Graphene-modified CePO4 nanorods effectively treat breast cancer-induced bone metastases and regulate macrophage polarization to improve osteo-inductive ability

Preparation of CePO₄ nanorods

1.3539 g Ce (NO₃)₃·6H₂O and 0.0990 g (NH₄)₂HPO₄ were dissolved separately in 30 ml ultrapure water. The Ce (NO₃)₃ solution was added dropwise into the (NH₄)₂HPO₄ solution under continuous stirring. During the dropping process, 1.0 M of HCl was utilized to keep the pH value at 0.5. After further stirring for 30 min, and the mixtures were transferred to the autoclave. The hydrothermal reaction was carried out at 180 °C for 24 h, and then was cooled to a room temperature. The final products were washed with distilled water and alcohol, and dried at 55 °C.

Preparation of CePO₄/CS/GO scaffolds

1.00 g CS was added into 25 ml CH₃COOH solution, forming a CS solution after mechanical agitation for 2 h. 2.00 g CePO₄ nanorods and 0.09 g GO nanosheets were added to the CS solution. The mixed solution was stirred for 2 h, and then was transfused to the mould of 24-well or 96-well plates. The samples were freeze-dried in a freezer at -60ºC for 48 h. The CePO₄/CS/GO scaffolds were washed by deionized water for 6 days, and freez-dried again. Furthermore, CePO₄/CS scaffolds were constructed by the same method without adding GO nanosheets.

Characterization

The morphology and crystal structure of CePO₄ nanorods was detected by transmission electron microscopy (TEM, JEOL2100, Japan) and selected area electron diffraction (SAED). Field-emission scanning electron microscopy (SEM, JSM-6380LV, Japan) and energy-dispersive spectrometry (EDS) were performed to observe the morphologies and element distributions of the nanorods and scaffolds. The phases of the samples were assayed by an X-ray diffractometer (XRD; D/max-III C, Japan) in a 2θ range of 10–70° with Cu Kα radiation. Functional groups in samples were detected by Fourier transform infrared spectroscopy (FTIR; PerkinElmer, USA) in the wavenumber range of 4000–500 cm⁻¹. The binding energies of the Ce in the CePO₄ nanorods were detected by an X-ray photoelectron spectroscopy (XPS, PHI5700 ESCA, USA). The light adsorption properties of the scaffolds were detected by a UV–vis spectrometer (UV3600, Shimadzu) in 400–1200 nm region. The Ce ion release performance from CePO₄/CS porous scaffolds was investigated by soaking 0.175 g CePO₄/CS/GO scaffolds in 4.5 ml ultrapure water. After released for different time, the concentrations of Ce³⁺ ions were determined by inductively coupled plasma/optical emission spectrometry (ICP/OES; Perkin Elmer, OPTIMA 3300 DV). To determine photothermal effects of the scaffolds, 7.80 mg samples were immersed in 100 µL ultrapure water. The temperatures were detected with time by a thermocouple thermometer upon the irradiation of NIR laser (λ = 808 nm, 4.6 W/cm²).

Cell culture and toxicity

MC3T3-E1, RAW264.7, and MDA-MB-231 cells were purchased from the Shanghai Institutes for Biological Sciences of the Chinese Academy of Sciences (China). Human bone marrow mesenchymal stem cells (hBMSCs) were purchased from the Shanghai Bio-Chain Biological Technology Co., Ltd. (China). All processes were approved by the Animal Hospital of Shanghai Jiao Tong University. The α-minimum essential medium (α-MEM) and foetal bovine serum (FBS) were purchased from the Gibco line of Thermo Fisher Scientific, Inc. (Waltham, MA, USA). Cells were cultured at 37 °C with 5% CO2. To examine the cell toxicity, 1 × 10⁴ MC3T3-E1 cells/well were seeded in a 96-well plate and cultured for 24 h. The extraction solutions of CS, CePO₄/CS, and CePO₄/CS/GO scaffolds were used as the exchange solutions. The cell toxicity was examined with Cell Counting Kit-8 (CCK-8 Dojindo, Kumamoto, Japan) on days 1, 2, 3, and 4.

