Mice with germline-deleted MIC-1/GDF15 (MIC-1^−/−) was generated by Ozgene (Ozgene Pty Ltd., Bentley DC, WA Australia). These mice have a complete deletion of the second of two exons of the MIC-1/GDF15 gene. This effectively deleted the poly A tract and amino acids 94–302 of MIC-1/GDF15, including all of the mature bioactive domain and most of the propeptide region. The founder mice were bred for more than 10 generations onto a C57BL/6 background.

All MIC-1/GDF15 antibodies and recombinant protein were prepared as previously described [17]. Briefly, recombinant human MIC-1/GDF15 was expressed and purified to homogeneity from conditioned medium of the yeast Pichia pastoris that is free from LPS. The monoclonal antibody against human MIC1/GDF15 (mAb-26) was purified by protein G affinity chromatography.

Indirect calorimetry was performed in age matched mice at 12–16 weeks of age using an eight-chamber open-circuit calorimeter (Oxymax Series; Columbus Instruments, Columbus, OH, USA). Mice were weighed and singly housed in Plexiglass cages (20.1×10.1×12.7 cm) and were left to acclimatized for 24 h before commencement of 48 h-recordings. Oxygen consumption (Vo₂) and carbon dioxide (Vco₂) were measured every 15 min. The respiratory exchange ratio (RER) was calculated as the quotient of Vco₂/Vo₂, with an RER of 1 indicating 100% carbohydrate oxidation and an RER of 0.7 indicating 100% fat oxidation [18]. Energy expenditure was measured as production of kcal of heat and was calculated as Calorific Value (CV) × Vo₂, where CV is 3.815+1.232 × RER [19]. Data for the 24-h monitoring period was averaged for 1-h intervals for RER and energy expenditure (kcal/h). Ambulatory activity was recorded with an OPTO-M3 infrared beam sensor system (Columbus Instruments, Columbus, OH). The senor beams were aligned on both x and y-axes directions. Data was collected at 1 min intervals at the same time as the indirect calorimetry measurements. The recording of ambulatory activity (locomotion) only counts the broken beam when a consecutive adjacent beam is broken, and does not include the same beam being broken repeatedly [20]. The total counts of x and y-axes for every 1-h interval from individual mouse were used for analysis of ambulatory activity.

Whole body fat mass and lean mass were measured in MIC-1^−/− and control mice at 12–14 weeks of age. Animals were subjected to dual-energy X-ray absorptiometry (DXA; PIXImus2 mouse densitometer; GE Health-care, Waukesha, WI) after anesthetized with isoflurane. The head and the tail were excluded from all the measurements.

Upon completion of metabolic and body composition measurements, mice at 14–16 weeks of age were sacrificed by cervical dislocation. Muscles (gastrocnemius and tibialis), whole interscapular brown adipose tissue, as well as white adipose tissue depots (inguinal, epididymal, mesenteric and retroperitoneal) were collected and weighed. Total white adipose tissue (WATt) mass is defined as the sum of the mass of these four WAT depots.

Recombinant human MIC-1/GDF15 was reconstituted in 4 mM HCl and loaded into a 7-day-Mini-osmotic pump (model 1007D, ALZET Osmotic pump, Cupertino, CA) to deliver 1 ug/24 h/20 gBW at delivery rate of 0.5 ul/h. MIC-1/GDF15 or vehicle-loaded pumps were implanted subcutaneously in the interscapular region of 10–14 week-old MIC-1^−/− or MIC-1^+/+ mice. Briefly, animals were anesthetized by inhalation of isoflurane then shaved and disinfected over the implantation site. A small incision was made across the midline and slightly posterior to the scapula, then a hemostat was used for blunt dissection into the subcutaneous space to create a space for the pump, which was inserted with the delivery portal oriented caudally. The wound was closed with two 9 mm wound clips. Mice were sacrificed at either day 5 or 6 after implantation for blood collection.

Mice were transferred from group house on soft bedding to individual cages with paper-towel and allowed to acclimatize for three days before commencement of food intake measurements. Body weight, food spillage on the bedding and food in the food hopper were weighed at between 9∶00 and 10∶00 h. Food consumption was calculated using the weight of food pellets left in the hopper as well as the weight of food (minus feces) spilled on the bedding [9].

