Controlling pericellular oxygen tension in cell culture reveals distinct breast cancer responses to low oxygen tensions

Abstract

Oxygen (O₂) tension plays a key role in tissue function and pathophysiology. O₂-controlled cell culture, in which the O₂ concentration in an incubator's gas phase is controlled, is an indispensable tool to study the role of O₂ in vivo. For this technique, it is presumed that the incubator setpoint is equal to the O₂ tension that cells experience (i.e., pericellular O₂). We discovered that physioxic (5% O₂) and hypoxic (1% O₂) setpoints regularly induce anoxic (0.0% O₂) pericellular tensions in both adherent and suspension cell cultures. Electron transport chain inhibition ablates this effect, indicating that cellular O₂ consumption is the driving factor. RNA-seq revealed that primary human hepatocytes cultured in physioxia experience ischemia-reperfusion injury due to anoxic exposure followed by rapid reoxygenation. To better understand the relationship between incubator gas phase and pericellular O₂ tensions, we developed a reaction-diffusion model that predicts pericellular O₂ tension a priori. This model revealed that the effect of cellular O₂ consumption is greatest in smaller volume culture vessels (e.g., 96-well plate). By controlling pericellular O₂ tension in cell culture, we discovered that MCF7 cells have stronger glycolytic and glutamine metabolism responses in anoxia vs. hypoxia. MCF7 also expressed higher levels of HIF2A, CD73, NDUFA4L2, etc. and lower levels of HIF1A, CA9, VEGFA, etc. in response to hypoxia vs. anoxia. Proteomics revealed that 4T1 cells had an upregulated epithelial-to-mesenchymal transition (EMT) response and downregulated reactive oxygen species (ROS) management, glycolysis, and fatty acid metabolism pathways in hypoxia vs. anoxia. Collectively, these results reveal that breast cancer cells respond non-monotonically to low O₂, suggesting that anoxic cell culture is not suitable to model hypoxia. We demonstrate that controlling atmospheric O₂ tension in cell culture incubators is insufficient to control O₂ in cell culture and introduce the concept of pericellular O₂-controlled cell culture.

Keywords: anoxia; breast cancer; cancer metabolism; cell culture; hypoxia; hypoxia-inducible factors; oxygen; physioxia.

Figure 1:. Cell culture parameters influence HIF stabilization kinetics in hypoxic (1% O₂) culture.

(A) O₂ kinetics (left) and time to 1% O₂ (right) of normoxic media (EMEM + 10% FBS + 1% P/S) placed in a 1% O₂ incubator. (B) O₂ kinetics (left) and time to 10% O₂ (right) of 1% O₂ media placed into different culture vessels under normoxia. (C) O₂ kinetics of MCF7 cultures with varying cell densities (left), medium volumes (middle), and culture vessel type (right) placed in a 1% O₂ incubator. (D) Time to 1% O₂ from (C). (E) Average fluorescence (Image-iT^™ Hypoxia) per cell (left) and representative confocal images at 4 hours (right) for MCF7 cultures (60mm dish) with 5 or 15 mL of media placed in a 1% O₂ chamber. Red = Image-iT^™ Hypoxia as an indicator of cellular hypoxia. (F) Percentage of GFP+ cells (left) and representative confocal images at 3 days (right) from MCF7 HIF reporter cells cultured at 7,000 or 29,000 cells/cm² for 4 days in a 1% O₂ incubator. Blue = nuclei stained with DAPI, Green = GFP+ (HIF+) cells. (G) Percentage of GFP+ cells (left), GFP mean fluorescence intensity (MFI) (middle) and representative contour plots with outliers (right) for MDA-MB-231 HIF reporter cells cultured in a 24-well plate or T25 flask for up to 5 days in a 1% O₂ incubator. Data were analyzed with ANOVA and Geisser-Greenhouse (E) or Bonferroni (F-G) corrections. N = 3 – 4 biological replicates per condition.

Figure 2:. Cellular O₂ consumption regularly induces anoxia (0.0% O₂) in both physioxic (5% O₂) and hypoxic (1% O₂) culture.

(A–B) O₂ profiles (left) and average O₂ tension values (right) of media, human mammary epithelial, MCF7, or MDA-MB-231 cultures seeded onto a 24-well plate in a 5% O₂ (A) or 1% O₂ (B) incubator for 72h. (C) O₂ profiles (left) and average O₂ tension values (right) of human dendritic cell (DC) 96-well cultures in a 5% or 1% O₂ incubator for 72h. (D) O₂ kinetics of media (green) or MDA-MBA-231 cultures (blue) of the top (dark) or bottom (light) of the well in a 1% O₂ incubator. (E) O₂ profiles of MDA-MB-231 cultures measured at the bottom of the well (spot) or 1mm above the bottom of the well (needle) in a 1% O₂ incubator. (F) Effect of sodium azide (NaN₃) on MCF7 pericellular O₂ tension and cytotoxicity. O₂ profiles (left) and average O₂ tension values (middle) of MCF7 cultures spiked with either 5 mM NaN₃ or PBS in a 1% O₂ incubator. MCF7 cell viability after ± incubation with 5 mM NaN₃ for 6 hours in a 1% O₂ incubator (right). (G) Average O₂ tension values of media and MCF7 cultures with different cell densities and culture vessel types in a 5% O₂ (left) or 1% O₂ incubator (right) for 72h. (H) Live, attached (left) and detached (right) cell counts for MCF7 cultures in a 18.6%, 5% or 1% O₂ incubator for 6 days. Data were analyzed with two-tailed t test (F) or ANOVA and Dunnett’s (A-B) or Tukey’s (C, F, G, H) corrections. N = 3 – 4 biological replicates per condition. Colored * indicates comparison to the control.

