The collagen films used as substrates for the cell culture studies have a fibrillar structure as seen by scanning electron microscopy (Fig. 1). At one day after plating, the singly dissociated hESCs and hiPSCs were uniformly attached to the collagen coating. At 10 days after plating, however, only several isolated colonies remained in the cultures on the collagen coating and the colonies were predominantly located at the edge of the culture wells. Most of the interior region of the culture well was devoid of cells. The cells within the colonies on collagen had a spindle-like morphology (Fig. 2A). In contrast, the cells on the control surface of tissue culture treated polystyrene attached and grew more robustly, and formed a tight monolayer throughout the well by day 10 (Fig. 2B). The cells on tissue culture polystyrene did not have a spindle-shaped morphology, and instead featured tight junction-like structures characteristic of epithelial cells (Fig. 2B inset). After the cells cultured on the collagen coatings were trypsinized and sub-cultured onto new collagen films, they had a uniform fibroblastic-like morphology (Fig. 2C). H9-hESCs and YK26-iPSCs demonstrated similar substrate dependent attachment and morphological changes during the derivation process with more cells attaching and growing more robustly on tissue culture plastic. Repeated passaging of the cells on tissue culture polystyrene did not cause any change in morphology – the cells remained tightly packed with an epithelial morphology.

Plating the pluripotent cells as colonies, which is the common method for passaging hESCs and iPSCs, did not induce the cells to attain a spindle-shape morphology on either the collagen coating or the control tissue culture plate in this medium. A representative image of the 10 day cultures of H9-hESCs plated as colonies are shown Fig. 2D. A mixture of cell types with various morphologies growing in monolayers in some areas while also forming multi-cellular macrostructures protruding up into the medium was observed in the cultures plated as colonies. This occurred for both H9-hESCs and the YK26-iPSCs. We interpret these varied morphologies as a signature of uncontrolled spontaneous differentiation into multiple cell types that should be avoided when generating a homogeneous progenitor population.

Flow cytometry was performed on the pluripotent cells that were differentiated through the process of being passaged twice on the collagen coating. The antigens CD73, CD90, CD105, CD146 and CD166 known to be present on adult marrow derived MSCs [9] were expressed by a high percentage of the differentiated pluripotent stem cell populations (Fig. 3). The hematopoietic markers CD34 and CD45 were detected at levels below 1% (Fig. 3) as expected for MSCs. The expression of CD90 was low relative to the other markers at passage two, 67.5% and 82.9%, for the H9 and iPS-YK26, respectively. However, after 4 passages, the expression of CD90 increased to 94.9% and 96.9% for H9-ESCs and YK26-iPSCs, respectively. Because the cells derived on collagen express a surface antigen profile similar to human bone marrow derived MSCs and have a fibroblastic morphology similar to MSCs, we refer to them as MSC-like cells. Note that the MSC-like cells derived from both the H9-hECs and YK26-iPSCs shared a very similar surface antigen profile.

Evidence of the multi-potentiality of the derived cells was assessed through tri-lineage differentiation experiments including osteogenic, chondrogenic and adipogenic. The MSC-like cells derived on fibrillar collagen attached and grew robustly when passaged onto tissue culture treated plates for the osteogenic differentiation studies. There was no obvious difference in attachment or growth between the cells derived from H9-hESCs or YK26-iPSCs (Fig. 4A,B). After 35 days in osteogenic medium, mineral deposition was detected in both cultures by xylenol orange (XO) staining (Fig. 4A,B). No XO staining was found in undifferentiated H9-hESCs and YK26-iPSC cells cultured under identical osteogenic conditions. The positive XO staining indicates the presence of calcium-containing mineral deposition in the cultures which is expected during osteogenic differentiation. Gene expression of the MSC-like cells was assessed before and after osteogenic differentiation. In comparison to the undifferentiated hESCs and hiPSCs, the MSC-like cells before exposure to osteogenic medium showed significantly greater expression of RUNX2 and COL1A1 genes, but not alkaline phosphatase (ALP) gene (Fig. 4C). Initially, the ALP gene expression was 1.5–2 fold less than that of hESCs and hiPSCs which is expected since ALP expression is very high in undifferentiated pluripotent cells. After 35 days of exposure to osteogenic medium, ALP expression was up-regulated by 4–6 fold in MSC-like cells, while RUNX2 and COL1A1 were maintained at significantly high levels (Fig. 4C). ALP expression is generally regarded as an early indicator of osteogenic differentiation. Osteocalcin (OC) and bone sialoprotein (BSP) gene expression was not detected, which are markers for late stage matrix-producing osteoblasts indicating the cells did not progress completely to mature osteoblasts under these culture conditions.

