Aerobic Glycolysis Controls Myeloid-Derived Suppressor Cells and Tumor Immunity via a Specific CEBPB Isoform in Triple-Negative Breast Cancer

Abstract

Myeloid-derived suppressor cells (MDSCs) inhibit anti-tumor immunity. Aerobic glycolysis is a hallmark of cancer. However, the link between MDSCs and glycolysis is unknown in patients with triple-negative breast cancer (TNBC). Here, we detect abundant glycolytic activities in human TNBC. In two TNBC mouse models, 4T1 and Py8119, glycolysis restriction inhibits tumor granulocyte colony-stimulating factor (G-CSF) and granulocyte macrophage colony-stimulating factor (GM-CSF) expression and reduces MDSCs. These are accompanied with enhanced T cell immunity, reduced tumor growth and metastasis, and prolonged mouse survival. Mechanistically, glycolysis restriction represses the expression of a specific CCAAT/enhancer-binding protein beta (CEBPB) isoform, liver-enriched activator protein (LAP), via the AMP-activated protein kinase (AMPK)-ULK1 and autophagy pathways, whereas LAP controls G-CSF and GM-CSF expression to support MDSC development. Glycolytic signatures that include lactate dehydrogenase A correlate with high MDSCs and low T cells, and are associated with poor human TNBC outcome. Collectively, tumor glycolysis orchestrates a molecular network of the AMPK-ULK1, autophagy, and CEBPB pathways to affect MDSCs and maintain tumor immunosuppression.

Keywords: CEBPB; G-CSF; GM-CSF; LDHA; autophagy; breast cancer; glycolysis; immunotherapy; myeloid-derived suppressor cell; tumor immunity.

Figure 1.. Glycolysis Regulates Tumor G-CSF and GM-CSF Expression

(A–E) Correlations between G-CSF and glycolysis enzymes. Expression of lactate dehydrogenase A (LDHA) (A), hexokinase-1 (HK1) (B), glucose-6-phosphate isomerase (GPI) (C), pyruvate kinase muscle isozyme 2 (PKM2) (D), and phosphofructokinase muscle subunit gene (PFKM) (E) was analyzed based on the dataset containing 250 TNBC patients. Gene expression was normalized to β-actin. Pearson’s correlation was calculated. (F–I) Effect of 2-DG on tumor G-CSF expression. 4T1 (F and H) and Py8119 (G and I) cells were treated with 5 mM 2-DG for 12 hr. G-CSF transcript was quantified by real-time PCR (F and G) and G-CSF protein was measured in culture supernatant with ELISA (H and I) (n = 3/group, one of three experiments is shown, *p < 0.001). (J and K) Effect of shLDHAs on tumor LDHA expression. Immunoblot analysis of LDHA knockdown (KD) by shLDHAs (shLDHA1 and shLDHA2) in 4T1 cells (J) and Py8119 cells (K). Scramble shRNA (Scr) was used as control. One of three experiments is shown. (L–O) Effect of shLDHAs on tumor G-CSF expression. Scramble and shLDHA-expressing 4T1 and Py8119 cells were cultured for 24 and 48 hr, respectively. G-CSF transcript was quantified by real-time PCR (L and M) and G-CSF protein was measured in culture supernatant with ELISA (N and O) (n = 3/group, one of three experiments is shown, *p < 0.003). Data represent mean ± SEM. (P) Immunofluorescence staining. Scramble and LDHA KD 4T1 cells were cultured for 48 hr and were stained with primary antibody anti-G-CSF and secondary antibody conjugated with Alexa Fluor 594. Scale bar, 20 μm. One of three experiments is shown.

