Computing the human interactome

TL;DR

This paper presents a new method to predict human protein-protein interactions using deep learning and large-scale genomic data, significantly expanding our knowledge of human protein networks.

Contribution

The novel use of 7-fold deeper multiple sequence alignments and a new DL network trained on 200 million predicted structures enables high-precision human PPI prediction.

Findings

The method predicted 18,316 PPIs with 90% precision, including 5,578 novel interactions.

3D models of predicted PPIs triple the number of human PPIs with structural information.

The results provide insights into protein function and mechanisms of human diseases.

Abstract

Protein-protein interactions (PPI) are essential for biological function. Recent advances in coevolutionary analysis and Deep Learning (DL) based protein structure prediction have enabled comprehensive PPI identification in bacterial and yeast proteomes, but these approaches have limited success to date for the more complex human proteome. Here, we overcome this challenge by 1) enhancing the coevolutionary signals with 7-fold deeper multiple sequence alignments harvested from 30 petabytes of unassembled genomic data, and 2) developing a new DL network trained on augmented datasets of domain-domain interactions from 200 million predicted protein structures. These advancements allow us to systematically screen through 200 million human protein pairs and predict 18,316 PPIs with an expected precision of 90%, among which 5,578 are novel predictions. 3D models of these predicted PPIs nearly triple the number of human PPIs with accurate structural information, providing numerous insights into protein function and mechanisms of human diseases.