Previous analysis of the heparanase knockout (Hpa-ko) mice showed neither remaining enzyme protein nor detectable catalytic activity in any of the tissues analysed [21]. The body weight of male Hpa-ko mice kept on normal chow was similar to that of wt siblings for the first 5–6 weeks of life but diverged thereafter. Hpa-ko mice weighed more than their wt siblings (Fig. 1A). Hpa-ko and congenic wt siblings were subjected to DEXA analysis of body composition at 21 weeks of age. Results showed that the difference in body weight was largely due to a substantial increase in fat mass in Hpa-ko mice, along with a smaller but significant increase in lean body mass (Fig. 1B). Notably, the fat content of the Hpa-ko lacking heparanase was almost twice that of wt controls. There was no difference in body length.

To investigate food consumption, individually housed adult male mice were given the choice between a low-fat and a high-fat diet for one week. Hpa-ko mice consumed significantly more of the high-fat diet and showed a higher overall energy intake than the wt controls (Fig. 1C, right panel). Neither the intake of low-fat diet (Fig. 1C, right panel) nor the intake of normal chow (with even lower fat content) when offered alone (Fig. 1C, left panel) differed between groups.

Over-expression of heparanase in the Hpg-tg mice was confirmed immunocytochemically, with marked expression in many brain areas, including the hypothalamus (Fig. S1). The Hpa-tg mice showed a striking metabolic phenotype. DEXA analysis of Hpa-tg mice at 5 months of age revealed reduced fat mass, but no difference in lean body mass or body weight. Body length was significantly increased compared to wt controls (Fig. 2A). Unexpectedly, cumulative food intake monitored over a period of one week was significantly higher in the Hpa-tg group. Consumption of normal chow by individually housed animals was monitored once a day. Hpa-tg mice ate more chow than wt controls (Fig. 2B), indicating decreased food efficiency. Bomb calorimetry measurements revealed no difference in energy contents of faeces from Hpa-tg and wt animals (Fig. S2), hence excluding energy loss in faeces as a cause of the decreased food efficiency. However, analysis of energy metabolism by indirect calorimetry (Fig. 2C) showed that whereas Hpa-tg mice equalled wt energy expenditure, they shifted towards a lower RQ during the dark phase. The transgenic mice thus appear more prone to use fat as an energy source. Consistent with this metabolic phenotype, Q-PCR analysis of relevant genes showed only marginal effects of heparanase overexpression on Synd-3 and Pomc, but significantly decreased hypothalamic expression of AgRP, compared to wt controls (Fig. S3).

According to the current hypothesis cell-surface HS promotes binding of AgRP to MC4R [13]. Truncation of these chains by heparanase would favour receptor binding of the agonist α-MSH and hence, cause a suppression of food intake. This hypothesis was tested in acute experiments involving injection of recombinant human heparanase into the lateral third dorsal ventricle along with a starvation-refeeding protocol. Intracerebro-ventricular (ICV) administration of heparanase caused a dramatic reduction in food intake compared to vehicle-treated control mice. Cumulative food intake at 6 hr after heparanase injection (and start of refeeding) was less than 50% of that observed in controls (Fig. 3A, left panel). This effect of heparanase injection was also evident in terms of body weight gain that was only 30% of control after 6 hr and still depressed after 24 hr (Fig. 3A, right panel).

Experiments designed to elucidate the time course of heparanase action revealed different temporal windows depending on when the enzyme was administered relative to the start of refeeding. When access to food was admitted immediately after heparanase injection, reflex hyperphagia was observed without any discernible difference between heparanase- and vehicle-treated groups during the first hour (Fig. 3B, left panel). Instead, the reduction in food intake developed gradually during the following hours, was most conspicuous 4–6 hr after enzyme administration, and persisted well beyond the time window required for control mice to resume normal feeding behaviour. Importantly, this finding suggests that heparanase affects food intake per se and not only in connection with reflex hyperphagia. We next investigated whether the delayed response was inherent to the mechanism triggered by the enzyme, alternatively, it could also be explained by pharmacokinetic factors. We therefore redesigned the experiment by administering the heparanase 1 hr prior to food presentation. Under these conditions the reduction in food intake was seen from the outset (Fig. 3B, right panel). The delayed action observed after simultaneous heparanase injection and food administration thus appears to reflect the time required for the enzyme to reach and act on the HSPG target.

