Applications of Knot Theory for the Improvement of the AlphaFold Protein Database

TL;DR

This paper evaluates AlphaFold's ability to predict knotted protein structures, revealing high accuracy in general shape but limitations in detailed knot orientation, and suggests improvements for the AlphaFold Protein Database.

Contribution

It introduces a detailed analysis of AlphaFold's performance on knotted proteins and proposes methods to enhance knot representation accuracy in the database.

Findings

95.6% accuracy with Alexander-Briggs notation

55.6% discrepancy with Gauss code analysis

Need for improved knot modeling in AlphaFold

Abstract

AlphaFold, a groundbreaking protein prediction model, has revolutionized protein structure prediction, populating the AlphaFold Protein Database (AFDB) with millions of predicted structures. However, AlphaFold's accuracy in predicting proteins with intricate topologies, such as knots, remains a concern. This study investigates AlphaFold's performance in predicting knotted proteins and explores potential solutions to enhance the AFDB's reliability. Forty-five experimentally verified knotted protein structures from the KnotProt database were compared to their AlphaFold-generated counterparts. Knot analysis was performed using PyKnot, a PyMOL plugin, employing both Gauss codes and Alexander-Briggs knot notations. Results showed 95.6% accuracy in predicting the general shape of knots using Alexander-Briggs notation. However, Gauss code analysis revealed a 55.6% discrepancy, indicating AlphaFold's limitations in accurately representing the intricate orientation and directionality of knots. This Applications of Knot Theory for the improvement of the AlphaFold Protein Database suggests potential inaccuracies in a significant portion of the AFDB's knotted protein structures. The study underscores the need for improved knot representation in AlphaFold and proposes potential solutions, including transitioning to a single-module design or removing incorrectly predicted structures from the AFDB. These findings highlight the importance of continuous refinement for AI-based protein structure prediction tools to ensure the accuracy and reliability of protein databases for research and drug development.