Follistatin Effects in Migration, Vascularization, and Osteogenesis in vitro and Bone Repair in vivo

Abstract

The use of biomaterials and signaling molecules to induce bone formation is a promising approach in the field of bone tissue engineering. Follistatin (FST) is a glycoprotein able to bind irreversibly to activin A, a protein that has been reported to inhibit bone formation. We investigated the effect of FST in critical processes for bone repair, such as cell recruitment, osteogenesis and vascularization, and ultimately its use for bone tissue engineering. In vitro, FST promoted mesenchymal stem cell (MSC) and endothelial cell (EC) migration as well as essential steps in the formation and expansion of the vasculature such as EC tube-formation and sprouting. FST did not enhance osteogenic differentiation of MSCs, but increased committed osteoblast mineralization. In vivo, FST was loaded in an in situ gelling formulation made by alginate and recombinant collagen-based peptide microspheres and implanted in a rat calvarial defect model. Two FST variants (FST288 and FST315) with major differences in their affinity to cell-surface proteoglycans, which may influence their effect upon in vivo bone repair, were tested. In vitro, most of the loaded FST315 was released over 4 weeks, contrary to FST288, which was mostly retained in the biomaterial. However, none of the FST variants improved in vivo bone healing compared to control. These results demonstrate that FST enhances crucial processes needed for bone repair. Further studies need to investigate the optimal FST carrier for bone regeneration.

Keywords: bone tissue engineering; follistatin 288 (FST288); follistatin 315 (FST315); injectable in situ gelling slow release system; migration; osteogenesis; regenerative medicine; vascularization.

Figure 1

Effect of follistatin upon MSC and HUVEC in a migration assay. (A) Average migration of MSCs exposed to several doses of follistatin (FST315) relative to the negative control (n = 4 donors in duplicate). (B) Average migration of HUVECs exposed to several doses of follistatin (FST315) relative to the negative control (n = 3 independent experiments in duplicate). The bars represent the mean ± SD.

Figure 2

Effect of follistatin on neovascularization. (A) Effect of follistatin (FST315) on vasculogenesis. Total number of nodes was quantified (n = 3 experiments in triplicate). Next to the graph, representative pictures of tube-like structures are shown after 6 h incubation in the presence and absence of FST (scale bar: 1,000 μm). (B) Effect of FST315 on angiogenesis. MVEC spheroids were embedded in collagen and incubated for 24 h. The total number of sprouts per spheroid w/o the addition of FST at 28 ng/ml dose are plotted in the graph (n = 10 individual spheroids per experimental group). Next to the graph, representative pictures of cell spheroids in the presence and absence of FST are shown after 24 h incubation (scale bar: 400 μm). The bars show the mean ± SD.

Figure 3

Effect of follistatin on osteogenic differentiation. Human MSCs and osteoblasts were induced to mineralize in the absence or continuous presence of follistatin (FST315). (A) Quantification of calcium deposition (nmol/ cm²) in the MSC extracellular matrix at the onset of mineralization relative to control (osteogenic differentiation medium) (n = 4 donors performed in triplicate). Donor dependently, mineralization started between 18 and 22 days of culture. Representative pictures of the Von Kossa staining at the onset of mineralization (scale bar: 500 μm). (B) Left graph: alkaline phosphatase (ALP) activity (mU/ cm²) during SV-HFO culture with and without continuous FST treatment at day 9 (gray bars) and 16 (black bars) of culture. Results are shown relative to day 9 control. Right graph: Quantification of calcium deposition (nmol/ cm²) in the SV-HFO extracellular matrix at day 16 relative to control (n = 3 experiments performed in triplicate). The bars show the mean ± SD.

Figure 4

Production of follistatin and activin A by MSCs and osteoblasts. FST (A) and activin A (B) levels were measured in supernatant of MSC and SV-HFO that were induced to mineralize until onset of mineralization. Production was corrected for cell lysate protein content. The bars show the mean ± SD. **p < 0.01 and ***p < 0.001.

Figure 5

In vitro release of FST288 compared to FST315. The cumulative release of FST288 and FST315 from the alginate-MS formulation in DMEM with 1% P/S detected by ELISA is demonstrated over 4 weeks. Data are presented indicating the mean ± SEM. Statistical difference at 28 days of cumulative release analyzed by Student's t-test, p < 0.001.

Figure 6

In vivo μCT analysis of rat skulls implanted with FST288 and FST315 over time. (A) Representative in vivo μCT images of the skulls at 2, 4, 6, 8, and 10 weeks after implantation (scale bar: 2 mm) of either biomaterial alone or loaded with FST288 or FST315. In the representative μCT images of both FST variants the right defect was loaded with 800 ng of FST and the left defect was loaded with 80 ng of FST. (B) Graphical representations of in vivo μCT analysis. Bone volume was normalized to animals without surgical intervention. The effect of the formulation loaded with FST288 (left graph) and FST315 (right graph) was compared to the effect of the use of the biomaterial alone as control group.

Figure 7

Newly formed bone tissue at 10 weeks of healing. (A) Bone density observed by ex vivo μCT analysis in the different conditions after implant harvesting. (B) Percentage of defect filling by newly formed mineralized tissue analyzed by ex vivo μCT. Mean is indicated as the line plotted in the middle of the graphs ± SD. (C) Representative pictures of rat skulls implanted with the biomaterial w/o the addition of the FST variants at 10 weeks. Histological analysis includes von Kossa and Goldner's trichrome staining. Von Kossa staining was used to distinguish mineralized tissue (black) (scale bar: 2.5 mm), while Goldner's trichrome staining was used to determine bone histomorphometry. The square grid delimitates the selected magnified area for each image that is shown with Goldner's trichrome staining (scale bars are 250 μm and 50 μm, respectively), showing erythrocytes (red/purple), nuclei (blue/ gray), alginate remains (alg), formed bone (B), and fibrous tissue (FT). Immature ECM is indicated by yellow arrows and regions where the microspheres have been likely degraded are indicated by black arrows. (D) Representative fluorescence images of the central region of the explants showing calcein fluorochrome incorporation in the newly formed bone tissue at 10 weeks post-implantation (scale bar: 500 μm) with or without the addition of the FST variants. Fluorescence images are combined with bright-field images of the same area.