Collectively, these results implicate heparanase in the modulation of MC4R signaling. To test this concept we designed a cross-over study in which food intake was measured in MC4R male knockouts and their wt siblings injected ICV with heparanase or vehicle. The results showed that wt mice injected with heparanase had 20–25% lower cumulative food intake 2 hr and 4 hr after food presentation compared to vehicle controls, whereas there was no effect of heparanase treatment in the MC4R knockout mice (Fig. 4). The acute effects of centrally administered heparanase on food intake can therefore be directly linked to modulation of MC4R signaling. We also infer that the appetite suppression in the wt mice was not due to general malaise/sickness induced by the heparanase injection.

Heparanase affects a variety of physiological and pathophysiological processes, essentially through cleavage of HS chains on HSPGs at cell surfaces or in the extracellular matrix [23]. Detailed analysis of the Hpa-tg mouse strain used in this study showed that cerebral expression of the enzyme led to degradation of HS, accompanied by change in disaccharide composition (X. Zhang, personal communication). Our results implicate heparanase with regulation of energy balance, through modulation of MC4R signaling. Male Hpa-ko mice display maturity-onset obesity and exhibit increased food intake when given access to a high-fat diet. Conversely, the Hpg-tg mice have reduced body fat. Moreover, central administration of heparanase lead to reduced food intake in mice and this effect was abolished in mice lacking MC4R.

The first observation associating a HSPG with appetite regulation was maturity-onset obesity in transgenic mice over-expressing syndecan-1 [16]. The constituent HS chains were assumed to promote binding of AgRP to its receptor, MC4R, thus stimulating food intake and at the same time precluding the appetite-suppressing effects of α-MSH. This co-receptor function would normally be exerted by syndecan-3, the predominant HSPG isoform in the hypothalamus. Notably, a polymorphism in the syndecan-3 gene has been associated with obesity in a female population [24]. The levels of syndecan-3 and hence, exposure of HS chains, at the cell surface, appear regulated through shedding of the HS-substituted ectodomain by protease cleavage and vary with the feeding state of the animal. It was proposed that the shedding enzyme that cleaves hypothalamic syndecan-3 does not recognize syndecan-1 [13], [16], [17], [18].

Heparanase provides an alternative mechanism for modulating accessibility of HS chains. Our results indicate that heparanase affects energy balance, in particular, as a negative modulator of AgRP signaling, by cleavage of HS chains on the syndecan-3 co-receptor (Fig. 5). Hpa-ko mice thus develop a phenotype reminiscent of that observed in syndecan-1 over-expressing mice [16], with maturity-onset increase in body weight due to increased fat and, to a lesser extent, lean body mass (Figs. 1A, B). Regulation of food intake is affected as shown by increased intake of high-fat chow (Fig. 1C). Conversely, heparanase over-expressing Hpa-tg mice showed reduced fat mass, in seemingly logical contrast to the Hpa-ko phenotype (Fig. 2A). The predicted mechanism was corroborated by acute injections of heparanase directly into the lateral cerebral ventricle, in connection with fasting-refeeding experiments. This treatment resulted in a marked, sustained suppression of food intake (Fig. 3) that was dependent upon intact MC4R function (Fig. 4). Thus, the increased food intake of Hpa-ko mice may be ascribed to more efficient AgRP co-receptor function of HS chains (Fig. 5).

The MC4R signaling system is known to modulate multiple factors in regulation of energy balance [20], and the seemingly unified picture outlined through the Hpa-ko and Hpa-tg models in Fig. 5 appears partly oversimplified. Heparanase affects a number of distinct factors in energy balance regulation. Key components of this equation are energy intake through feeding and energy expenditure through basal metabolism, physical activity and adaptive thermogenesis [2]. Unexpected effects of heparanase overexpression may be ascribed to the complex regulatory mechanisms behind this balance. Hpa-tg males thus were unexpectedly found to eat more than wt controls (Fig. 2B), in spite of their reduced fat mass (Fig. 2A). Whereas there was no significant difference in energy expenditure, the Hpa-tg mice showed a lower nominal RQ indicating a relative preference for fat as the main fuel source (Fig. 2C). The decreased AgRP expression of the Hpa-tg mice (Fig. S3) is of particular significance in this context, as central melanocortin signaling also controls peripheral nutrition partitioning that may affect the amount of body fat independently of food intake [25]. In fact, AgRP-ko mice, a predicted phenotype mimic of our Hpa-tg animals (see Fig. 5) showed increased fat utilization [11]. The Hpa-tg mice appear more aggressive at adult age than wt controls but otherwise show no apparent deviation in behaviour. Overall, our data indicate that heparanase affects food intake primarily in a short-term perspective and energy balance over a longer time span. It thus has been suggested that AgRP acts both as an antagonist of the MC4R and as an inverse agonist on its own, and that the different modes of signaling relate to short-term effects of fasting and more long-term effects on energy balance regulation, respectively [17]. We therefore surmise that the increased food intake by the Hpa-tg mice is a compensatory phenomenon, secondary to the increased use of fat as energy source [26], [27].

