All-atom inverse protein folding through discrete flow matching

TL;DR

ADFLIP is a novel all-atom inverse protein folding model that uses discrete flow matching to design sequences conditioned on structural context, excelling in complex and dynamic protein structures.

Contribution

This work introduces ADFLIP, a new generative model for inverse protein folding that incorporates all-atom structural context and ensemble sampling, outperforming previous methods.

Findings

Achieves state-of-the-art performance in inverse folding tasks.

Effectively designs sequences for dynamic and multi-state protein complexes.

Incorporates pre-trained models for property-guided sequence optimization.

Abstract

The recent breakthrough of AlphaFold3 in modeling complex biomolecular interactions, including those between proteins and ligands, nucleotides, or metal ions, creates new opportunities for protein design. In so-called inverse protein folding, the objective is to find a sequence of amino acids that adopts a target protein structure. Many inverse folding methods struggle to predict sequences for complexes that contain non-protein components, and perform poorly with complexes that adopt multiple structural states. To address these challenges, we present ADFLIP (All-atom Discrete FLow matching Inverse Protein folding), a generative model based on discrete flow-matching for designing protein sequences conditioned on all-atom structural contexts. ADFLIP progressively incorporates predicted amino acid side chains as structural context during sequence generation and enables the design of dynamic protein complexes through ensemble sampling across multiple structural states. Furthermore, ADFLIP implements training-free classifier guidance sampling, which allows the incorporation of arbitrary pre-trained models to optimise the designed sequence for desired protein properties. We evaluated the performance of ADFLIP on protein complexes with small-molecule ligands, nucleotides, or metal ions, including dynamic complexes for which structure ensembles were determined by nuclear magnetic resonance (NMR). Our model achieves state-of-the-art performance in single-structure and multi-structure inverse folding tasks, demonstrating excellent potential for all-atom protein design. The code is available at https://github.com/ykiiiiii/ADFLIP.