Figure 2.. Glycolysis Targets CEBPB Isoform LAP to Control G-CSF Expression

(A and B) Effect of shCEBPB on tumor G-CSF expression. Scramble and shCEBPB (shCEBPB1 and shCEBPB2)-infected 4T1 cells were cultured for 24 hr. G-CSF transcript was quantified by real-time PCR (A) and G-CSF protein was measured in culture supernatant with ELISA (B) (n = 3/group, one of three experiments is shown, *p < 0.003). (C) 4T1 and Py8119 cells were treated with 2-DG (10 mM) for different times. Tumor CEBPB isoforms were detected by western blotting. One of three experiments is shown. (D) CEBPB isoforms were detected by western blotting in whole-cell lysis of scramble and shLDHA-expressing 4T1 and Py8119 cells. One of three experiments is shown. (E) 4T1 cells were transfected with plasmid vectors expressing CEBPB isoforms LAP*, LAP* mutant, and LAP. Expression of LAP*, LAP* mutant, and LAP was detected by western blotting. One of three experiments is shown. (F and G) 4T1 cells were transfected with the plasmid vectors expressing LAP*, LAP* mutant, and LAP. G-CSF transcript was quantified by real-time PCR (F) and G-CSF protein was measured in culture supernatant with ELISA (G) (n = 3/group, one of three experiments is shown, *p < 0.001). (H and I) LDHA KD 4T1 cells were transfected with plasmid vectors expressing LAP. G-CSF transcript was quantified by real-time PCR (H) and G-CSF protein was measured in culture supernatant with ELISA (I) (n = 3/group, one of three experiments is shown, *p < 0.001). (J) LAP was knocked out in 4T1 cells (LAP KO) and LAP KO cells were infected with LAP overexpressing (LAP OE) lentivirus. LAP protein was detected by western blot. One of three experiments is shown. Data represent mean ± SEM. (K–M) Role of LAP in G-CSF expression. G-CSF transcript was quantified by real-time PCR (K). G-CSF protein was measured in culture supernatant with ELISA (L) (n = 3/group, *p < 0.001). (M) Intracellular G-CSF was stained with anti-G-CSF, revealed with Alexa Fluor 594-conjugated secondary antibody, and detected by fluorescence microscope. Scale bar, 20 μm. One of three experiments is shown.

Figure 3.. Glycolysis Targets LAP via the AMPK-ULK1 Pathway

(A) 4T1 and Py8119 cells were treated with 2-DG (20 mM) for 1 hr. AMPK and ULK1 were detected by western blotting. One of three experiments is shown. (B) Immunoblot analysis of AMPK, p-AMPK, ULK1, and p-ULK1 in whole-cell lysis of scramble and shLDHA1-expressing 4T1 and Py8119 cells. One of three experiments is shown. (C) LDHA KD 4T1 cells were treated with dorsomorphin for 1 hr. AMPK and AMPK phosphorylation were detected by western blotting. One of three experiments is shown. (D) Scramble and shLDHA-expressing 4T1 cells were treated with dorsomorphin for 24 hr. LAP* and LAP were detected by western blotting. One of three experiments is shown. (E) Scramble and shLDHA-expressing 4T1 cells were treated with dorsomorphin for 24 hr. G-CSF transcripts were quantified by real-time PCR (n = 3/group, one of three experiments is shown, *p < 0.001). (F) Scramble and shLDHA-expressing 4T1 and Py8119 cells were transfected with siULK and control for 12 hr. Cells were cultured for an additional 24 hr. LAP* and LAP were detected by western blotting. One of three experiments is shown. (G–J) Scramble and shLDHA-expressing 4T1 and Py8119 cells were transfected with siULK and control for 12–24 hr. Cells were cultured for an additional 48 hr. G-CSF transcripts and proteins were detected by real-time PCR (G and H) and ELISA (I and J), respectively (n = 3/group, one of three experiments is shown, * p < 0.001). Data represent mean ± SEM.