The various phenotypes resulting from genetic perturbation of the melanocortin signaling system (Fig. 5) largely conform to our hypothesis that heparanase modulates energy balance via the melanocortin system, by compromising the AgRP—syndecan-3 interaction at the MC4R. The obese phenotypes seen in mice lacking MC4R [8] or over-expressing either AgRP or syndecan-1 [10], [11], [16] resemble that of Hpa-ko mice. Both the MC4R knockouts [28], [29] and heparanase knockouts (Fig. 1C) react by increasing food intake when challenged with a high-fat diet. Conversely, the syndecan-3 knockout and AgRP-deficient mice display lean phenotypes [11], [17] similar to the Hpa-tg mice.

The Hpa-tg mice used in this study differ from those described in a previous report, characterized by significantly reduced food intake and body weight compared to controls [22]. However, subsequent examination of these mice revealed a defective intestinal barrier and leakage of nutrients in the intestine [30]. Intestinal malfunction with nutrient leakage presumably confounds metabolic phenotype analysis. The mice used in the present work were from a different founder derived from the same construct [22], and were backcrossed to yield a pure genetic background (C57BL/6J). They had no apparent intestinal problems, most likely due to the low level of overexpression of heparanase in the intestinal system. However, this mouse strain showed more prominent heparanase expression in the brain (Fig. S1).

Human genetic data and murine studies have implicated MC4R with energy balance regulation in the CNS, hence a potential target for treatment of obesity and eating disorders [31], [32], [33]. Mutations in the MC4R are the most common cause of monogenic childhood obesity and the severity of obesity can be quantitatively correlated to the impairment of signaling [12], [34]. Moreover, several polymorphisms close to the MC4R gene were associated with BMI in recent genome-wide association studies [35], [36], [37]. The receptor apparently has a key role in coordinating afferent messages from the periphery and regulatory signals in control of food intake as well as energy expenditure. Our data indicate that heparanase acts as a negative modulator of AgRP signaling at MC4R, through cleavage of HS chains that are constituents of syndecan-3. This mechanism, along with previously proposed, modulated shedding of syndecan-3 ectodomain [13], [16], [17], [18], constitutes a novel signaling system that will help improve our understanding of obesity and its causes.

Male mice were used throughout the study. Heparanase overexpressing (Hpa-tg) mice were essentially as described in [22], except that the mice used in the present study were from a different founder and were backcrossed (×10) to C57BL/6 background. Heparanase cDNA was expressed under the chicken ß-actin promoter with a CMV-IE enhancer, followed by a rabbit ß-globin poly-adenylation site. The Hpa-ko mice were described in [21]. The genotypes of the mice were determined by PCR as described [21], [22]. MC4R-ko (B6;129S4-Mc4r_tm1Lowl/J) mice [38] were purchased from The Jackson Laboratories (Maine, USA) and were further bred and raised at the local animal facility (Gothenburg University). For genotyping a three-primer touchdown PCR was used (Scandinavian Gene Synthesis AB, Köping, Sweden). All MC4R-ko mice were of mixed background (C57BL/129SV) and we therefore used only siblings as controls. C57BL/6J mice were purchased from Taconic, Denmark.

Mice were maintained on a 12-hour light, 12-hour dark schedule (lights on at 7 am). Food and water were available ad libitum except where otherwise indicated. Standard protocols of laboratory animal care were followed. The age of mice is indicated in connection with description of experiments. The experiments were approved by the ethical committee at Gothenburg University, Sweden (ID numbers: 211/08, 308/06 and 66/07).

Genomic DNA was isolated from tail biopsies and was purified using “HotSHOT” genomic DNA preparation [39]. Primers for Hpa-ko: Neo U-5′-gaggctattcggctatgactg-3′ and Neo L-5′-aggagcaaggtgagatgaca-3′; Hspe U-5′-cgttcctgtccatcaccatc-3′ and Hspe L-5′- aggctccagacaaagtgctaa-3′; For Hpa-tg: Primers were as in [22]. For MC4R-ko: common MC4r#1 5′-gcagtacagcgagtctcagg -3′, mutant MC4r#2 5′-gtgcaagtgcaggtgccag-3′ and wild type MC4r#3 5′-ctccaacaggcttatgacacc-3′, yielding a band of 500 bp (mutant) and a band of 400 bp (wildtype).

