Improving AlphaFlow for Efficient Protein Ensembles Generation

TL;DR

This paper introduces AlphaFlow-Lit, a lightweight generative model that significantly accelerates protein ensemble sampling, maintaining accuracy while reducing computational costs by approximately 47 times.

Contribution

AlphaFlow-Lit is a novel, feature-conditioned model that improves sampling efficiency for protein conformations without extensive fine-tuning.

Findings

AlphaFlow-Lit matches AlphaFlow's performance.

AlphaFlow-Lit surpasses its distilled version without pretraining.

Sampling acceleration of around 47 times achieved.

Abstract

Investigating conformational landscapes of proteins is a crucial way to understand their biological functions and properties. AlphaFlow stands out as a sequence-conditioned generative model that introduces flexibility into structure prediction models by fine-tuning AlphaFold under the flow-matching framework. Despite the advantages of efficient sampling afforded by flow-matching, AlphaFlow still requires multiple runs of AlphaFold to finally generate one single conformation. Due to the heavy consumption of AlphaFold, its applicability is limited in sampling larger set of protein ensembles or the longer chains within a constrained timeframe. In this work, we propose a feature-conditioned generative model called AlphaFlow-Lit to realize efficient protein ensembles generation. In contrast to the full fine-tuning on the entire structure, we focus solely on the light-weight structure module to reconstruct the conformation. AlphaFlow-Lit performs on-par with AlphaFlow and surpasses its distilled version without pretraining, all while achieving a significant sampling acceleration of around 47 times. The advancement in efficiency showcases the potential of AlphaFlow-Lit in enabling faster and more scalable generation of protein ensembles.