The multi-lineage potential of the MSC-like cells derived from pluripotent cells was further assayed in a chondrogenic differentiation assay performed in pellet cultures. After 21 days of culturing in chondrogenic medium, a cartilage-like glycosaminoglycan-rich matrix which stained positively with alcian blue was detected throughout the histological sections of the pellet (Fig. 5A,B). Since the cells are cultured in pellets, individual cells are not clearly visualized in the multi-cellular pellet sections. To further confirm that both cell types formed a cartilaginous matrix, the sections were immunochemically stained for aggrecan and collagen type II proteins. Both molecules were prevalent throughout the sections of both cultures (Fig. 5A,B). No immunostaining was detected in the negative controls (Fig. 5C). At 21 days, expression of SOX9, COL2A1 and ACAN genes was significantly up-regulated in pellet cultures (Fig. 5D). SOX9 was present in low amounts in undifferentiated hESCs and the MSC-like cells before the chondrogenic differentiation protocol. COL2A1 and aggrecan (ACAN) genes were not detected in the undifferentiated hESCs or in the MSC-like cells before exposure to the chondrogenic differentiation medium. The expression of SOX9 gene in the pellet cultures increased by 14–18 fold compared to the undifferentiated MSC-like cells derived from both H9 and YK26-iPSCs.

Adipogenic differentiation was conducted on tissue culture plates. In response to the insulin stimulation, the MSC-like cells displayed significant lipid accumulation in the cytoplasm which was positively stained with Oil Red O (Fig. 6A,B). The upregulation of the expression of the FABP4 gene further confirmed adipogenic differentiation capability (Fig. 6C). PPARγ was upregulated relative to undifferentiated hESCs, but not enhanced by the adipogenic differentiation protocol. No obvious difference was noticed between cultures derived from H9 hESCs and YK26 iPSCs.

Purified bovine Type I collagen monomer stabilized in an acidic solution (PureCol, Inamed Biomaterials, CA) was used at a concentration of 300 µg/ml to prepare biomimetic fibrillar collagen coatings following a protocol developed by the National Institute of Science and Technology (NIST) [27]. Briefly, the collagen was diluted into a phosphate buffered saline solution (PBS) consisting of 1× PBS: 0.1 M NaOH:10× PBS: 3 mg/ml collagen stock solution at a 70∶1∶1∶8 ratio (vol∶vol) in a 50 ml conical tube. The collagen stock solution was added last to minimize the formation of insoluble aggregates. One ml of the diluted solution was added per well in 12-well non-tissue culture plates. After incubation at 37°C in humidified air with 5% CO₂ for 12–21 hours, the gel-like supernatant was aspirated from the plates and the coated surfaces were rinsed with PBS twice. 1 ml PBS was added to each well to cover the coatings. The coated plates were sealed and stored at 4°C for later use. The coating typically comprised of Type I collagen fibrils of ∼250 nm in thickness and several microns in length (Fig. 1).

H9 hESCs (WiCell, Madison, WI, USA) and human induced pluripotent stem cell line HDFa-YK26 (YK26-iPSCs; Stem Cells Core at UConn Health Center) [38] were maintained on Matrigel™ (BD Biosciences, Mountain View, CA) and fed with mouse embryonic fibroblast (MEF)-conditioned medium supplemented with 4 ng/ml bFGF (Invitrogen). The basal medium used for preparing the MEF-conditioned medium contained basal Dulbecco's modified Eagle's medium (DMEM)/F-12, 20% knockout serum replacement, 2 mM nonessential amino acids, 2 mM L-glutamine (all from Invitrogen, Carlsbad, CA), and 0.1 mM beta-mercaptoethanol (Sigma-Aldrich, St. Louis, MO). MEF cells were mitotically inactivated by gamma irradiation (irr-MEF) for producing the MEF-conditioned medium used to culture the hESCs and hiPSCs prior to the derivation step [39]. The maintenance medium was replenished daily for the hESCs and hiPSCs culture. H9 cells at passage 47 and YK26-iPSCs at passage 67 were used for the derivation.

