Predictomes, a classifier-curated database of AlphaFold-modeled protein-protein interactions

Abstract

Protein-protein interactions (PPIs) are ubiquitous in biology, yet a comprehensive structural characterization of the PPIs underlying cellular processes is lacking. AlphaFold-Multimer (AF-M) has the potential to fill this knowledge gap, but standard AF-M confidence metrics do not reliably separate relevant PPIs from an abundance of false positive predictions. To address this limitation, we used machine learning on curated datasets to train a structure prediction and omics-informed classifier (SPOC) that effectively separates true and false AF-M predictions of PPIs, including in proteome-wide screens. We applied SPOC to an all-by-all matrix of nearly 300 human genome maintenance proteins, generating ∼40,000 predictions that can be viewed at predictomes.org , where users can also score their own predictions with SPOC. High-confidence PPIs discovered using our approach enable hypothesis generation in genome maintenance. Our results provide a framework for interpreting large-scale AF-M screens and help lay the foundation for a proteome-wide structural interactome. • SPOC classifier identifies functional AlphaFold-Multimer structure predictions • Proteome-wide in silico screening with AlphaFold-Multimer enabled by SPOC classifier • Curated database of 40,000 binary structure predictions in genome maintenance • User-friendly website predictomes.org to browse predictions and build hypotheses Schmid and Walter train a classifier that discerns functionally relevant structure predictions in proteome-wide protein-protein interaction (PPI) screens using AlphaFold-Multimer, and they use this confidence metric to curate a database of 40,000 predicted interactions among ∼300 genome maintenance proteins.

Abstract of "Predictomes, a classifier-curated database of AlphaFold-modeled protein-protein interactions" by Ernst W. Schmid, Johannes C. Walter, https://doi.org/10.1016/j.molcel.2025.01.034, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.