Proline metabolism supports metastasis formation and could be inhibited to selectively target metastasizing cancer cells

Abstract

Metastases are the leading cause of mortality in patients with cancer. Metastasis formation requires cancer cells to adapt their cellular phenotype. However, how metabolism supports this adaptation of cancer cells is poorly defined. We use 2D versus 3D cultivation to induce a shift in the cellular phenotype of breast cancer cells. We discover that proline catabolism via proline dehydrogenase (Prodh) supports growth of breast cancer cells in 3D culture. Subsequently, we link proline catabolism to in vivo metastasis formation. In particular, we find that PRODH expression and proline catabolism is increased in metastases compared to primary breast cancers of patients and mice. Moreover, inhibiting Prodh is sufficient to impair formation of lung metastases in the orthotopic 4T1 and EMT6.5 mouse models, without adverse effects on healthy tissue and organ function. In conclusion, we discover that Prodh is a potential drug target for inhibiting metastasis formation.

Figure 1. Proline catabolism distinguishes 3D from 2D growth.

(a) Total contribution of ¹³C₆-glucose and ¹³C₅-glutamine to different organic acids and amino acids in MCF10A H-Ras^V12 spheroids (3D) versus attached cells (2D). Changes in total contribution >25% with a P value≤0.05 are depicted. (b) Proline labelling from ¹³C₆-glucose and ¹³C₅-glutamine in MCF10A H-Ras^V12 spheroids (3D) versus attached cells (2D). (c) Proline uptake in MCF10A H-Ras^V12 spheroids (3D) versus attached cells (2D). (d) Intracellular levels of proline in MCF10A H-Ras^V12 spheroids (3D) versus attached cells (2D). (e) Relative expression of proline catabolism (PRODH and P5CDH) and biosynthesis (P5CS and PYCR1) genes in MCF10A H-Ras^V12 spheroids (3D) versus attached cells (2D) measured by qRT–PCR. The number of biological replicates for each experiment was n≥3. All error bars represent s.d. Two-tailed unpaired Student's T-test was performed. *P≤0.05; **P≤0.01.

Figure 2. Proline catabolism via Prodh supports 3D growth.

(a) Representative pictures and size quantification of MCF10A H-Ras^V12 spheroids transduced with an inducible lentiviral CRISPR with or without guide for PRODH. CRISPR expression was induced with 0.1 μg ml⁻¹ doxycycline. Analysis was performed 5 days after PRODH knockdown (KD) induction. (b) Representative pictures and size quantification of MCF10A H-Ras^V12 spheroids with or without L-THFA treatment. Treatment was started at day 0. Analysis was performed at day 5 of treatment. Scale bar: 150 μm. The number of biological replicates for each experiment was n≥3. All error bars represent s.d. Two-tailed unpaired Student's T-test was performed. **P≤0.01; ***P≤0.001.

Figure 3. Prodh activity depends on P5C recycling via Pycr1.

(a) Representative pictures and size quantification of MCF10A H-Ras^V12 spheroids in complete media and media without proline. Analysis was performed at day 5. Scale bar: 150 μm. (b) NADPH to NADP⁺ ratio in MCF10A H-Ras^V12 spheroids (3D) versus attached (2D) cells. (c) Representative pictures of MCF10A H-Ras^V12 spheroids transduced with a lentiviral vector with shRNA for either PYCR1 or a scrambled sequence. Analysis was performed at day 5. Scale bar: 150 μm. (d) Protein content in MCF10A H-Ras^V12 spheroids transduced with a lentiviral vector with shRNA for either PYCR1 (KD) or a scrambled sequence. Analysis was performed at day 5. (e) Intracellular levels of proline in MCF10A H-Ras^V12 spheroids transduced with a lentiviral vector with shRNA for either PYCR1 (KD) or scrambled sequence. Analysis was performed at day 5. Total ion counts were normalized for protein content. The number of biological replicates for each experiment was n≥3. All error bars represent s.d. Two-tailed unpaired Student's T-test was performed. *P≤0.05.

Figure 4. Prodh activity generates ATP during 3D growth.

(a) Time-resolved ATP levels of MCF10A H-Ras^V12 spheroids upon treatment with the Prodh inhibitor L-THFA. (b) Schematic representation of Rotenone and Antimycin A mode of action as well as ATP generation from proline catabolism. (c) Representative pictures of MCF10A H-Ras^V12 spheroids upon treatment with either rotenone or antimycin A. Treatment was started at day 0. Analysis was performed at day 5 of treatment. Scale bar: 150 μm. The number of biological replicates for each experiment was n≥3. All error bars represent s.d. Two-tailed unpaired Student's T-test was performed. *P≤0.05.

Figure 5. Prodh activity is specifically relevant in transformed cells.