Figure 4.. Glycolysis Controls LAP Expression via Autophagy Activation

(A) 4T1 and Py8119 cells were treated with 2-DG (5 mM) for 12 hr. LC3b-I and LC3b-II were detected by western blotting. One of three experiments is shown. (B) Scramble and shLDHA-expressing 4T1 and Py8119 cells were cultured for 24 hr. LC3b-I and LC3b-II were detected by western blotting. One of three experiments is shown. (C and D) Scramble and shLDHA-expressing 4T1 cells were treated with and without chloroquine (CQ). Autophagy puncta were revealed with anti-LC3b monoclonal antibody staining and were analyzed with fluorescence microscope (C). Results were shown as the percentage of puncta-positive cells ± SEM (D) (n = 6/group, one of three experiments is shown, *p < 0.0001). Scale bar, 25 μm. (E) Scramble and shLDHA-expressing 4T1 cells were treated with CQ for 24 hr. LAP* and LAP were detected by western blotting. One of three experiments is shown. (F) Scramble and shLDHA-expressing 4T1 cells were treated with CQ for 24 hr. G-CSF transcript was detected by real-time PCR (n = 3/group, one of three experiments, *p < 0.0001). (G) Scramble and shLDHA-expressing 4T1 and Py8119 cells were transfected with FIP200 siRNA for 36 hr. CEBPB isoforms were detected by western blotting. One of three experiments is shown. (H–K) Scramble and shLDHA-expressing 4T1 and Py8119 cells were transfected with FIP200 siRNA for 12–24 hr. Cells were cultured for 48 hr. G-CSF transcripts and proteins were detected by real-time PCR (H and I) and ELISA (J and K), respectively (n = 3/group, one of three experiments is shown, *p < 0.0001). Data represent mean ± SEM.

Figure 5.. Tumor LDHA Affects MDSCs to Control Tumor Immunity

(A–D) Effect of shLDHA on tumor growth (A), metastasis (B and C), and mouse survival (D). Scramble and LDHA KD 4T1 cells (2.5 × 10⁴) were inoculated into female BALB/c mice. (A) Tumor growth was monitored and tumor size was measured (n = 10/group, *p < 0.001). Bioluminescence detection showed the distant 4T1 metastasis (B) and metastatic rate (C) on 30 days (n = 7/group, one of two experiments is shown). (E–G) Gr1⁺CD11b⁺ cells in tumor-bearing mice. (E) Representative flow cytometry dot plots showed spleen and tumor tissue Gr1⁺CD11b⁺CD45⁺ cells in mice bearing scramble and LDHA KD 4T1 tumors. (F and G) Percentages of Gr1⁺CD11b⁺ cells were shown in spleen (F) and tumor tissues (G) (n = 6/group, one of two experiments is shown, *p < 0.05). (H and I) Representative flow cytometry dot plots (H) and the percentages of TNF-α and IFN-γ (I) were shown in CD8⁺ T cells in 4T1 tumor tissue (n = 5–6/group, one of two experiments is shown, *p < 0.05). (J and K) Representative flow cytometry dot plots (J) and the percentages of TNF-α and IFN-γ (K) were shown in CD8⁺ T cells in 4T1 tumor draining lymph nodes (TDLNs) (n = 5–6/group, one of two experiments is shown, *p < 0.05). (L and M) Effect of CD4 and CD8 T cell depletion on 4T1 tumor growth. (L) Representative flow cytometry dot plots showed T cell depletion efficiency. (M) Tumor volume was shown in different groups (n = 5/group, one of two experiments is shown, *p < 0.05). Data represent mean ± SEM.

