilitate co-design in the discrete space. Comprehensive experiments demonstrate that CoFlow outperforms previous design methods across multiple evaluation metrics. Notably, CoFlow achieves a consistency approximately eight times higher than that of ESM3 in unconditional generation. Moreover, CoFlow exhibits competitive performance in conditional generation tasks, including motif-scaffolding, protein folding, and inverse folding. The source code of CoFlow, including data preprocessing and model, is available at https://github.com/LtECoD/CoFlow and https://zenodo.org/records/14842367. (DOI: 10.5281/zenodo.14842367).