Before dissociation, H9-hESCs and YK26-iPSCs, maintained on Matrigel™, were treated with 10 uM ROCK inhibitor Y-27632 in maintenance medium for 1 hour. Colonies were then dissociated into single cells after incubating with 1 ml Accutase® per well for 10 minutes in a 37°C incubator. The cells were spun down and re-suspended in the maintenance medium supplemented with 10 uM ROCK inhibitor Y-27632. The single cells were seeded onto the collagen coating at a density of 15,000/cm² in the maintenance medium. After 24 hours, the maintenance medium was supplemented with an equal volume of the derivation medium which contained basal alpha-MEM (Invitrogen), 10% FBS (Hyclone), 100 U/ml penicillin and 100 ug/ml streptomycin (Invitrogen), 100 nM dexamethasone (Sigma-Aldrich) and 50 uM magnesium L-ascorbic acid phosphate (Sigma-Aldrich). After incubation for two more days, the medium was replenished with the derivation medium and changed every 3–4 days thereafter. At 10 days, the cells were harvested and labeled as passage zero (P0). The cells were expanded on new collagen coating using an expansion medium containing alpha-MEM (Invitrogen), 10% MSC-qualified FBS (Hyclone), 100 U/ml penicillin and 100 ug/ml streptomycin, 2 mM L-glutamine and 0.1 mM non-essential amino acid (all from Invitrogen). The expansion medium was replenished every 3–4 days. Cells were passaged upon subconfluency, usually within 5–7 days, at a 1∶3 split ratio. The second passage (P2) was used for the tri-lineage differentiation evaluation and flow cytometry analysis.

In control studies, the singly dissociated hESCs and iPSCs were plated onto tissue culture-treated polystyrene (conventional tissue culture plates) instead of the collagen coating, but otherwise with the same manipulation of the cells as described above. In other controls, hESC and iPSC colonies instead of dissociated cells were plated and cultured on both tissue culture plates and collagen coatings. In these studies, the cells were not treated with ROCK inhibitor Y-27632 since intact colonies of pluripotent cells survive well after passaging.

The cells derived on the collagen coatings were passaged on the collagen coating (P2), then the surface antigen profile was probed by flow cytometry. A panel of surface markers typical for characterizing human MSCs was used, including: CD73, CD90, CD105, CD146, CD166, CD34 and CD45 [8]. Surface antigen profiles were analyzed on a BD LSR II Flow Cytometer (Becton-Dickinson, San Jose, CA). Cells at or near confluence were harvested from the collagen coating using 0.05% Trysin-EDTA and washed twice in PBS containing 15% fetal bovine serum (FBS, Invitrogen). After filtering through a 70 um cell strainer, cells were spun down and then re-suspended in staining medium containing 1× HBSS, 10 mM HEPES at pH 7.4 and 2% FBS. Cells were separately labeled with fluorochrome-conjugated antibodies including phycoerythrin (PE) conjugated anti-human CD73 antibody (BD Pharmingen), FITC conjugated anti-human CD90 (Thy1) antibody (eBioscience), PE conjugated anti-human CD105 antibody (eBioscience), Alexa Fluor 647 conjugated anti-human CD146 (Biolegend), PE conjugated anti-human CD166 (Biolegend), FITC conjugated anti-human Stro-1 (Biolegend), FITC conjugated anti-human CD34 antibody (BD Pharmingen), Pacific Blue (PB) conjugated anti-human CD45 antibody (eBioscience). After a 45 minute incubation, cells were washed twice with staining buffer. Unstained cells were used as a control. At least 10,000 events were acquired for each sample. The data were analyzed using FlowJo software (Tree Star Inc, Ashland, OR).

The functional differentiation ability of the derived MSC-like cells was tested in vitro. The osteogenic medium contained alpha-MEM (Invitrogen), 10% FBS (Hyclone), 100 U/mlpenicillin and 100 ug/ml streptomycin (Invitrogen), 100 nM dexamethasone (Sigma-Aldrich), 50 uM magnisum L-ascorbic acid-phosphate (Sigma-Aldrich), and 4 mM beta-glycerophosphate (Sigma-Aldrich). Cells were seeded at density of 30,000/cm² in 12 well tissue culture plates (Falcon, Becton-Dickinson, NJ). Three replicates were analyzed for each assay. The medium was replenished every 3–4 days. Mineral deposition in the osteogenic cultures was detected by staining with 20 ug/ml xylenol orange (XO) supplemented to the culture medium 24 hours before analysis. XO is a fluorescent dye that has been used for labeling of calcium phosphate mineral deposition in osteogenic cultures [40]. Positive staining was visualized using fluorescence microscopy.

