Reconstructing phosphorylation signalling networks from quantitative phosphoproteomic data

Abstract

Cascades of phosphorylation between protein kinases comprise a core mechanism in the integration and propagation of intracellular signals. Although we have accumulated a wealth of knowledge around some such pathways, this is subject to study biases and much remains to be uncovered. Phosphoproteomics, the identification and quantification of phosphorylated proteins on a proteomic scale, provides a high-throughput means of interrogating the state of intracellular phosphorylation, both at the pathway level and at the whole-cell level. In this review, we discuss methods for using human quantitative phosphoproteomic data to reconstruct the underlying signalling networks that generated it. We address several challenges imposed by the data on such analyses and we consider promising advances towards reconstructing unbiased, kinome-scale signalling networks.

Keywords: biological networks; intracellular signaling; phosphorylation/dephosphorylation; systems biology.

Figure 1. Study bias is a hindrance to comprehensive signalling pathway reconstruction

(A) Well-studied human protein kinases may appear to be signalling hubs. They have more annotated substrates (top-left panel), including more substrates that are other protein kinases (top-right). They also are annotated to be substrates of more protein kinases themselves (bottom-left) and to carry more activity-regulating phosphorylation sites (bottom-right). Linked publications were retrieved from NCBI Entrez Gene database for each human protein kinase and filtered to remove publications associated with more than ten kinases [11]. Substrate and regulatory site counts were retrieved from PhosphoSitePlus [9]. All data were retrieved on 1 May 2018. (B) Literature-derived signalling networks are biased towards canonical pathways: annotated kinase-kinase phosphorylation (left) and regulatory (right) relationships tend to be between well-studied kinases, while relationships involving lesser studied kinases remain unknown. Publication counts for each kinase were binned into ten categories (deciles) of approximately 50 protein kinases each. Human kinase-kinase regulatory relationships were retrieved from OmniPath [10], restricting to directed relationships with support from at least two source databases. Autophosphorylation and autoregulation were omitted for clarity.

Figure 2. A kinome-wide, probabilistic regulatory network would serve as a foundation upon which to derive context-specific signalling pathways

Phosphoproteomic and other data are collected from large-scale experiments in which different cellular contexts (e.g. cell lines, tissue types or stimulus regimes) are measured across several perturbations and/or time points. Kinase activities are inferred from these data and mapped on to the probabilistic network. Further network refinement is then performed to reconstruct context-specific signalling pathways.