Adult stem cells, found in varied tissues such as bone marrow, adipose, and synovium, have the capacity for proliferation and differentiation and are important cell sources for clinical therapy (Brown et al., 2019). However, adult stem cells from different sources have different capacities for proliferation and tissue-specific differentiation (Pizzute et al., 2015). This discrepancy even exists in a single tissue, for example, adipose tissue. Recent evidence indicates that, compared with subcutaneous adipose tissue (ScAT), infrapatellar fat pad (IPFP) is a unique adipose tissue with some distinct features (Sun et al., 2018). ScAT, a fat pad beneath the skin, is becoming an attractive stem cell source for tissue regeneration due to its ease of harvest in large quantities with a minimally invasive procedure (Chu et al., 2019). IPFP, located inside the knee joint and outside the synovial membrane, is becoming a promising stem cell source for cartilage engineering and regeneration (Sun et al., 2018).

In osteoarthritis, IPFP exhibits both anti-inflammatory and pro-inflammatory characteristics (Alegre-Aguarón et al., 2012). Increasing evidence indicates the superiority of IPFP-derived stem cells (IPFSCs) over subcutaneous adipose stem cells (ScASCs) in chondrogenic differentiation capacity (Alegre-Aguarón et al., 2012; Lopa et al., 2014); however, most reports are not donor-matched studies, leading to an uncertain conclusion unless large-scale samples are used. In this study, donor-matched IPFSCs and ScASCs isolated from four New Zealand white rabbits were used for comparison in cell proliferation and tri-lineage differentiation capacities. We hypothesized that adipose stem cells have a depot-dependent lineage preference. Transcriptome and proteome analyses were used to facilitate an in-depth understanding of site-dependent variations of lineage preference.

Adult stem cells have the ability to differentiate into varied lineages. Increasing evidence indicates that adult stem cells from different tissues do not have equivalent ability toward a specific lineage differentiation (Jones and Pei, 2012; Pizzute et al., 2015). However, there is a lack of comparable studies using donor-matched adult stem cells and their matrix microenvironment. In this study, we found that, despite both deriving from adipose tissue, ScASCs and IPFSCs isolated from different depots of four donor-matched rabbits exhibited significant divergence in both proliferation and differentiation potential. Transcriptome and proteomics data provide robust evidence to support our hypothesis that there are site-dependent variations in lineage potential and preference of stem cells from adipose tissue.

Our proliferation data showed that ScASCs grew faster than donor-matched IPFSCs, which might result from higher levels of COL12A1, COL14A1, THBS1, THBS2, and VCAN expression in the matrix proteins deposited by ScASCs. These matrix proteins trend higher in tumor microenvironments and tissues to support proliferative or structurally rigid phenotypes (Wight et al., 2014; Subramanian and Schilling, 2015; Belotti et al., 2016). We also found that IPFSCs expressed significantly higher CD146 than donor-matched ScASCs, which was in line with the gene expression level in RNA-seq data (Log2FC from IPFSCs to ScASCs in CD146/MCAM was 2.62, FDR = 5.7E-07). Regardless of the role as a perivascular marker for adult stem cells (Crisan et al., 2008), a higher level of CD146 expression in adult stem cells might be associated with an advantage in chondrogenic differentiation (Hagmann et al., 2014; Su et al., 2015). Despite the failure to measure expression of surface markers CD90 and CD105 using flow cytometry on both ScASCs and IPFSCs (data not shown), our RNA-seq data indicated that the genes (NT5E, THY1, ENG, and CD44) encoding surface marker proteins (CD73, CD90, CD105, and CD44) were expressed in both cells with NT5E preferentially expressed in ScASCs and CD44 advantageously expressed in IPFSCs. We also found no statistical difference in measured stemness-related genes (NANOG, REX1, NESTIN, and SOX2), indicating that these genes expressed in the donor-matched IPFSCs and ScASCs might not contribute to the discrepancy of a specific lineage differentiation found in this study.

Our differentiation data indicated that IPFSCs exhibited a significantly higher level of chondrogenic markers compared with donor-matched ScASCs. RNA-seq data showed that advantageous genes in IPFSCs can be categorized into several clusters based on functional annotation clustering. For example, the HOX gene, an evolutionarily highly conserved gene family, determines lineage specific differentiation of adult stem cells once tissue damage occurs (Seifert et al., 2015). In this study, HOXD genes, including HOXD9-11 and HOXA10/11, were only dominantly expressed in IPFSCs over donor-matched ScASCs. HOXD genes, one of four grouped HOX clusters (HOXA, HOXB, HOXC, and HOXD) in vertebrates, are suggested to play a role in stem cell based chondrogenesis (Jung and Tsonis, 1998; González-Martín et al., 2014). HOXA11 and HOXD11 double mutant mice had shorter limb formation (Boulet and Capecchi, 2004). Compared with IPFSCs, however, donor-matched ScASCs exhibited robust expression of other HOX genes, such as HOXA4, HOXA5, HOXC4, and HOXC8, which are closely associated with adipogenesis rather than osteogenesis (Levi et al., 2010). An exception is HOXC8 which does not inhibit but retards chondrogenesis, resulting in a boost of proliferating precursor cells and a negative influence on chondrogenesis (Yueh et al., 1998; Cormier et al., 2003).

