A high-throughput biomimetic bone-on-a-chip platform with artificial intelligence-assisted image analysis for osteoporosis drug testing

Abstract

Although numerous organ-on-a-chips have been developed, bone-on-a-chip platforms have rarely been reported because of the high complexity of the bone microenvironment. With an increase in the elderly population, a high-risk group for bone-related diseases such as osteoporosis, it is essential to develop a precise bone-mimicking model for efficient drug screening and accurate evaluation in preclinical studies. Here, we developed a high-throughput biomimetic bone-on-a-chip platform combined with an artificial intelligence (AI)-based image analysis system. To recapitulate the key aspects of natural bone microenvironment, mouse osteocytes (IDG-SW3) and osteoblasts (MC3T3-E1) were cocultured within the osteoblast-derived decellularized extracellular matrix (OB-dECM) built in a well plate-based three-dimensional gel unit. This platform spatiotemporally and configurationally mimics the characteristics of the structural bone unit, known as the osteon. Combinations of native and bioactive ingredients obtained from the OB-dECM and coculture of two types of bone cells synergistically enhanced osteogenic functions such as osteocyte differentiation and osteoblast maturation. This platform provides a uniform and transparent imaging window that facilitates the observation of cell-cell interactions and features high-throughput bone units in a well plate that is compatible with a high-content screening system, enabling fast and easy drug tests. The drug efficacy of anti-SOST antibody, which is a newly developed osteoporosis drug for bone formation, was tested via β-catenin translocation analysis, and the performance of the platform was evaluated using AI-based deep learning analysis. This platform could be a cutting-edge translational tool for bone-related diseases and an efficient alternative to bone models for the development of promising drugs.

Keywords: bone formation; bone‐on‐a‐chip; deep learning; drug testing; high‐throughput analysis; osteoporosis.

FIGURE 1

Schematic overview of a biomimetic bone‐on‐a‐chip platform combined with AI‐assisted image analysis for high‐throughput drug testing. (a) Illustration of 3D osteon niche of bone in vivo. (b) The configurational mimicking of bone in the biomimetic bone‐on‐a‐chip platform. Immature osteocytes were embedded in collagen and OB‐dECM composite (Col/OB‐dECM) within a chip, and preosteoblasts were cocultured in a region around the chip. Both cells were differentiated and matured to bone in bone‐on‐a‐chips built in a well plate. (c) Illustration of osteoporosis drug testing based on this platform and image data analysis using deep learning algorithms. 3D, three‐dimensional; AI, artificial intelligence; OB‐dECM, osteoblast‐derived decellularized extracellular matrix

FIGURE 2

Optimization and characterization of cell‐laden OB‐dECM hydrogel in a bone‐on‐a‐chip. (a) Viability of IDG‐SW3 cells cultured in a hydrogel with different collagen/OB‐dECM ratios on Day 3 (N = 3). (b) Representative microscopic images of hydrogel shrinkage (white dotted line with arrows) according to collagen/OB‐dECM ratios on Day 3. Scale bar represents 500 μm. (c) Young's modulus and (d) storage modulus of the optimized Col/OB‐dECM hydrogel compared to the collagen hydrogel (N = 5). All values are expressed as mean ± SD (**p < 0.01, ****p < 0.0001). OB‐dECM, osteoblast‐derived decellularized extracellular matrix

FIGURE 3

Effect of OB‐dECM on osteogenic differentiation and maturation of IDG‐SW3 cells in a bone‐on‐a‐chip. (a) A schematic showing the strategy for cell–ECM interaction using Col/OB‐dECM simulating an in vivo osteon. (b and c) Relative gene expression levels of early osteocyte differentiation markers (ALP, PDPN, and PHEX) and late osteocyte differentiation markers (DMP1, SOST, and FGF23) in IDG‐SW3 cells according to the gel type (collagen or Col/OB‐dECM). Assays were performed on Days 7 and 14 after differentiation of osteocytes within gel (N = 3). GAPDH was used as an internal control. (d) Morphological changes and alignment of IDG‐SW3 cells differentiated in collagen or Col/OB‐dECM hydrogels for 14 days (N = 3). The area enclosed in a white box in the images above was enlarged in the images below. The cells were immunostained against F‐actin (Alexa Fluor 594, red). (e) Nuclear shape index (NSI) and alignment angle of IDG‐SW3 cells analyzed using the representative confocal images (Figure S5) (Col, n = 66; Col/OB‐dECM, n = 70). (f) A schematic representing the implicit role of Cx43 on cellular function of osteocytes through cell–cell and cell–ECM interactions. (g) Cx43 protein level expressed in IDG‐SW3 cells according to the gel type. Assays were performed using ELISA on Days 7 and 14 after differentiation (N = 3). All values are expressed as mean ± SD (*p < 0.05, **p < 0.01). OB‐dECM, osteoblast‐derived decellularized extracellular matrix; ELISA, enzyme‐linked immunosorbent assay