MDA-MB-21 cells (metastatic breast cancer cells) were cultured in Dulbecco's modified Eagle's medium (DMEM) containing 10% FBS at 37 °C with 5% CO2. The cells were then mixed and cultured with the CS, CePO₄/CS, and CePO₄/CS/GO scaffolds (12 mm diameter, 2 mm height) in 24-well plates for 24 h under NIR radiation with a power density of 4.6 W cm^− 2 for 3 min. The cell viability was examined with Cell Counting Kit-8 (CCK-8 Dojindo, Kumamoto, Japan) on days 1, 2, 3, and 4.

Alkaline phosphatase staining and alizarin red staining

MC3T3-E1 cells were cultured in a 24-well plate for 24 h. The CS, CePO₄/CS, and CePO₄/CS/GO extraction solutions were used as exchange solutions to test for cell osteogenesis. Cells were cultured in the extraction solutions for 7 and 21 days and fixed with paraformaldehyde (PFA), followed by two rinses with phosphate-buffered saline (PBS). The cells were then stained using an alkaline phosphatase (ALP) kit and alizarin red staining kit (Hongqiao, Shanghai, China) and observed under an optical microscope.

Cell adhesion

The hBMSCs were cultured in 24-well plates at a density of 1 × 10⁴ cells/well with CS, CePO₄/CS, and CePO₄/CS/GO for 12 h. The cells were fixed with 2.5% glutaraldehyde for 20 min and then dehydrated in ethanol with concentration gradients of 75, 85, 95, and 100% before being observed under scanning electron microscopy (SEM, Siriaon 200, FEI, Hillsboro, OR, USA).

Flow cytometry

The CS, CePO₄/CS, and CePO₄/CS/GO scaffolds were added to MDA-MB-231 cell culture medium, and the cells were exposed to radiation from a near-infrared (IR) spectrometer with a power density of 4.6 W cm⁻² for 3 min. The apoptotic cells were detected using flow cytometry (annexin V/PI staining) according to the protocol provided by the manufacturer (BD Bioscience, USA). The RAW264.7 cells were then added to the CS, CePO₄/CS, and CePO₄/CS/GO scaffolds. The cells with the CePO₄/CS/GO scaffolds were divided into two groups; one group was exposed to NIR radiation, and other was not. According to the protocol provided by the manufacturer (BD Bioscience, USA), the polarization of the macrophages was examined by flow cytometry using anti-mouse CD16/32-PE (cat. No. 553145) and anti-mouse CD206-Alexa 647 (cat. No. 565250).

Immunofluorescence

The CS, CePO₄/CS, and CePO₄/CS/GO scaffold materials were added to other batches of RAW264.7 cell culture medium. The cells with CePO₄/CS/GO were divided into two groups; one group was exposed to NIR radiation, and the other was not. The cells were fixed with 4% PFA fixation solution for 20 min. The CD206 (1:200) antibody and CD16/32 (1:200) antibody were employed for the immunofluorescence analysis. All antibodies were purchased from Cell Signaling Technology.

Quantitative reverse transcription polymerase chain reaction (RT-qPCR) and western blot

The MC3T3-E1 cells were seeded at a concentration of 4 × 10⁶ in extraction solutions of CS, CePO₄/CS, and CePO₄/CS/GO scaffolds. The total RNAs were collected with an RNeasy Mini kit (Qiagen: Valencia, CA, USA) after 5 days of culture. Reverse transcriptase (TaKaRa) was employed to transcribe the RNA to complementary DNA (cDNA). SYBR1 Premix ExTaqTM II (TaKaRa) was added to the Real-Time PCR and ABI 7500 Sequencing Detection System (AppliedBiosystems, Foster City, CA). The PCR primer was designed as follows:

GAPDH forward 5′-CACCACCATGGAGAAGGCCG-3'

and reverse 5′-ATGATGTTCTGGGCAGCCCC-3'

Runx2 forward 5′-GACTGTGGTTACCGTCATGGC-3'

and reverse 5′-ACTTGGTTTTTCATAACAGCGGA-3'

ALP forward 5′-AGAAGTTCGCTATCTGCCTTGCCT-3'

and reverse 5′-TGGCCAAAGGGCAATAACTAGGGA-3'

BMP-2 forward 5′-CCGCTCCACAAACGAGAAAA-3′

and reverse 5′-CAGCAAGGGGAAAAGGACAC-3′

OCN forward 5′-TAGCAGACACCATGAGGACCATCT-3'

and reverse 5′-CCTGCTTGGACATGAAGGCTTTGT-3'