Mice were sacrificed at day 6 after implantation of osmotic minipump. Blood samples were collected by cardiac puncture and allowed to clot by standing for 2 hour at 4°C. After centrifugation, the collected sera were stored at −70°C for assay of human MIC-1/GDF15 by a previously described, in house ELISA [21], [22].

The difference in body weight between the MIC-1^−/− and MIC-1^+/+ animal over 52 weeks were average of 12 animals in each group for each age. Comparison of energy expenditure between genotypes were performed first by determining the equality of variance between the group with Levene’s test followed by ANCOVA with lean body mass as covariate, which also tested the homogeneity of regression line slopes between the groups (SPSS version 20, Chicago, IL). All data for energy expenditure were readjusted at a common lean mass generated by ANOVA and subsequent comparison between the groups was performed using repeated-measure ANOVA or t-test. RER and physical activity collected over 24-h were averaged for the whole 24-h period, as well as for the light and dark phase, comparison between genotypes within the same sex or between difference treatments were performed using an repeated measures ANOVA and unpaired-two-tailed t-test or with when values over different times were analyzed. These analyses were performed using GraphPad Prism (PRISM 4, GraphPad, San Diago, CA). Equation of Power analysis was used for determining animal number required for 95% power and 5% significance in food intake between male genotypes, which was derived by using the standard deviation and difference between mean in food intake of genotypes [23].

To investigate whether MIC-1/GDF15 might contribute to the physiological regulation of energy homeostasis, the body weight of MIC-1^−/− mice and syngeneic controls were monitored between the ages of 4 weeks to 1 year. Male MIC-1^−/− mice were on average 6±0.6% heavier than male MIC-1^+/+ control mice of the same age, and female MIC-1^−/− mice weighed on average 10±0.7% more than female controls (Fig. 1A and 1B, male p = 0.04; female p = 0.01). For both male and female mice, the weight differences between genotypes increased significantly over time (Fig. 1C and 1D, female p<0.01; male p = 0.04).

To understand what might have contributed to the increased body weight in MIC-1^−/− mice, whole body lean and fat mass were determined by dual energy X-ray absorptiometry (DXA). Whilst male MIC-1^−/− mice show a similar lean body mass to age and sex matched controls, female MIC-1^−/− mice had a significantly lower lean body mass than age and sex matched MIC-1^+/+ mice (Fig. 2A, male p = 0.21; female p<0.01). Both male and female MIC-1^−/− mice had a significantly higher total fat mass relative to the sex matched MIC-1^+/+ mice (Fig. 2B, male p<0.01; female p = 0.04).

To further delineate differences in body composition, tissue specific lean mass and fat depot weights were measured directly. There was no significant difference between MIC-1^+/+ and MIC-1^−/− mice of either sex in the relative mass of either the gastrocnemius or tibialis muscles (data not shown), and no differences were observed in mass of brown adipose tissue (Fig. 2C, 2D, male p = 0.35, female p = 0.35). However, there was a significant increase in total white adipose tissue mass (WATt), normalized to body weight, in both male and female MIC-1^−/− animals (Fig. 2C, 2D, male p<0.01, female p = 0.02). This was associated with marked significant increases in the weight of the inguinal, mesenteric and/or retroperitoneal fat depots in MIC-1^−/− compared to control mice (Fig. 2C, 2D). These data indicate that MIC-1/GDF15 plays a role in regulating body composition and energy storage in mice.

To examine possible causes for the increased body weight and fat mass in the MIC-1^−/− mice, we first studied their spontaneous food intake. Female but not male MIC-1^−/− had significant increased food intake compared to the age and sex-matched control mice, both in absolute terms (15.59±0.67 versus 12.77±0.88 g/gBW/d in female knockout and control mice, respectively) and when normalized to body weight (p = 0.05 for female mice (Fig. 3A). This data suggested that the increased body weight in female MIC-1^−/− is at least partly due to increased food intake. Whilst the 3.7% difference in food intake between male MIC-1^−/− and MIC-1^+/+ was not statistically significant, this may reflect the capacity of our method to detect small differences in food intake. Power analysis indicates that to determine with 95% certainty whether this 3.7% difference in food intake was significant would require 126 mice of each genotype. As, over a more prolonged period, a difference in 3 days-accumulated food intake of as little as 3.7% is likely to be able alter body weight and composition [23], in this study, we cannot exclude such a small difference being present.