Chondrogenic differentiation assays were performed using a standard pellet culture method [41]. The chondrogenic medium contained high glucose DMEM (Invitrogen), 1% ITS+Premix (Becton-Dickinson), 100 mM sodium pyruvate (Invitrogen), 10 ng/ml TGF- β1 (Peprotech), 100 nM dexamethasone (Sigma-Aldrich), 120 uM magnesium L-ascorbic acid-phosphate (Sigma-Aldrich), and 100 U/ml penicillin and 100 ug/ml streptomycin (Sigma-Aldrich). The pellets were formed in 5 ml polypropylene tubes (Becton-Dickinson) by centrifugation of 200,000 cells at 600×g for 5 min. Three replicates were analyzed for each assay. Medium was changed every 3–4 days. Histological examination was performed on frozen sections of the chondrogenic pellets. Pellets were fixed in 10% neutral buffered formalin. The sections were prepared by embedding the fixed pellets in OCT (Tissue-Tek, Ted Pella Inc, CA) and 7 um sections were made using a Cryostat (Leica Microsystems Inc, Bannockburn, IL). Sections were stained with alcian blue solution which was prepared by adding 1 g alcian blue 8 GX (Sigma-Aldrich) to 100 ml 3% acetic acid solution at pH 2.5. The sections or pellets were soaked in alcian blue for 30 minutes, followed by rinsing with pH 1.0 acetic acid once and pH 2.5 acetic acid twice. For immunohistochemical analysis, sections were treated for 30 min at 37°C in 0.05% Trypsin (Invitrogen). Endogenous peroxidase activity was quenched by incubation with 3% hydrogen peroxide (Sigma-Aldrich) for 10 minutes at room temperature. Primary antibodies raised against aggrecan (cat# sc-16492) and COL1A1 (cat# sc-28887) (both from Santa Cruz Biotechnology Inc, CA) were added at 1∶50 dilution and incubated for 1 hour at 37°C. The biotin conjugated secondary antibodies recognizing immunoglobin of either goat (Cat#305-065-045) or rabbit (Cat#111-065-003) (both are from Jackson ImmunoResearch Laboratories Inc, West Grove, PA) were added at 1∶1000 dilution and incubated for 1 hour at 37°C. Streptavidin-conjugated horseradish peroxidase (HRP) from an ultra-sensitive ABC peroxidase staining kit (Pierce, Rockford, IL) was added to react with the biotin conjugated secondary antibody for 30 minutes at 37°C, then a diaminobenzidine (DAB) chromogenic subtrate kit (Pierce, Rockford, IL) was used to develop the staining.

The adipogenic differentiation medium consisted of high glucose DMEM (Invitrogen) supplemented with 10% FBS (Hyclone), 1 uM dexamethasone (Sigma-Aldrich), 100 uM indomethacin (Sigma-Aldrich), 500 uM 3-isobutyl-1-methylxanthin (IBMX) (Sigma-Aldrich), and 10 ug/ml insulin (Sigma-Aldrich), and 1% penicillin and streptamycin (Invitrogen). Cells were seeded at a density of 15,000/cm² in 12 well tissue culture plates (Falcon, Becton-Dickinson). Medium was replenished very 3–4 days. Lipid production in the 21 day adipogenic cultures was examined with Oil Red O (ORO) staining. The staining solution was prepared by dissolving 0.7 g Oil Red powder (Sigma) in 200 ml of isopropanol (Sigma-Aldrich), followed by dilution with distilled water at a ratio of 3∶2 (3 parts Oil Red O stock: 2 parts distilled water). Cells were fixed with 10% formalin for 5 minutes at room temperature, then stained with Oil Red-O for approximately 10 minutes, followed by rinsing once with 60% isopropanol and then water.

RNA was extracted using Trizol (Invitrogen) according to the manufacturer. Genomic DNA was removed by treatment with DNase I following the manufacturer manual (Invitrogen). Total 10 µg of RNA was used for cDNA synthesis using the High Capacity cDNA Reverse Transcription Kit (Applied Biosystems, Foster City, CA) performed with the iCycler® Thermal Cycler (Bio-Rad Laboratories, Richard, CA) following the manufacturer's instructions. TaqMan Gene Expression Assays for RUNX2 (Hs00231692_m1), COL1A1 (Hs00164004_m1), ALP (Hs00758162_m1), OC (Hs01587813_g1), BSP (Hs00913377_m1), SOX9 (Hs00165814_m1), COL2A1 (Hs00264051_m1), ACAN (Hs00153936_m1), COL10A1 (Hs00166657_m1) and GAPDH (Hs99999905_m1) were purchased from Applied Biosystems. Quantitative RT-PCR reactions were carried out on an ABI HT7900 system (Applied Biosystems) following the manufacturer's protocol. Quantification was performed with the Delta-Delta Ct method using GAPDH as an internal control.

For adipogenic gene analysis quantitative PCR was carried out using the SYBR Green PCR master mix platform (ABI). Primer pairs for GAPDH (GCACCGTCAAGGCTGAGAAC; ATGGTGGTGAAGACGCCAGT) and PPARγ (TGCCAAAAGCATTCCTGGTT; TCGCTGTCATCTAATTCCAGTGC) [42] and FABP4 (ACTGGGCCAGGAATTTGACG; CCCCATCTAAGGTTATGGTGCTC) retrieved from PrimerBank [43] (PrimerBank ID: 168480125b1) were used.