Prediction of protein-protein interactions using sequences of intrinsically disordered regions

Protein-protein interactions (PPIs) play a crucial role in numerous molecular processes. Despite many efforts, mechanisms governing molecular recognition between interacting proteins remain poorly understood and it is particularly challenging to predict from sequence whether two proteins can interact. Here we present a new method to tackle this challenge using intrinsically disordered regions (IDRs). IDRs are protein segments that are functional despite lacking a single invariant three-dimensional structure. The prevalence of IDRs in eukaryotic proteins suggests that IDRs are critical for interactions. To test this hypothesis, we predicted PPIs using IDR sequences in candidate proteins in humans. Moreover, we divide the PPI prediction problem into two specific subproblems and adapt appropriate training and test strategies based on problem type. Our findings underline the importance of defining clearly the problem type and show that sequences encoding IDRs can aid in predicting specific features of the protein interaction network of intrinsically disordered proteins. Our findings further suggest that accounting for IDRs in future analyses should accelerate efforts to elucidate the eukaryotic PPI network.

Automated summary

Protein-protein interactions (PPIs) are crucial for molecular processes, but the mechanisms of molecular recognition between interacting proteins are poorly understood, making it challenging to predict interactions from sequence. This study proposes a new method using intrinsically disordered regions (IDRs) to tackle this challenge. Using IDR sequences, the researchers predicted PPIs in candidate proteins and divided the prediction problem into subproblems, adapting appropriate strategies. The findings highlight the importance of defining problem type and suggest that accounting for IDRs can aid in predicting features of the intrinsically disordered protein interaction network, accelerating efforts to understand the eukaryotic PPI network.