FIGURE 4

Effect of osteocyte and osteoblast coculture in a bone‐on‐a‐chip. (a–c) The osteocyte differentiation of IDG‐SW3 cells was affected upon coculture with MC3T3‐E1 cells. Relative gene expression levels of early differentiation markers (ALP, PDPN, and PHEX) and late differentiation markers (DMP1, SOST, and FGF23) in IDG‐SW3 cells monocultured or cocultured with MC3T3‐E1 cells on (a) Day 7 and (b) Day 14 after culture (N = 3). GAPDH was used as an internal control. (c) The ALP protein level of IDG‐SW3 cells in mono or cocultured groups measured using an ALP quantification assay on Day 7 and Day 14 after culture (N = 3). (d–g) The proliferation and osteoblastogenic differentiation of MC3T3‐E1 cells was affected upon coculture with IDG‐SW3 cells. (d) Representative immunofluorescence images showing staining against F‐actin (green) and nucleus (blue) of MC3T3‐E1 cells in monoculture or coculture groups on Day 7. (e) Proliferation rate of MC3T3‐E1 cells cocultured with IDG‐SW3 cells during 7 days measured using a CCK‐8 assay (N = 3). (f and g) Relative gene expression levels of proliferation markers (Cyclin D1, c‐Myc, and CTNNB1) and osteoblast differentiation markers (Runx2, Osx, and OPG) in MC3T3‐E1 cells monocultured or cocultured with IDG‐SW3 cells on (f) Day 7 and (g) Day 14 after culture (N = 3). GAPDH was used as an internal control. All values are expressed as mean ± SD (*p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001). CCK‐8, Cell Counting Kit‐8

FIGURE 5

A comparison of the contribution of a bone‐on‐a‐chip and a Transwell system to bone maturation in osteocytes and osteoblasts. (a) Schematic illustration showing the difference in spatial structure between a bone‐on‐a‐chip and a Transwell system for coculturing osteocytes and osteoblasts. (b) Relative gene expression levels of early osteocyte markers (ALP, PDPN, and PHEX) and late osteocyte markers (DMP1, SOST, and FGF23) in IDG‐SW3 cells in each system on Day 7 (N = 3). IDG‐SW3 cells embedded in gel (1 × 10⁴ cells in 10 μl gel) were cocultured with osteoblasts (500 cells/well). All conditions were the same in both systems. GAPDH was used as an internal control. (c) Proliferation rate of MC3T3‐E1 cells cocultured with IDG‐SW3 cells during 7 days measured using a CCK‐8 assay (N = 3). All values are expressed as mean ± SD (*p < 0.05, **p < 0.01, ****p < 0.0001). CCK‐8, Cell Counting Kit‐8

FIGURE 6

Osteoporosis drug testing using bone‐on‐a‐chip. (a) A schematic showing the Wnt pathway related to bone formation, one of the target mechanisms for osteoporosis treatment. SOST, secreted by osteocytes, downregulates osteoblast proliferation (left image) whereas an anti‐SOST antibody (used as an osteoporosis drug) upregulates osteoblast proliferation through nuclear translocation of β‐catenin via the Wnt pathway (right image). (b) The overall sequential process for osteoporosis drug treatment in the bone‐on‐a‐chip. After 10 days of IDG‐SW3 maturation for SOST secretion, MC3T3‐E1 cells were cocultured for additional 4 days. Cells were treated twice with an osteoporosis drug on Days 10 and 12. (c) Representative images of MC3T3‐E1 cells in osteoporosis drug‐treated and untreated groups that were immunostained against β‐catenin (green) and nucleus (blue). (d) Relative average fluorescence intensity of β‐catenin in cells in each drug‐treated group compared to that in the control (N = 20). (e) Relative β‐catenin nuclear translocation rate in drug‐treated group compared to that in the control (N = 20). (f) The proposed CNN‐based deep learning architecture to perform osteoporosis drug testing. (g and h) Accuracy (left x‐axis) and loss curves (right x‐axis) of CNN training and validation for the (g) BN and (h) BNM datasets with successive epochs. (i) ROC curve analysis comparing classification results in BN and BNM datasets. AUC, area under the ROC curve; BN, β‐catenin and nucleus fluorescence image data; BNM, β‐catenin, nucleus, and their merged image data; CNN, convolutional neural network; ROC, receiver operating characteristic