The expression levels of COL1, bone morphogenetic protein (BMP-2), P-Smad1/5, RUNX2, and GAPDH were examined with CS, CePO₄/CS, and CePO₄/CS/GO scaffold extraction solutions. After 3 days of culture, radioimmunoprecipitation assay (RIPA) lysate containing protease inhibitor was added to the MC3T3-E1 cells, and they were left for 20 min. The cells were centrifuged at 12,000 rpm for 20 min, and the supernatant was collected. The protein content of the supernatant was analysed by a bicinchoninic acid assay (BCA). The supernatant was transferred to gel pores for sodium dodecyl sulfate–polyacrylamide gel electrophoresis (SDS-PAGE) and then transferred to a poly (vinylidene fluoride) (PVDF) membrane after electrophoresis. The membrane was stored in 5% low-fat milk for 1 h. Primary antibody was added, and the samples were incubated at room temperature for 4 h. GAPDH(1:1000), P-Smad1/5 (1:1000), RUNX2 anti-bodies (1:1000), BMP-2 anti-bodies (1:1000), and COL1 anti-bodies (1:1000) were purchased from Cell Signaling Technology (Shanghai, China). Finally, horseradish peroxide (HRP) secondary antibody was added to the sample and incubated for 1 h. Analysis was then performed with the Odyssey infrared imaging system (LI-COR Biosciences, Lincoln, NE).

Construction of animal model

All experimental procedures were approved by the Institutional Animal Care and Use Committee (IACUC) of the Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine. All mice were provided by the Research Council of the Animal Center of the Shanghai Ninth People's Hospital (China). All mice were kept at room temperature of 20–26 °C, with a relative humidity of 70% and light intensity ≥ 200 lx (12 h light/dark) and provided with sufficient food and water. MDA-MB-231 cells (5 × 10⁷ metastatic breast cancer cells) were subcutaneously injected at the underarm of the mice. Mice with a tumour size of 6 mm in diameter were randomly divided into 4 groups (n = 4): control, CS, CePO4/CS, CePO4/CS/GO groups. An incision was performed on the edge of the tumour, and the scaffold was installed. All mice were exposed to NIR radiation (0.55 W/cm) for 10 min. The tumour tissue temperature was monitored by a LIRTM A320 camera. All mice were exposed to NIR radiation once a day for 14 days. After 14 days, the mice were given full anaesthesia, and the immunofluorescence intensity of the metastatic breast cancer cells was measured with IVIS scanning (PerkinElmer, USA). At the end of the process, all mice were euthanized, and the tumour tissues were removed, followed by the measurement of the volume. After the quantitative measurement, the tumour tissues were fixed in 4% PFA, embedded in paraffin, and sliced, and the sliced tissues from each group were subjected to caspase-3 immunofluorescence staining.