As the timing of food intake can influence energy storage independently of total intake [24], we also measured food intake after fasting, as well as during the light and dark phases in all animals (Figs 3B, 3C, 3D). However, there was no difference between knockout and control mice of either sex with respect to re-feeding after a 24-hour fast (Fig. 3B, p = 0.8 for both sexes). Additionally, there were no significant differences in the pattern of food intake in the light and dark phase between male and female MIC-1^−/− and control mice (Fig. 3C, 3D).

To further investigate possible mechanisms underlying the increases in body weight and adiposity of male and female MIC-1^−/− versus MIC-1^+/+ mice, we compared their respiratory exchange ratio (RER), energy expenditure and physical activity (Figs 4 and 5). The increased body weight and adiposity of MIC-1^−/− animals does not appear to result from differential use of lipids versus carbohydrate as oxidative fuel sources as there was no difference in RER between genotypes (Fig. 4A, 5A). Female mice, MIC-1^−/− animals exhibit significantly lower energy expenditure normalized to bodyweight compared to the age matched control MIC-1^+/+ mice (p<0.01, Fig. 5B, 5D). This difference may be partially attributed to a decrease in physical activity, since physical activity was significantly decreased during the dark phase in female MIC-1^−/− versus control mice (p = 0.03, Fig. 5C, 5E). No such differences in energy expenditure or physical activity were observed between MIC-1^−/− and MIC-1^+/+ male mice (Fig. 4B, 4C, 4D, 4E).

To determine the likely contribution of changes in physical activity to changes in energy expenditure, correlation analysis was performed using hourly data from individual mice. There was a positive correlation between energy expenditure and physical activity within all the groups (p<0.02 by Pearson correlation for all groups, Fig. 6A and 6B). In both males and females, the difference in the slope of the regression line is significantly different for MIC-1^−/− and MIC-1^+/+ mice (p<0.01 in all group, Fig. 6), indicating that the energy cost of activity was different between genotypes. Further, to estimate basal metabolic rate, the function from the trend line was used to extrapolate physical activity to zero, with the point at which the line crosses the X-axis signifying basal metabolic rate. While there was no genotypic difference in basal metabolic rate between males (Fig. 6A), female MIC-1^−/− displayed a significantly lower basal metabolic rate compared to wild type controls (p<0.01) (Fig. 6B). These data indicate that there is a fundamental metabolic difference between the male and female MIC-1^−/− mice relatively to their matched controls, suggesting MIC-1/GDF15 exerts its effects differentially on male and female mice. The difference in total energy expenditure between the female genotypic groups may have been more affected by changes in basal metabolic rate and less by the physical activity. Both of these are likely to contribute to the body weight difference displayed in female MIC-1^−/− versus control mice.

To investigate whether the increased body weight of MIC-1^−/− mice was specifically due to germline gene deletion of MIC-1/GDF15 and not resulting from any unrecognized compensatory or developmental changes in MIC-1^−/− mice, we continuously infused male MIC-1^−/− and MIC^+/+ mice with MIC-1/GDF15 (1–2 µg/d) via osmotic minipumps. Infusion of MIC-1/GDF15 over 5 days resulted in increased circulating human MIC-1/GDF15 levels from zero to 643±67 pg/ml and 576±45 pg/ml in MIC-1^−/− and MIC-1^+/+ mice, respectively. As discussed below, this would have the effect of increasing total MIC-1/GDF15 levels in MIC-1^−/− mice to about the middle of the human normal range and in MIC-1^+/+ mice to the top of the human normal range. This infusion of MIC-1/GDF15 resulted in reduced body weight gain relative to syngeneic vehicle-infused controls (Fig. 7A and 7B, MIC-1^−/− p<0.01; MIC-1^+/+ p = 0.01), coupled with a significant reduction in food intake (Fig. 7C and 7D, MIC-1^−/− p = 0.04; MIC-1^+/+ p<0.01).