Another group of conservative transcription factors, TBX family genes, also plays crucial roles throughout development. Our RNA-seq data showed that TBX5, TBX15, and TBX18 were highly expressed in IPFSCs compared to donor-matched ScASCs. TBX5 was reported to activate WNT and fibroblast growth factor (FGF) signaling in upper limb development (Takeuchi et al., 2003). Overexpression of TBX15 in 3T3-L1 preadipocytes impeded adipocyte differentiation and reduced triglyceride content (Gesta et al., 2011). TBX15 and TBX18 co-expressed in the limb mesenchyme indicate their functions during limb development (Tanaka and Tickle, 2004; Singh et al., 2005). Recently, TBX18 was reported to co-express with SOX9 in chondrogenic progenitors and differentiating chondrocytes (Haraguchi et al., 2015). In contrast, TBX1 was reported to be preferentially expressed in the inducible pool of brown adipocytes (beige cells) present in white fat of the inguinal depot (Wu et al., 2012). The above findings indicate that two fat depots, ScAT and IPFP, exhibit distinct HOX and TBX conservative gene expression profiles that likely influence their differentiation preference.

The TGFβ superfamily is composed of two subfamilies; the TGFβ subfamily mainly includes TGFβs (1, 2, and 3) and the BMP subfamily mainly includes BMPs (2, 4-10) (Wang et al., 2014). A considerable amount of in vitro data indicate that TGFβ signaling pathways promote mesenchymal condensation (Barry et al., 2001; Tuli et al., 2003) and the early stages of chondrocyte differentiation, but restrain terminal hypertrophy (Mueller and Tuan, 2008; Shintani et al., 2013). In this study, we found that all TGFβ isotypes (TGFB1, TGFB2, and TGFB3) and latent-TGFB-binding protein 1 (LTBP1) were preferentially expressed in IPFSCs rather than donor-matched ScASCs. However, the protein level showed an opposite trend for TGFB1 and LTBP2, indicating that, while ScASCs have more available bound ligand, IPFSCs may have more free ligand, which needs to be further confirmed. This finding is in line with the advantageous expression in IPFSCs of the combination of SOX5, SOX6, and SOX9 (the SOX trio) that supplies signals sufficient to induce permanent cartilage (Ikeda et al., 2004) and of SOX11 that contributes to the regulation of growth/differentiation factor 5 (GDF5) in joint maintenance (Kan et al., 2013). Our data also showed that only BMP4 exhibited a statistically higher level of expression in IPFSCs compared with donor-matched ScASCs. BMP4 plays an important role in retaining chondrogenic phenotype, through both increasing matrix production and suppressing the production of collagen type X (Reddi, 2001; Steinert et al., 2003). Another important BMP isotype in chondrogenesis, BMP2, was expressed at a higher level in IPFSCs than in donor-matched ScASCs despite no significant difference (FDR = 5.9E-01). Interestingly, BMP3, which was reported to inhibit bone formation by hindering BMP2 activity (Bahamonde and Lyons, 2001), was significantly expressed in ScASCs compared with donor-matched IPFSCs. These findings indicate that IPFSCs have an expression profile consistent with endochondral bone formation over donor-matched ScASCs. The above data support that TGFβ signaling cooperated with BMP signaling in stimulating articular cartilage regeneration (Wang et al., 2014).

Increasing evidence indicates that the canonical Wnt signaling pathway inhibits adipogenesis while the noncanonical Wnt pathway promotes adipogenesis by antagonizing the Wnt/β-catenin pathway (Christodoulides et al., 2009). In accordance with the above findings, we found that preferential expression favoring Wnt/β-catenin signaling genes such as SPARC-related modular calcium binding protein 2 (SMOC2) (Nie and Sage, 2009), low-density lipoprotein receptor-related protein 6 (LRP6) (Peröbner et al., 2012), and Gremlin 2 (GREM2) (Wu et al., 2015) in IFPSCs might be responsible for the inhibition of adipogenesis and the enhancement of chondrogenesis. In contrast, expression inhibiting Wnt/β-catenin signaling genes such as WNT4 (Liu et al., 2016) and nuclear factor of activated T-cells 4 (NFATC4) (Yang et al., 2006) in ScASCs might be responsible for promoting adipogenesis and blocking chondrogenesis (Church et al., 2002).