Figure 6.. Tumor LDHA Regulates Tumor Immunity via G-CSF

(A) Effect of forced G-CSF overexpression (G-CSF OE) on tumor growth. 4T1 cells (0.5 × 10⁵/mouse) were inoculated into female BALB/c mice. Tumor size was measured every 2 days (n = 5/group, one of two experiments is shown, *p < 0.05). (B) Effect of G-CSF OE on MDSCs. Ly6G⁺CD11b⁺ cells were analyzed by flow cytometry in CD45⁺ cells in tumor-bearing mice. The percentages of Ly6G⁺CD11b⁺ cells were shown in spleen and tumor (n = 5/group, one of two experiments is shown, *p < 0.01). (C and D) Effect of G-CSF OE on CD8⁺ T cell profile. The percentages of IFN-γ⁺ and TNF-α⁺ in CD8⁺ T cells in tumor tissue (C) and TDLN (D) were shown (n = 5/group, one of two experiments is shown, *p < 0.05). (E) Effect of G-CSF knockout (G-CSF KO) on tumor growth. 4T1 cells (0.5 3 10⁵/mouse) were inoculated into female BALB/c mice. Tumor size was measured every 2 days (n = 6–7/group, one of two experiments is shown, *p < 0.05). (F) Effect of G-CSF KO on MDSCs. Ly6G⁺CD11b⁺ cells were analyzed by flow cytometry in CD45⁺ cells in tumor-bearing mice. The percentages of Ly6G⁺CD11b⁺ cells were shown in spleen and tumor (n = 6–7/group, one of two experiments is shown, *p < 0.01). (G and H) Effect of G-CSF KO on CD8⁺ T cell profile. The percentages of IFN-γ⁺ and TNF-α⁺ in CD8⁺ T cells in tumor tissue (G) and TDLN (H) were shown (n = 6–7/group, one of two experiments is shown, *p < 0.05). (I) Effect of LAP knockout (LAP KO) on tumor growth. 4T1 cells (0.5 3 10⁵/mouse) were inoculated into female BALB/c mice. Tumor size was measured every 2 days (n = 8–9/group, one of two experiments is shown, *p < 0.05). (J) Effect of forced LAP KO on MDSCs. Ly6G⁺CD11b⁺ cells were analyzed by flow cytometry in CD45⁺ cells in tumor-bearing mice. The percentages of Ly6G⁺CD11b⁺ cells were shown in spleen and tumor tissues (n = 8–9/group, one of two experiments is shown, *p < 0.01). (K and L) Effect of LAP KO on CD8⁺ T cell profile. The percentages of IFN-γ⁺ and TNF-α⁺ in CD8⁺ T cells in tumor tissues (K) and TDLN (L) were shown (n = 8–9/group, one of two experiments is shown, *p < 0.05). Data represent mean ± SEM.

Figure 7.. Glycolysis, MDSCs, and T Cell Response Correlate in TNBC Patients

(A–D) Correlation between LDHA and protective immune signature in human TNBC. Glycolytic (A) and immune cell (B–D) gene signatures were analyzed and compared between high and low LDHA-expressing TNBCs (EGAS00000000083, n = 250). The normalized enrichment score (NES) (green line) reflects the degree to which the gene set is over-represented at the top or bottom of the ranked list of genes. A positive value indicates more correlation with “high LDHA-expressing tumor,” and a negative value indicates more correlation with “low LDHA-expressing tumor.” (E) GSEA comparison between patients with high LDHA expression (red) and low LDHA expression (blue). Median split, n = 250 (EGAS00000000083). Cytoscape and Enrichment map were used for visualization of the GSEA results (p value cutoff: 0.05). Enrichment results were mapped as a network of gene sets. Nodes represent enriched gene sets, which were grouped by their similarities according to the related gene sets. Node size was proportional to the total number of genes within each gene set. Proportion of shared genes between gene sets was presented as the thickness of the green lines between nodes. (F–I) Estimates of signature correlation among MDSC, glycolysis, and T cell immune response. Signature scores were calculated as reported previously (Welte et al., 2016). The correlations were evaluated by Person’ correlation test controlled by cohort (EGAS00000000083 and GEO: GSE58812, n = 357). (J–M) Kaplan-Meier estimates of overall survival in TNBC patients. Patients were divided into low and high groups based on the median of LDHA expression (J), glycolysis signature score (K), MDSC signature score (L), and T cell metagene signature score (M); p values were calculated using the log-rank test controlled by cohort (EGAS00000000083 and GEO: GSE58812, n = 357).