Reduced levels of IGF-I mediate differential protection of normal and cancer cells in response to fasting and improve chemotherapeutic index

Abstract

Inhibitors of the insulin-like growth factor-I (IGF-I) receptor have been widely studied for their ability to enhance the killing of a variety of malignant cells, but whether IGF-I signaling differentially protects the host and cancer cells against chemotherapy is unknown. Starvation can protect mice, but not cancer cells, against high-dose chemotherapy [differential stress resistance (DSR)]. Here, we offer evidence that IGF-I reduction mediates part of the starvation-dependent DSR. A 72-hour fast in mice reduced circulating IGF-I by 70% and increased the level of the IGF-I inhibitor IGFBP-1 by 11-fold. LID mice, with a 70% to 80% reduction in circulating IGF-I levels, were protected against three of four chemotherapy drugs tested. Restoration of IGF-I was sufficient to reverse the protective effect of fasting. Sixty percent of melanoma-bearing LID mice treated with doxorubicin achieved long-term survival whereas all control mice died of either metastases or chemotherapy toxicity. Reducing IGF-I/IGF-I signaling protected primary glia, but not glioma cells, against cyclophosphamide and protected mouse embryonic fibroblasts against doxorubicin. Further, S. cerevisiae lacking homologs of IGF-I signaling proteins were protected against chemotherapy-dependent DNA damage in a manner that could be reversed by expressing a constitutively active form of Ras. We conclude that normal cells and mice can be protected against chemotherapy-dependent damage by reducing circulating IGF-I levels and by a mechanism that involves downregulation of proto-oncogene signals.

Figure 1

The effect of 72 hour fasting on glucose levels, IGF-I, and IGFBP-1/3. 30 week old CD-1 mice were fasted for 72 hours and sacrificed. Blood was collected via cardiac puncture under anesthesia, and blood glucose was measured immediately. Plasma IGF-1 and IGFBP-1/3 levels were measured by a mouse-specific in-house ELISA. All P values were calculated by Student’s t-test except for IGFBP-1 which was done by the Mann-Whitney U test.

Figure 2

in vitro DSR to CP treatments by reducing IGF-I. Primary rat glial cells and rat glioma cell lines (C6, 9L, and A10–85) cell lines were tested. (A) Cells were pre-incubated in DMEM/F12 with 1% serum and neutralizing anti-IGF-IR monoclonal antibody alpha-IR3 (1 ug/ml) for 24 hours (15 mg/ml; n=12). (B) Cells were pre-incubated in medium with either 1% (STS) or 10% FBS for 24 hours (15 mg/ml; n=12). (C) Cells were pre-incubated in medium with 1% serum with or without rhIGF-I (100ng/ml) for 48 hours (12 mg/ml; n=21). (D) The effect of IGF-I on DSR against oxidative stress. Chemotherapy drugs such as etoposide, cyclophosphamide, 5-fluorouracil, and DXR have been shown to increase reactive oxygen species (ROS) and cause oxidative stress. Primary neurons and PC12 pheochromocytoma cells were pre-treated with IGF-I (100ng/ml) for 30 minutes, followed by paraquat treatments for 24 hours. Cytotoxicity (LDH assay) was determined following treatment. * P <0.05, ** P <0.005, *** P<0.0001 by Student’s t test.

Figure 3

R⁺ and R⁻ cells were grown to confluence and treated with DXR (0–500μM) in DMEM/F12 supplemented with 10% FBS for (A) 24 hours or (B) 48 hours. Viability was determined by the relative degree of MTT reduction compared to untreated; mean ± SD. * P <0.05, ** P <0.01, *** P <0.001 by Student’s t test; R⁺ vs. R⁻ cells at same DXR concentration. (C) Comet assay. Cells overexpressing IGF-IR or with IGF-IR deficiency (R⁺ and R⁻) were treated with 50μM DXR for 1 hour. Significant DNA damage was observed in the DXR treated R+ cells, whereas R− cells showed enhanced protection against DXR induced DNA damage. (D) Tail olive moment analysis of the comet assay. *** P <0.001 by Student’s t test; R⁺ DXR vs. R⁻ DXR. Similar results were obtained from two independent experiments. Representative experiment is shown.

Figure 4

Stress resistance testing in LID mice with various high-dose chemotherapeutic drugs. LID and control mice received (A) a single injection of 100 mg/kg etoposide (n=10/LID, n=9/control, P=0.064), (B) a single injection of 500 mg/kg CP (n=20/group, P=0.001), (C) a single injection of 400 mg/kg 5-fluorouracil (n=11/LID, n=10/control, P=0.148), (D) two injections of doxorubicin (DXR). The first injection of 20 mg/kg was given on day 0, and the second injection of 28 mg/kg was given on day 22 (n=5/LID, n=4/control, P=0.022). Toxicity evaluated by percent survival is shown. P values by Peto’s log rank test.

Figure 5

Differential stress resistance (DSR) against 2 cycles of high-dose DXR in melanoma bearing LID mice. (A) Timeline of experimental procedures (n=4/LID-B16, n=5/LID-B16-DXR, n=8/Control-B16, n=7/Control-B16-DXR). (B) Bioluminesence imaging of B16Fluc melanoma bearing LID mice and control mice treated with 2 cycles of high-dose DXR. Five mice were randomly selected and followed throughout the experiment to monitor tumor progression or regression. (C) Survival rate comparison between B16Fluc melanoma bearing LID and control mice treated with 2 cycles of high-dose DXR (P <0.05). (D) DXR induced cardiomyopathy in control and LID mice. Heart failure is a major outcome of acute DXR toxicity. Histological slides of the heart from DXR treated control mice showed loss of myofibrils and infiltration of immune cells, whereas DXR dependent cardiac myopathy was not observed in LID mice. Hematoxylin and eosin staining (H&E). Representative slide shown. Bar, 100μm.