Interestingly, we found FACIT collagen, such as COL14A1 and COL21A1, was expressed at a higher level in ScASCs rather than IPFSCs. We also found that, despite collagen modifying enzymes detectable in both cells, IPFSCs exhibited significantly higher expression of LOX isoforms and tissue transglutaminase (Log2FC from IPFSCs to ScASCs for TGM2 was 3.68, FDR = 4.9E-06) at both mRNA and protein levels than ScASCs, along with fibrillar collagens COL5A1 and COL5A3, which participate in the formation of a fibrillar collagen network and the regulation of fibrillogenesis (Imamura et al., 2000; Malfait et al., 2005; Lincoln et al., 2006). These findings indicate that IPFSCs are more suitable adipose stem cells for chondrogenesis compared to donor-matched ScASCs. During chondrogenesis, the contents of collagen type II and of non-reducible collagen cross-links were positively linked with tensile biomechanical properties and the functional integrity of cartilage tissues (Williamson et al., 2003). LOX family enzyme activities catalyze the eventual enzymatic conversion that is needed for the generation of biosynthetic collagen cross-links. For example, knockdown studies demonstrated that LOXL2 expression is required for mouse ATDC5 chondroprogenitors’ differentiation toward chondrocytes through regulation of SNAIL and SOX9, two important transcription factors for chondrogenesis (Iftikhar et al., 2011). Interestingly, hypoxia increased LOX gene expression, which promoted pyridinoline cross-links in engineered cartilage (Makris et al., 2013).

Regarding the matrix components, we found that IPFSCs deposited more basement membrane proteins compared to ScASCs, including LAMA1, LAMA3, and HSPG2 at an mRNA level and LAMA5, LAMB1, LAMB2, LAMG1, NID1, and HSPG2 at a protein level. In contrast, NID2 and COL4A5 were significantly more highly expressed in ScASCs compared to donor-matched IPFSCs. Given the function of HSPG2 encoding perlecan as the “factotum” in cartilage (Melrose et al., 2008) and the role of laminins in cartilage regeneration (Sun et al., 2017), NID2 and COL4A5 expression might be associated with adipogenic differentiation, which remains to be elucidated.

Interestingly, matrix turnover enzymes were uniquely preferentially expressed in IPFSCs or ScASCs. For example, matrix metallopeptidase 13 (MMP13), known as collagenase 3, was found exclusively in IPFSCs. The enzyme’s initial role is in tissue remodeling, especially during embryonic development, but it is also highly active in some pathological processes such as osteoarthritis and cancer (Inada et al., 2004; Tardif et al., 2004). In osteoarthritis, MMP13 was highly expressed in chondrocytes and synovial cells responsible for the degradation of cartilage matrix (Inada et al., 2004; Davidson et al., 2006; van den Berg, 2011). However, little is known about MMP13 expression in IPFP, either in healthy donors or in the pathological process. In this study, qPCR data showed that MMP13 was expressed more than 1000-fold higher in IPFSCs than donor-matched ScASCs during cell condensation (day 0 pellet), in accordance with RNA-seq data of cell samples (Log2FC from IPFSCs to ScASCs in MMP13 was 7.45, FDR = 1.4E-16). Interestingly, after an 18-day chondrogenic induction, IPFSCs exhibited a comparable expression of MMP13 to donor-matched ScASCs. From the proteomics analysis, A disintegrin and metalloproteinase with thrombospondin motifs 5 (ADAMTS5) and ADAMTS1 were identified as significantly higher levels in IPFSCs versus a much higher level of ADAMTSL1 (ADAMTS like 1) in ScASCs. The protease profile is likely important for key processing events associated with the physiological role of IPFP in support of the remodeling of articular cartilage, which requires further investigation.

Integrin, a transmembrane receptor, facilitates cell-ECM adhesion. Interestingly, more integrins were advantageously expressed in IPFSCs including ITGA3, ITGA4, ITGA6, ITGA7, and ITGB8 compared to ITGA8, which was superiorly expressed in donor-matched ScASCs. Another transmembrane protein, aquaporin, called the “the plumbing system for cells”, was found to serve as a water channel to rapidly move water through cells. Chondrocytes from articular cartilage are unique due to their sensitivity to water transfer and ionic and osmotic adjustments from the extracellular environment and are responsible for the creation of synovial fluid. A recent report showed that the expression of AQP1 and AQP3 were upregulated during chondrogenic induction of human adipose stem cells, indicative of physiological modification of functionally mature chondrocytes to the local environment (Graziano et al., 2018). This finding was consistent with our data, in which all statistically significant AQP gene expression was advantageously found in IPFSCs rather than donor-matched ScASCs, not only AQP1 and AQP3 but also AQP4 and AQP11.

