Functional arrays of human pluripotent stem cell-derived cardiac microtissues

Abstract

To accelerate the cardiac drug discovery pipeline, we set out to develop a platform that would be capable of quantifying tissue-level functions such as contractile force and be amenable to standard multiwell-plate manipulations. We report a 96-well-based array of 3D human pluripotent stem cell (hPSC)-derived cardiac microtissues - termed Cardiac MicroRings (CaMiRi) - in custom 3D-print-molded multiwell plates capable of contractile force measurement. Within each well, two elastomeric microcantilevers are situated above a circumferential ramp. The wells are seeded with cell-laden collagen, which, in response to the gradual slope of the circumferential ramp, self-organizes around tip-gated microcantilevers to form contracting CaMiRi. The contractile force exerted by the CaMiRi is measured and calculated using the deflection of the cantilevers. Platform responses were robust and comparable across wells, and we used it to determine an optimal tissue formulation. We validated the contractile force response of CaMiRi using selected cardiotropic compounds with known effects. Additionally, we developed automated protocols for CaMiRi seeding, image acquisition, and analysis to enable the measurement of contractile force with increased throughput. The unique tissue fabrication properties of the platform, and the consequent effects on tissue function, were demonstrated upon adding hPSC-derived epicardial cells to the system. This platform represents an open-source contractile force screening system useful for drug screening and tissue engineering applications.

Figure 1

Design and manufacture of Cardiac MicroRing (CaMiRi) platform. (A) Process flow of substrate manufacturing. The process started with creating a three-dimensional Computer Aided Design (3D CAD) model of the plate. The design is then printed using an Objet 30 Pro 3D printer to generate a positive mold. A negative PDMS mold is then created which is followed by a complementary positive PDMS mold. This positive PDMS mold is used to then create a polyurethane-based negative master mold which can be used to mold multiple PDMS plates. (B) 3D CAD model of a plate for 3D printing (top panel) and actual 3D-printed mold (bottom panel). Scale bars represent 20 mm. (C) Cross section of a well showing the seeding reservoir where cells are pipetted and the microcantilevers used for force-displacement measurement (empirically calibrated with a force transducer (Micro-Squisher) with tissue anchor points to hold microtissue in place. Scale bars represent 1 mm. (D) Tissue anchor angles and lengths were tested to determine optimal anchor geometry. Scale bars represent 1 mm. (E) Force-displacement curve of cantilevers as measured with the Micro-Squisher. (F) Cell-laden collagen seeded into reservoirs of CaMiRi device remodel into cardiac tissues tethered around microcantilevers within 24 hours. 9 wells of a 96-well plate containing CaMiRi are also shown. Scale bars represent 5 mm. (G) CaMiRi formulated from a range of total input cells (25,000; 50,000; 100,000; and 150,000 cells seeded per well. Scale bars represent 1 mm. (H) Live/dead staining of CaMiRi. From left to right: bright field, nuclei in blue, live cells in green, and dead cells in red. Scale bars represent 1 mm.

Figure 2

Central Composite Design (CCD)-informed formulation of CaMiRi. (A) Contractile force (as measured by cantilever deflection) of cardiac microtissues in all tested conditions, with condition 10 resulting in the highest measured contractile force. Data are reported from three independent experiments, each with three replicates, as the mean ± standard deviation. (B) Representative plots of cantilever deflection of optimal and least optimal conditions. Tissue images are shown in bright field. Scale bars represent 400 µm.

Figure 3

Tissue structure of CaMiRi. (A) Whole mount CaMiRi immunostaining of least optimal condition 7, (B) condition 10, and (C) the optimal condition. DAPI shown in blue, cardiac troponin T (cTnT) shown in green, and vimentin shown in red. Middle row (ii) shows higher magnification of CaMiRi. Final row (iii) shows cTnT in green aligning in parallel with white arrows. Scale bars represent 400 µm, 100 µm, and 50 µm, of images in top, middle, and bottom rows, respectively.

Figure 4

CaMiRi response to cardiotropic drugs and growth factors. Drugs were administered and tissues incubated for 20 minutes before contractile force assay. Along with the vehicle control, up to five drug concentrations of 1 nm, 10 nm, 100 nm, 1 µm, and 10 µm are administered. Data shown are relative change in contraction amplitude due to the administration of (A) Blebbistatin (negative inotrope), (B) Isoproterenol (positive inotrope), and (C) Nifedipine (negative inotrope), as compared to the vehicle control. Data are reported from three independent experiments, each with three replicates, as the mean ± standard deviation. *P < 0.05.

Figure 5

Automated CaMiRi imaging and analysis. (A) Whole well imaged with 2X objective on Molecular Devices Image Xpress Micro 4 under transmitted light (left), after image analysis routine to identify posts (center), and at 20X after identification of right edge of left post (right). (B) Kymograph of post deflection over time, noting calculation of output parameters. (C) Correlation between contraction amplitudes calculated with automated script (y-axis) vs. manual calculations (x-axis) performed on kymographs. (D,E) Response of auto-seeded CaMiRi to isoproterenol (green) and blebbistatin (red). Data are reported from a single trial as the median ± median absolute deviation.

Figure 6

Exploring the effects of epicardial cells in CaMiRi. (A) Cross-sectional schematic of heart wall including epicardium, myocardium, and endocardium shows the complexity of cell types that compose heart wall tissue. (B) Spatial organization and tissue compaction of hPSC-CM and epicardial cells in CaMiRi (top panel is day 0, and bottom panel is day 14). Epicardial fractions of 0% (control), 5%, 9%, 20%, and 33% were used to create tissues. In grayscale (top layer of each panel), bright field is shown of tissues. Green (middle layer) represents hPSC-CM and red (bottom layer) represents hPSC-derived epicardial cells. Scale bars represent 1 mm. (C) Contractile force readings of CaMiRi composed of five different epicardial cell fractions along with associated cFB controls. CaMiRi composed of 33% epicardial fraction failed due to overwhelming tension forces. Data are reported from four independent experiments, each with two to four replicates, as the mean ± standard deviation. *P < 0.05.