Opening Amyloid-Windows to the Secondary Structure of Proteins: The Amyloidogenecity Increases Tenfold Inside Beta-Sheets

TL;DR

This study uses AI to predict amyloidogenic regions in proteins, revealing that internal beta-sheet hexamers are significantly more likely to be amyloidogenic than border regions, suggesting a protective mechanism against amyloid formation.

Contribution

The paper introduces an AI-based method to distinguish amyloidogenic regions within beta-sheets, uncovering a potential natural protective mechanism in protein structures.

Findings

Over 30% of internal beta-sheet hexamers are predicted amyloidogenic.

Only 3% of border regions are predicted amyloidogenic.

No similar pattern observed in alpha-helices or random sequences.

Abstract

Methods from artificial intelligence (AI), in general, and machine learning, in particular, have kept conquering new territories in numerous areas of science. Most of the applications of these techniques are restricted to the classification of large data sets, but new scientific knowledge can seldom be inferred from these tools. Here we show that an AI-based amyloidogenecity predictor can strongly differentiate the border- and the internal hexamers of $\beta$-pleated sheets when screening all the Protein Data Bank-deposited homology-filtered protein structures. Our main result shows that more than 30\% of internal hexamers of $\beta$ sheets are predicted to be amyloidogenic, while just outside the border regions, only 3\% are predicted as such. This result may elucidate a general protection mechanism of proteins against turning into amyloids: if the borders of $\beta$-sheets were amyloidogenic, then the whole $\beta$ sheet could turn more easily into an insoluble amyloid-structure, characterized by periodically repeated parallel $\beta$-sheets. We also present that no analogous phenomenon exists on the borders of $\alpha$-helices or randomly chosen subsequences of the studied protein structures.