Another animal model was initiated using Sprague–Dawley rats with defects in the skull. Female Sprague–Dawley rats of 200–250 g were selected as the model animal. An animal model with bilateral bone defects in the skull was used to measure the polarization of macrophages and the regeneration of bone. The diameter and height of the bone defects were 5 and 2 mm, respectively. CS, CePO₄/CS, and CePO3/CS/GO scaffolds (n-5) were filled into the defects, and the scalp was sutured. The new bone formation and osteogenesis were examined by multicolour immunofluorescence. Intraperitoneal injections of the immunofluorescence markers alizarin red (30 mg/kg, Sigma-Aldrich) and calcein (30 mg/kg, Sigma-Aldrich) were given 3 and 21 days before sacrificing the rats, respectively. All rats were euthanized after 12 weeks, and the skulls with the scaffolds in the defects were dissociated. The skulls were stored in 4% phosphate formaldehyde solution for 7 days and subjected to micro-CT (mCT-80, Scanco Medical AG, Switzerland) examination. The parameters were as follows: a voltage of 90 kV, a current of 88 μA, and a pixel size of 28 μm. The 3D model was reconstructed after the scanning. The bone mineralization density (BMD) and new bone volume/tissue volume (BV/TV) were analysed by software. The undecalcified samples were fixed by bone cement, and the skulls were sectioned along the sagittal plane using a microtome (Leica, Hamburg, Germany). The immunofluorescence was measured by scanning confocal microscopy (Leica, Heidelberg, Germany; Alizarin red: 543/580–670 nm, Calcein: 488/500–550 nm). The bone mineralization rate was measured by a PC-based analysis system. The skulls were stored in 10% ethylene diamine tetraacetic acid (EDTA) for 30 days after the removal of the soft tissues. Finally, we dewaxed the sample and placed it in: xylene for 5 min, xylene for 5 min, xylene for 5 min, 100% ethanol for 2 min, 100% ethanol for 2 min, 100% ethanol for 2 min, and 90% ethanol for 2 min. 80% ethanol for 2 min; deionized water for 2 min. Put in the hematoxylin dye solution for 5 min. Eosin stained for 5 min. Subsequently, it was taken out and placed in 80% ethanol for 2 min; 90% ethanol for 2 min; 100% ethanol for 2 min; 100% ethanol for 2 min; xylene for 5 min; and 100% ethanol for 2 min. Hematoxylin–eosin (HE) staining and Masson staining were performed for a morphology analysis. The above samples were washed with TBST, and the dewaxed sections were taken out and placed in a blocking solution for 1 h on a shaker. After the end of the time, the blocked sections were washed 3 times with TBST for 10 min each time. Then carry out a primary antibody reaction. The antibody of the target protein was prepared in advance, and the primary antibody (iNOS, 1:200; CD206, 1:200) was diluted with the primary antibody dilution according to the instructions, and dropped on the surface of the slice. The primary antibody was applied and allowed to stand overnight at 4 °C. After the end of the primary antibody, the primary antibody was collected and the membrane was washed with TBST solution for 10 min each time. Finally, the secondary antibody was incubated, protected from light, and allowed to stand at room temperature for 2 h. The polarization index of the sample was detected by fluorescence microscopy.

Data analysis

SPSS 13.0 software (Statistical Package for the Social Science, USA) was used to analyze the data. It presented as the Means ± SD. One-way analysis of variance was used to determine statistically significant differences. P ≤ 0.05 as statistically significant.

Morphology and structure of CePO₄ nanorods

The CePO₄ nanorods were prepared according to the hydrothermal method, as shown in Fig. 1. During the hydrothermal reaction, the CePO₄ crystals grew along the c-axis orientation, forming one-dimensional rod shapes. The CePO₄ nanorods had diameters of 5 µm and lengths of 50 nm, as confirmed by the SEM and TEM images (Fig. 1a, b). The crystal structure of CePO₄ nanorods was investigated further by the high-resolution TEM images (Fig. 1c). The lattice fringes of the CePO₄ nanorods demonstrated the monocrystalline structure, and the d-space of 0.610 nm was ascribed to (100) crystal plane. The SAED pattern of CePO₄ nanocrystals revealed that the diffraction spots corresponded to [010] zone axis (Fig. 1d).

The phase structure of CePO₄ nanorods was investigated by XRD pattern (Fig. 1e). All the diffraction peaks were much matched with the hexagonal CePO₄ crystals with space group of P622 (180), which were indexed to PDF card NO. 34-1380. The cell parameters of CePO₄ nanorods were calculated by using MDI JADE5.0 software, as followed: a = b = 0.7067 nm, c = 0.6439 nm, α = β = 90º, and γ = 120º. The characteristic peaks of CePO₄ nanorods showed strong peak intensity, demonstrating their high crystallinity. Moreover, the functional groups in CePO₄ nanorods were revealed by FTIR spectrum (Fig. 1f). The band at 1619 cm⁻¹ was ascribed to adsorbed water on the surfaces of CePO₄ nanorods. The bands due to the asymmetric stretching vibration of PO₄³⁻ groups located at 1039 and 1012 cm⁻¹. The P–O bending vibration and antisymmetric deformation vibration band located at 955 cm⁻¹ and 620 cm⁻¹, respectively.

