Deep Contextual Learners for Protein Networks
This work addresses the need for contextualized protein interactions to better characterize disease-specific interactions and elucidate disease manifestations in specific cell types, representing a domain-specific advancement.
The authors tackled the problem of lacking spatial context in protein interaction networks, which limits understanding of where interactions occur and how they are altered in disease, by introducing AWARE, a graph neural message passing approach that injects cellular and tissue context into protein embeddings, resulting in at least a 12.5% improvement over generic embeddings in predicting disease-related protein alterations.
Spatial context is central to understanding health and disease. Yet reference protein interaction networks lack such contextualization, thereby limiting the study of where protein interactions likely occur in the human body and how they may be altered in disease. Contextualized protein interactions could better characterize genes with disease-specific interactions and elucidate diseases' manifestation in specific cell types. Here, we introduce AWARE, a graph neural message passing approach to inject cellular and tissue context into protein embeddings. AWARE optimizes for a multi-scale embedding space, whose structure reflects network topology at a single-cell resolution. We construct a multi-scale network of the Human Cell Atlas and apply AWARE to learn protein, cell type, and tissue embeddings that uphold cell type and tissue hierarchies. We demonstrate AWARE's utility on the novel task of predicting whether a protein is altered in disease and where that association most likely manifests in the human body. To this end, AWARE outperforms generic embeddings without contextual information by at least 12.5%, showing AWARE's potential to reveal context-dependent roles of proteins in disease.