Interpretable Network Propagation with Application to Expanding the Repertoire of Human Proteins that Interact with SARS-CoV-2

TL;DR

This paper introduces a network propagation framework with provenance tracing to predict human proteins interacting with SARS-CoV-2, providing biological insights and potential drug targets, while reducing manual parameter tuning.

Contribution

It presents a novel provenance tracing method for network propagation predictions and a technique to minimize manual parameter adjustments, applied to SARS-CoV-2 protein interactions.

Findings

Top predictions are mainly influenced by direct neighbors in the protein network.

Identified connections between endoplasmic reticulum stress and SARS-CoV-2.

Provided a resource implicating new proteins and potential drugs for COVID-19.

Abstract

Background: Network propagation has been widely used for nearly 20 years to predict gene functions and phenotypes. Despite the popularity of this approach, little attention has been paid to the question of provenance tracing in this context, e.g., determining how much any experimental observation in the input contributes to the score of every prediction. Results: We design a network propagation framework with two novel components and apply it to predict human proteins that directly or indirectly interact with SARS-CoV-2 proteins. First, we trace the provenance of each prediction to its experimentally validated sources, which in our case are human proteins experimentally determined to interact with viral proteins. Second, we design a technique that helps to reduce the manual adjustment of parameters by users. We find that for every top-ranking prediction, the highest contribution to its score arises from a direct neighbor in a human protein-protein interaction network. We further analyze these results to develop functional insights on SARS-CoV-2 that expand on known biology such as the connection between endoplasmic reticulum stress, HSPA5, and anti-clotting agents. Conclusions: We examine how our provenance tracing method can be generalized to a broad class of network-based algorithms. We provide a useful resource for the SARS-CoV-2 community that implicates many previously undocumented proteins with putative functional relationships to viral infection. This resource includes potential drugs that can be opportunistically repositioned to target these proteins. We also discuss how our overall framework can be extended to other, newly-emerging viruses.