New horizons in hypoxia signaling pathways

Abstract

Investigation into the regulation of the erythropoietin gene by oxygen led to the discovery of a process of direct oxygen sensing that transduces many cellular and systemic responses to hypoxia. The oxygen-sensitive signal is generated through the catalytic action of a series of 2-oxoglutarate-dependent oxygenases that regulate the transcription factor hypoxia-inducible factor (HIF) by the post-translational hydroxylation of specific amino acid residues. Here we review the implications of the unforeseen complexity of the HIF transcriptional cascade for the physiology and pathophysiology of hypoxia, and consider the origins of post-translational hydroxylation as a signaling process.

Keywords: Cancer; Hypoxia; Hypoxia-inducible factor; Prolyl hydroxylase; Protein hydroxylation; Transcription.

Fig. 1

Schematic illustrating the operation of the HIF pathway on processes both directly and indirectly related to the maintenance of oxygen balance. The HIF targets first identified were genes with direct effects on oxygen balance but as the number of identified HIF targets has increased the links of many to oxygen homeostasis have become increasingly indirect as exemplified by those involved in development and immune-inflammatory pathways.

Fig. 2

The implications of un-physiological ‘switching’ of massively interconnected pathways in cancer, exemplified by the activation of HIF following inactivation of the von Hippel-Lindau tumour suppressor. Inactivation of the von Hippel Lindau tumour suppressor leads to the unphysiological activation of both HIF-1 and HIF-2, each of which regulates its own set of target genes. Individual target genes will have net pro- (+), anti- (-) or broadly neutral (=) effects on tumour cell growth of varying intensity (+ or ++; - or --). In some contexts (i.e. those tissues where tumours do not arise in VHL disease) the net effect of this genetic switch will not be compatible with cell survival. In those tissues where tumours do arise in VHL disease the initial genetic switch is permissive for cell survival but many of the up-regulated genes will be co-selected passengers, rather than drivers of the cancer and the co-selected anti-tumourigenic genes will make the cells intrinsically vulnerable. It is proposed that the genetic switch will alter the cellular milieu and further selective pressures will lead to the enhanced representation of cells with altered gene expression profiles that qualitatively or quantitatively favour pro-tumourigenic genes and /or down-regulate anti-tumourigenic genes. This selection may act at the level of individual genes or entire sub-pathways, as exemplified by the tendency to silence or inactivate HIF-1 alpha in renal cancer. At any one time a tumour will contain a heterogeneous mixture of cells exhibiting different solutions compatible with survival.

Fig. 3

Multiple connections between oxygen sensors signaling to nuclear transcriptional functions and similar enzymes catalysing the hydroxylation of ribosomal and ribosome-related proteins. Intriguingly the sub-families of 2-oxoglutarate-dependent oxygenases that are most closely linked to the HIF prolyl (PHD) and asparginyl hydroxylases (FIH) both contain members that also target elongation factors (EF-Tu), release factors (ERF-1) and ribosomal proteins in addition to transcription factors. Known physiological oxygen-sensitive hydroxylations are indicated in red.