Characterization of CePO₄/CS/GO scaffolds

The freeze-drying technology was used to construct three-dimensional porous scaffolds including CS, CePO₄/CS and CePO₄/CS/GO scaffolds. All CS, CePO₄/CS and CePO₄/CS/GO scaffolds had the 3D macropores with sizes of 80 µm (Fig. 2a, d and g), which were created due to ice crystal sublimation during the freeze-drying procedure. These macroporous structures could provide enough spaces for cell migration, nutrient transfer and bone tissue ingrowth. Interestingly, these macropores existed among the plate-like films. For the pure CS scaffolds, the films presented smooth surfaces (Fig. 2b). For the CePO₄/CS and CePO₄/CS/GO scaffolds, many CePO₄ nanorods were uniformly dispersed on the films (Fig. 2e and h). The GO nanosheets were not obviously detected in the CePO₄/CS/GO scaffolds because of small particle sizes and low percentages (Fig. 2 h). The chemical elements in the CS, CePO₄/CS and CePO₄/CS/GO scaffolds were detected by EDS patterns (Fig. 2c, f and i). The Ce and P were originated from the CePO₄ nanorods, C was originated from CS or/and GO (Fig. 2c, f and i). Notably, the Ce, P and C element distribution maps further demonstrated that the CePO₄ nanorods and GO nanosheets were uniformly distributed throughout the CePO₄/CS/GO scaffolds (Fig. 2j–m).

The XRD patterns of the CePO₄/CS and CePO₄/CS/GO scaffolds was much similar to the pure CePO₄ nanorods (Fig. 1e). Notably, only CePO₄ characteristic peaks were detected in the XRD patterns of CePO₄/CS/GO scaffolds, which was ascribed to the following two reasons: (i) CS showed amorphous characteristic, as confirmed by the XRD pattern of CS scaffolds (Fig. 1e); (ii) the percentage of the GO nanosheets in the scaffolds was only approximately 2.9%. The functional groups of the CePO₄/CS and CePO₄/CS/GO scaffolds were demonstrated by FTIR spectra (Fig. 1f). The characteristic bands of CS were detected in the FTIR spectra of the CS, CePO₄/CS and CePO₄/CS/GO scaffolds, including C = N vibration (1636 cm⁻¹), C-N vibration (1409/1320 cm⁻¹), bridge oxygen stretching vibration (1152 cm⁻¹), N–H deformation vibration (1547 cm⁻¹), C-O stretching vibration (1025/1072 cm⁻¹), N–H wagging vibration (892 cm⁻¹). The characteristic bands of CePO₄ nanorods were detected in the FTIR spectra of the CePO₄/CS and CePO₄/CS/GO scaffolds, too (Fig. 1f). The bands due to GO were not observed in the FTIR spectrum of the CePO₄/CS/GO scaffolds due to the low percentages, which was in good agreement with the XRD results (Fig. 1e, f). Figure 3a showed the Ce3d XPS pattern of CePO₄ nanorods in the CePO₄/CS/GO scaffolds. The peaks at 882.1 and 885.8 eV corresponded to the Ce3d_5/2, and those at 900.5 and 903.9 eV corresponded to Ce3d_3/2. All the above peaks were assigned to Ce³⁺ ions, suggesting that the Ce ions in the CePO₄ nanorods existed as trivalent states without Ce⁴⁺.

In order to assay the release performances of CePO₄/CS/GO scaffolds in vitro, the samples were immersed in ultrapure water. With increasing the soaking time, the Ce³⁺ ions were continuously released from the scaffolds (Fig. 3b). Notably, the Ce³⁺ ions showed quick release performance within 48 h, and then gradually arrived at the dissolution-reprecipitation balance. After the release for 120 h, the concentrations of Ce³⁺ ions reached 2.48 μM. The high crystallinity of the CePO₄ nanorods caused the low degradability, resulting in the slow release rates of Ce³⁺ ions (Figs. 1e and 3b).

The mechanical property of CePO₄/CS/GO scaffolds was characterized by microcomputer control electronic universal testing machine, as shown in Additional file 1: Figure S1. Since CS scaffolds possessed a ductile feature, three-dimensional porous structure was easy to cause damage under load-bearing conditions [39]. The combination of CePO₄ nanorods, CS and GO formed the organic/inorganic hybrid scaffolds, leading to a good mechanical property. As the external forces were exerted on the CePO₄/CS/GO scaffolds, the macropore damage and material deformation successively took place (Additional file 1: Figure S1). When the compressive strengths of the CePO₄/CS/GO scaffolds arrived at approximately 0.21 MPa, the macroporous structure was completely destroyed.

As we know, GO possesses excellent light‐absorbing properties and photothermal conversion efficiency. The incorporation of GO nanosheets provided the CePO₄/CS/GO scaffolds with better light adsorption properties in the region of 400–1200 nm than the CS and CePO₄/CS scaffolds (Fig. 3c). With increasing the irradiation time of NIR light, the temperatures in the CS and CePO₄/CS scaffolds rose slightly (Fig. 3d). Interestingly, the temperatures around the CePO₄/CS/GO scaffolds rose rapidly, and arrived at 64.8 ºC after only 10 min, which was high enough to kill tumor cells.