Figure 3:. Setting the incubator to physiological O₂ conditions mimics ischemia-reperfusion injury in human hepatocyte culture.

(A) Schematic of the primary human hepatocyte culture. RNA-seq was performed on uncultured hepatocytes and cells cultured in normoxic (18.6% O₂) or physioxic (6% O₂) incubator after 36h. (B–C) Average O₂ tension values (B) and detached cells per well (C) during each step of the culturing process. (D) Principal component analysis (PCA) of the RNA-seq results for normoxic and physioxic cultured hepatocytes. (E) Volcano plot indicating upregulated (blue) and downregulated (red) genes for physioxic vs. normoxic cultured hepatocytes (p_adj < 0.05 and |log₂FC| ≥ 1). (F) Hypoxia gene set enrichment analysis (GSEA) from the Hallmark database for normoxic vs. uncultured (left) and physioxic vs. uncultured (right). (G–I) Enriched pathways from the Gene Ontology (GO) database for physioxic vs. normoxic samples associated with oxidative stress (G), sterile inflammatory response (H) and mitochondrial and ribosomal biogenesis (I). Data were analyzed with ANOVA and Tukey’s correction (B-C). N = 3 biological samples per condition for RNA seq analysis.

Figure 4:. Developing a reaction-diffusion model to predict pericellular O₂ tension in cell cultures.

(A) Numerical (num) (dashed) and experimental (exp) (solid) O₂ kinetics of normoxic media (EMEM + 10% FBS + 1% P/S) in different culture vessels placed in a 1% O₂ incubator. (B) Diffusion model predictions for different volumes of normoxic media in a 6-well plate (left) or a 24-well plate (right) placed in a 1% O₂ incubator. (C) Numerical and experimental O₂ kinetics of MDA-MB-231 cultures seeded in a 24-well plate placed in a 1%, 4%, 6%, or 8% O₂ incubator for 48h. (D) Reaction-diffusion model predictions of the gradient within MDA-MB-231 cultures seeded in a 24-well plate in a 5% O₂ (left) or 1% O₂ (right) incubator. (E) Reaction-diffusion model predictions of MDA-MB-231 cells cultured at different cell densities and culture vessel types in a 5% O₂ incubator. N = 4 biological replicates per condition for experimental data.

Figure 5:. Pericellular anoxia induces stronger metabolic reprogramming and distinct transcriptional HIFA and HRE controlled gene responses compared to pericellular hypoxia in MCF7 cells.

(A) Average pericellular O₂ tensions in MCF7 cultures placed in 18.6%, 4.5%, and 1% O₂ incubators for 72 hours. (B–E) Extracellular concentrations of glucose (B), glutamine (C), lactate (D), and glutamate (E) in different O₂ tensions for 72 hours. Normalized metabolite concentrations over time (left) and metabolite consumption or production rates for 72 hours (right). (F–I) Gene expression levels of genes associated with the hypoxic response (F), metabolic reprogramming (G), autophagy (H), and immunosuppression (I) in different O₂ tensions for 72 hours. Data were analyzed using ANOVA with Tukey’s correction. N = 4 biological samples per condition. Color code for asterix (*): Red colored * indicate comparison to control (normoxia) and blue colored * indicate comparison between hypoxia and anoxia.

Figure 6:. Proteomic characterization of pericellular hypoxic and anoxic metabolic reprogramming in 4T1 cells.

(A) Protein set enrichment analysis (PSEA) using the Hallmark database of mRNA processing and protein translation pathways for Hypoxia (H) vs. Normoxia (N), Anoxia (A) vs. Normoxia, and Hypoxia vs. Anoxia. (B) PSEA using the Hallmark database of hypoxic response pathways (left). Heat maps of selected proteins in Hallmark hypoxia, epithelial to mesenchymal transition (EMT), and reactive O₂ species (ROS) pathways (right) (Hypoxia vs. Anoxia). (C) Heat map of glycolytic and hypoxic response proteins. (D) PSEA using Reactome database for fatty acid (FA) metabolism pathways for Hypoxia vs. Anoxia (top). Heat maps of selected proteins in fatty acid β-oxidation and synthesis Reactome pathways (bottom). (E) Heat maps of selected proteins from Tricarboxylic acid (TCA) cycle and electron transport chain (ETC) processes for Hypoxia vs. Normoxia and Anoxia vs. Normoxia. PSEA using the Reactome database of TCA and ETC pathways for Hypoxia vs. Normoxia, Anoxia vs. Normoxia (left), and Hypoxia vs. Anoxia (right). NES = normalized enrichment score. N = 3 biological replicates and N = 2–3 technical replicates per condition.