Classifying Metamorphic versus Single-Fold Proteins with Statistical Learning and AlphaFold2

TL;DR

This paper introduces a novel method combining AlphaFold2 and statistical learning to classify proteins as metamorphic or single-fold, aiding in the discovery of proteins with multiple conformations.

Contribution

We repurposed AlphaFold2 to generate conformational ensembles and trained a random forest classifier, achieving high accuracy in identifying metamorphic proteins.

Findings

Achieved a mean AUC of 0.869 in classification accuracy.

Identified potential metamorphic proteins in the Protein Data Bank.

Demonstrated the effectiveness of combining AI and statistical features for protein classification.

Abstract

The remarkable success of AlphaFold2 in providing accurate atomic-level prediction of protein structures from their amino acid sequence has transformed approaches to the protein folding problem. However, its core paradigm of mapping one sequence to one structure may only be appropriate for single-fold proteins with one stable conformation. Metamorphic proteins, which can adopt multiple distinct conformations, have conformational diversity that cannot be adequately modeled by AlphaFold2. Hence, classifying whether a given protein is metamorphic or single-fold remains a critical challenge for both laboratory experiments and computational methods. To address this challenge, we developed a novel classification framework by re-purposing AlphaFold2 to generate conformational ensembles via a multiple sequence alignment sampling method. From these ensembles, we extract a comprehensive set of features characterizing the conformational ensemble's modality and structural dispersion. A random forest classifier trained on a carefully curated benchmark dataset of known metamorphic and single-fold proteins achieves a mean AUC of 0.869 with cross-validation, demonstrating the effectiveness of our integrated approach. Furthermore, by applying our classifier to 600 randomly sampled proteins from the Protein Data Bank, we identified several potential metamorphic protein candidates -- including the 40S ribosomal protein S30, whose conformational change is crucial for its secondary function in antimicrobial defense. By combining AI-driven protein structure prediction with statistical learning, our work provides a powerful new approach for discovering metamorphic proteins and deepens our understanding of their role in their molecular function.