For gene expression, the brains of the mice (12–18 weeks old) were dissected and total RNA was extracted from hypothalamus. Q-PCR was applied using the primers shown in Table S1. The data were normalized using the mRNA level of GAPDH from each sample. For immunohistochemical staining, the brain sections were stained with anti-heparanase antibody (733) and counter-stained with H&M as described previously [22].

High-fat diet, HFD (D12492; 60% fat, 20% protein, 20% carbohydrate by calories, 5.24 kcal/g), and low-fat diet, LFD (12450B; 10% fat, 20% protein, 70% carbohydrate by calories, 3.85 kcal/g) were purchased from Research Diets Inc. (New Brunswick, USA). Normal chow (4% fat, 16.5% protein, 58% carbohydrate by calories, 2.99 kcal/g) was provided by the animal facility for routine maintenance (product number R34; Lantmännen, Stockholm, Sweden). Food intake was measured manually, involving weighing of pre-weighed food pellets at times indicated.

Recombinant heparanase for injection experiments was generated using single-chain GS3 active heparanase gene construct, comprising the 8 and 50 kDa heparanase heterodimer (8+50), kindly provided by Dr. Christian Steinkuhler (IRMB/Merck Research Laboratories, Pomezia, Italy). The recombinant protein was purified to homogeneity (crystallization grade) from the conditioned medium of baculovirus-infected cells [40]. GS3 active heparanase was assayed for the presence of bacterial endotoxin by Biological Industries, using the gel-clot technique (Limulus amebocyte lysate, LAL test) and was found to contain <10 pg/ml endotoxin [41].

For ICV surgery, mice (6–8 weeks old; C57BL/6J) were anaesthetized using isofluran (induction 4%, maintenance 2–3%; air flow, 260 ml/min) and then placed in a stereotactic frame. Holes through the skull were made using a dentist drill, one for a steel guide cannula (AG-8, code 806302 from Agntho's, Lidingö, Sweden) that was implanted projecting to the lateral ventricle using stereotactic co-ordinates (0.94 mm posteriorly from bregma and down 1 mm) and one for a stabilizing screw (Agntho's). The cannulae were held in position by dental cement (Dentalon, Agntho's, fluid 7509, powder 7508) attached to the stabilizing screw. Saline (approximately 500 µL/mouse) was given subcutaneously for hydration and Rimadyl (2.5 mg/kg mouse) for analgesic was administered intraperitoneally. After 5–6 days of recovery on normal chow in individual cages the mice were fasted for 16 h over-night before ICV injections. Food consumption and weight regain were recorded as described in the results.

Recombinant heparanase (1.4 µg/µL) in vehicle (20 mM MES, 0.15 M NaCl, pH 6.0) was injected (1 µL/min, total 1 µL) using CMA pumps (CMA Microdialysis AB, Solna, Sweden) and Hamilton syringes (Genentec, Västra Frölunda, Sweden) connected to injection cannulae (30G, AMI-9.5; Agntho's). The vehicle was used as a control. Food intake was measured at the time points indicated. To check placement of needle, trypan blue was injected into the guide cannulae after the experiment followed by dissection of the brains.

Mice at varied ages were used in the different experiments (see legends to figures); however, wt and transgenic mice in each experiment were invariably of similar age. Indirect calorimetry was performed using the INCA systems (Somedic, Hörby, Sweden). Mice were placed individually in metabolic chambers 2 hr before start of measurement for adaptation, and were then maintained in the chambers for 16–20 hr with ad libitum access to food and water. Oxygen consumption and carbon dioxide release were measured at 2 min intervals. Data were analysed by calculating areas under curves followed by two-tailed independent t-tests. Body composition was determined by dual energy X-ray absorptiometry (DEXA) using a Lunar PIXImus (GE Lunar, Madison, WI, USA). Body length was measured on sedated mice with a ruler from nose to anus.

Data were analysed using independent two-tailed t-test and two-way analysis of variance (ANOVA) using the SPSS program (SPSS, Chicago, IL, USA). All data presented are means ± SEM. P values reported are from independent two-tailed t-tests unless otherwise stated.