Effects of different scaffold materials against bone metastasis from breast cancer under nir exposure

Figure 4a, b shows the result by live-dead cell staining and flow cytometry cell counting. It was found that the MDA-MB-231 cells in the control, CS and CePO₄/CS control groups were live cells, while those in the CePO₄/CS/GO group were dead cells (green represents live cells and red represents dead cells). The CePO₄/CS/GO scaffolds significantly increased the local temperature under NIR light compared to the groups without GO nanoparticles. Figure 4c illustrates the results of the statistical analysis of the flow cytometry. The degree of apoptosis resulting from the NIR exposure was different in each group, with the highest number of dead cells in the CePO₄/CS/GO group. Figure 4d shows the proliferation of MDA-MB-231 cells cultured with different scaffolds while under NIR exposure. From day 1 to day 4, the survival of the control, CS and CePO₄/CS groups increased with the culturing time, but the survival of the CePO₄/CS/GO group decreased. This result suggested that the proliferation of MDA-MB-231 cells in the CePO₄/CS/GO group was inhibited under NIR exposure.

In vivo, Scaffolds with different materials were then implanted into the mice. All scaffolds were exposed to NIR light within 30 s. The temperature of the implanted scaffold was measured by thermal imaging (Fig. 5a). As shown in Fig. 5b, the temperature in the CePO₄/CS/GO group was higher than those in the other groups: the temperature reached as high as 52 degrees, while the highest among the other groups was only 41 degrees. After the second week, IVIS Lumina K Series III was employed for florescence measurements on the mice. The florescence intensity was measured again after 2 weeks of NIR exposure (Fig. 5c). Compared with the control, CS and CePO₄/CS groups, the red fluorescence intensity in the CePO₄/CS/GO group began to decrease with prolonging the therapy time (Fig. 5d). This result indicated that CePO₄/CS/GO could significantly inhibit tumour cell proliferation. After the measurements, the mice were euthanized, followed by the removal of the tumours and the measurement of the tumour sizes. As shown in Fig. 5e, f the tumour size of the CePO₄/CS/GO group was significantly smaller than those of the other three groups. Figure 5 g shows the TUNEL staining and caspase-3 staining of the tumours, which reveal the degree of the tumour cell apoptosis. Apoptosis was observed in the CePO₄/CS/GO group but not in the other group.

Effects of different scaffold materials on the degree of polarization of RAW264.7 cells

The RAW cells were cultured with control, CS, CePO4/CS, and CePO4/CS/GO scaffolds. After 24 h of culture, RAW cells were added with the primary antibodies (CD206 represents M2 macrophages and CD16/32 represents M1 macrophages) and incubated overnight. The color-labeling secondary antibodies were added and incubated for 1 h, and the samples were then observed with a confocal microscope. The immunofluorescence intensities of the CePO4/CS and CePO4/CS/GO were observed (Fig. 6a), and the florescence intensity of CD206 was significantly higher than those of the other two groups, which suggested that the cells of these groups polarized into M2 macrophages. The results of the flow cytometry are also provided (Fig. 6b, c), which shows the effects of different scaffold materials on the polarization of macrophages. It was found that the macrophages did not differentiate into M2 macrophages in the control and CS groups, but they did in the presence of Ce. Figure 6d, e illustrates the results of different scaffolds on the polarization of macrophages. In vivo experiments indicate that the control and CS group do not promote macrophage polarization in the M2 direction. However, the scaffold material of the CePO₄/CS and CePO₄/CS/GO groups can promote the M2 direction polarization of macrophages. We know that M2 macrophages can promote the formation of blood vessels [34, 36]. and promote the mineralization of osteoblasts [35, 37].