(a) Relative expression of PRODH in HCC70, MCF7, 4T1 and MDA-MB-231 spheroids (3D) versus the corresponding attached (2D) cells. (b) Proline uptake of 4T1 and EMT6.5 spheroids versus attached cells and representative pictures of 4T1 and EMT6.5 spheroids with or without L-THFA treatment. Treatment was started at day 0. Analysis was performed 5 days after treatment. Scale bar: 150 μm (4T1 spheroids) and 75 μm (EMT6.5 spheroids). (c) Relative expression of PRODH in MCF10A H-Ras^V12 spheroids compared to MCF10A acini. (d) Relative ATP levels of MCF10A H-Ras^V12 spheroids compared to MCF10A acini. (e) Representative pictures of MCF10A acini with or without L-THFA treatment. Treatment was started at day 0. Analysis was performed 5 days after treatment. Scale bar: 150 μm. (f) Time-resolved ATP levels of MCF10A acini upon treatment with the Prodh inhibitor L-THFA. (g) Representative pictures of MCF10A acini upon treatment with either Rotenone or Antimycin A. Treatment was started at day 0. Analysis was performed 5 days after treatment. Scale bar: 150 μm. To each experiment, 0.5% Matrigel was added to the media of both cell lines to allow acini formation of non-transformed MCF10A cells and to enable the comparison between MCF10A H-Ras^V12 and MCF10A cells. The number of biological replicates for each experiment was n≥3. All error bars represent s.d. Two-tailed unpaired Student's T-test was performed. *P≤0.05; **P≤0.01; ***P≤0.001.

Figure 6. Prodh activity is specifically relevant in metastasis tissue.

(a) PRODH expression levels in primary breast cancer (BC) tissue (GSE20711) and breast cancer-derived metastases (DM) tissue (GSE14017) from patients. Data are shown as medians (bar) with the 25th–75th percentile range (box) and the 10th–90th percentile range (whiskers). Two-tailed unpaired Student's T-test with Welch's correction was performed. **P≤0.01. (b) Proline labelling from ¹³C₆-glucose in primary breast cancers (BC) and the resulting lung metastases (LM) of BALB/c mice orthotopically injected with murine 4T1 breast cancer cells. Four mice with primary BC and resulting LM (n=7) were analysed. Two-tailed Student's T-test with F-testing to confirm equal variance was performed. **P≤0.01. (c) Intracellular proline levels in primary breast cancers (BC) and the resulting lung metastases (LM) of BALB/c mice orthotopically injected with murine 4T1 breast cancer cells and treated with either L-THFA or vehicle normalized to the respective control condition. For the vehicle-treated group, n=8 mice with primary BC and resulting LM (n=11) were analysed. For the L-THFA-treated group, n=5 mice with primary breast cancer and resulting LM (n=5) were analysed. Two-tailed Student's T-test with F-testing to confirm equal variance was performed. **P≤0.01. (d) Relative metabolite levels of MCF10A H-Ras^V12 spheroids treated with or without L-THFA. Two-tailed unpaired Student's T-test was performed. *P≤0.05. (e) Relative metabolite levels of the heart, liver and brain of mice treated with different doses of L-THFA compared to vehicle (PBS). Changes in metabolite levels >27% are depicted (n≥5). Two-tailed Student's T-test with F-testing to confirm equal variance was performed. Error bars represent s.d. unless otherwise noted.

Figure 7. Prodh inhibition impairs lung metastases formation.

(a) Primary tumour weight, (b) the number of surface lung metastases and (c) representative pictures of ink-stained lungs with white tissue indicating metastases of BALB/c mice orthotopically injected with murine 4T1 breast cancer cells treated with vehicle or L-THFA at different concentrations for 16 days: 0 mg kg⁻¹ (n=36, 4 independent cohorts), 7.5 mg kg⁻¹ (n=9), 15 mg kg⁻¹ (n=8), and 30 mg kg⁻¹ (n=21, 3 independent cohorts). Treatment was started after primary breast tumours were formed. Scale bar: 0.5 cm. Two-tailed unpaired Student's T-test with Welch's correction was performed. **P≤0.01; ***P≤0.001. (d) Number of lung metastases per lung section and (e) representative pictures of H&E-stained lung sections of BALB/c mice orthotopically injected with murine 4T1 breast cancer cells treated with vehicle or L-THFA at 30 mg kg⁻¹ (n=5 per condition). Scale bar: 2.7 mm. Two-tailed Student's T-test with F-testing to confirm equal variance was performed. *P≤0.05. (f) Primary tumour weight, (g) the number of surface lung metastases and (h) representative pictures of ink-stained lungs (black) with metastases (white) of BALB/c mice orthotopically injected with murine EMT6.5 breast cancer cells treated with vehicle (n=9) or L-THFA at 15 mg kg⁻¹ (n=8) for 18 days. Scale bar: 0.5 cm. Two-tailed Student's T-test with F-testing to confirm equal variance was performed. *P≤0.05. All error bars represent s.e.m.