Study on the toxicity and osteo-inductivity of scaffold materials to MC3T3-E1 cells

The freeze-drying technology was employed to fabricate the CePO₄/CS/GO porous scaffolds, in which CePO₄ nanorods and GO nanosheets were dispersed through the whole scaffolds (Fig. 1). Rare earth elements (REEs), for example Ce, could accumulate in human bones mainly by substituting parts of Ca²⁺ ions in apatite. The biological responses of the REEs represented the hermetic concentration–response relationship, namely, the low concentrations showed positive stimulation and the high concentrations showed inhibition effects against normal cells. Fortunately, the CePO₄/CS/GO scaffolds had the controlled release performances of Ce³⁺ ions because of the appropriate biodegradability, and the Ce³⁺ concentrations were kept at only 2.48 μM even after 120 h. The low concentrations of Ce³⁺ ions did not do harm to hBMSCs and MC3T3-E1 cells, and even contributed to cell proliferation (Fig. 7a). Moreover, the 3D microporous in the scaffolds facilitated the cell migration, and the degree of the hBMSCs’ adhesion on the surface of the CS, CePO₄/CS, and CePO₄/CS/GO scaffolds and their morphological characteristics were observed by SEM (Fig. 7b). In vitro assays demonstrated that the CePO₄/CS/GO porous scaffolds had excellent biocompatibility.

The effects of the CS, CePO₄/CS, and CePO₄/CS/GO scaffolds on osteo-inductivity were studied via ALP staining, alizarin red staining, PCR, and western blot. An ALP staining image of the MC3T3-E1 cells of the control group is provided in Fig. 7c. The cells of this group were cultured with CS, CePO₄/CS, and CePO₄/CS/GO for 7 days and extracted. The number of ALP-stained cells of the CePO₄/CS and CePO₄/CS/GO group was significantly higher than those of the control and CS groups. Figure 7d illustrates the calcium deposition of the groups cultured with the control, CS, CePO₄/CS, and CePO₄/CS/GO scaffolds. Compared to the CS and control groups, the calcium deposition of the CePO₄/CS and CePO₄/CS/GO groups was significantly increased. The osteoblast activity of the CS, CePO₄/CS, and CePO₄/CS/GO groups was analysed by RT-PCR based on the expression levels of the ALP, BMP-2, OCN, and RUNX2 genes in the early osteoblasts (Fig. 7e). The expression levels of the ALP, BMP-2, OCN, and RUNX2 genes were the highest in the CePO₄/CS, and CePO₄/CS/GO group. Further, the western blot results of the osteogenesis-associated proteins are provided in Fig. 7f. The expression levels of the BMP-2, P-Smad1/5, Smad1/5, RUNX2 and COL1 proteins were higher in the CePO₄/CS and CePO₄/CS/GO groups compared to the other groups. In vivo, it was seen in the micro-CT images that the volume of newly generated bone tissue was higher in the CePO₄/CS and CePO₄/CS/GO groups than in the control group. Compared to CS, CePO₄/CS and CePO₄/CS/GO could effectively promote the formation of new bone (Fig. 7 g). A quantitative analysis of the morphology of the CePO₄/CS (48.15 ± 4.21%) and CePO₄/CS/GO (58.67 ± 3.32%) groups showed that the bone volume/tissue volume (BV/TV) ratios were higher than those of the control group (9.81 ± 3.26%) and CS group (21.21 ± 2.95%) (Fig. 7 h). Compared to the control and CS groups, the bone mineral densities of the CePO₄/CS and CePO₄/CS/GO groups were higher (Fig. 7i).

To investigate the mineralization of osteoblasts, the florescence labelling agents alizarin red and calcein were injected at different times prior to sacrificing the mice. The first line represents data from calcein, which suggests that bone mineralization occurred 21 days prior to sacrificing the mice. The second line represents data from alizarin red, which suggests that bone mineralization occurred 3 days prior to sacrificing the mice. The average distance between the two lines represent the newly formed bone tissue (Fig. 8a). The bone mineralization rate was analysed by a PC-based analysis system, and the calculated ratios for the CePO₄/CS and CePO₄/CS/GO groups, 5.38 ± 0.68 μm/d and 6.54 ± 0.52 μm/d, respectively, were significantly higher than those of the CS (2.34 ± 0.32 μm/d) and control groups (1.98 ± 0.48 μm/d) (Fig. 8b). Figure 8c, d illustrate the results of the HE staining and Masson staining for the investigation of the bone and collagen components of the four groups. An immunohistochemical analysis of VEGF was performed. This property was confirmed by immunohistochemical analysis of VEGF in tissues (Fig. 8e). It was found that the amount of VEGF proteins was significantly increased in the CePO₄/CS and CePO₄/CS/GO groups compared with the other two groups.