Furthermore, we found that important clusters associated with cartilage matrix were preferentially expressed in IPFSCs over donor-matched ScASCs. For instance, one of the clusters is glycosaminoglycan (GAG) metabolic and biosynthetic process, including N-Deacetylase And N-Sulfotransferase 1 (NDST1), Polypeptide N-Acetylgalactosaminyltransferase 5 (GALNT5), Biglycan (BGN), Carbohydrate Sulfotransferase 11 (CHST11), Dermatan-sulfate epimerase (DSE), Hyaluronidase-1 (HYAL1), and Inter-alpha-trypsin inhibitor heavy chain H3 (ITIH3), along with GAG binding function cluster, genes of CD44, ACAN, BGN, BMP4, Chemokine (C-C motif) ligand 2 (CCL2), Extracellular matrix protein 2 (ECM2), FGF10, FGFR2, Fibulin 7 (FBLN7), Follistatin-like 1 (FSTL1), Hyaluronan and proteoglycan link protein 1 (HAPLN1), Layilin (LAYN), LPL, procollagen C-endopeptidase enhancer 2 (PCOLCE2), Proline/arginine-rich end leucine-rich repeat protein (PRELP), Superoxide dismutase 3 (SOD3), THBS4, and Toll-like receoptor 2 (TLR2). The CD44 receptor transduces signals on chondrocytes, which is an important mediator of cell-matrix interactions, especially the homeostasis maintained by hyaluronan-CD44 interactions (Knudson and Loeser, 2002). Another crucial cluster is chondroitin sulfate proteoglycan and its metabolic process of which the advantageously expressed genes in IPFSCs include ACAN, BGN, Fibromodulin (FMOD), HSPG2, Syndecan 2 (SDC2), SDC4, IGFI, Cytokine-like 1 (CYTL1), CHST11, CHST15, Chondroitin sulfate N-acetylgalactosaminyltransferase 2 (CSGALNACT2), DSE, and Uronyl 2-sulfotransferase (UST). IGFI encodes insulin-like growth factor-I, which is the predominant anabolic growth factor and decreases matrix catabolism for articular cartilage (Jenniskens et al., 2006). Apparently, IPFSCs naturally express abundant genes involved in the chondrogenesis pathway by modulating cartilage development and cartilage ECM while ScASCs show no significant correlation with chondrogenesis.

Both ScASCs and donor-matched IPFSCs expressed plenty of genes related to lipid and fatty acid in their biosynthetic, catabolic, binding, and homeostasis processes. Among these differentially expressed genes, none of them showed a distinct tendency toward the brown adipose tissue due to either nondetectable expression of Uncoupling protein-1 (UCP1), Peroxisome proliferator-activated receptor-γ coactivator 1-α (PGC1A), and Forkhead box protein C2 (FOXC2), or comparable expression of Cell death inducing DFFA-like effector A (CIDEA) (Log2FC from IPFSCs to ScASCs was −1.45, FDR = 7.1E-01), a core set of brown adipose genes (Harms and Seale, 2013). Given the preferential expression of PPARG, a master regulator of adipogenesis (Kawai and Rosen, 2010), in ScASCs, most privileged associated genes favored adipogenesis, including but not limited to ATP Binding Cassette Subfamily G Member 1 (ABCG1) (Frisdal et al., 2015), Fibrillin-1 (FBN1) (Davis et al., 2016), NFATC4 (Yang et al., 2006), Oxysterol-binding protein-related protein 11 (OSBPL11) (Zhou et al., 2012), Paternally expressed gene-10 (PEG10) (Hishida et al., 2007), Salt inducible kinase 2 (SIK2) (Henriksson et al., 2015), and WNT4 (Christodoulides et al., 2009). Protein inhibitor of activated STAT 3 (PIAS3) did not favor adipogenesis (Deng et al., 2006). In contrast, excluding a few genes favoring adipogenesis, such as Docking protein 1 (DOK1) (Hosooka et al., 2008), ECM1 (Challa et al., 2015), and Leukemia inhibitor factor receptor alpha (LIFR) (Aubert et al., 1999), most related genes inhibited adiogenic differentiation in IPFSCs, including but not limited to Fatty acid binding protein 4 (FABP4) (Garin-Shkolnik et al., 2014), GREM2 (Wu et al., 2015), Jagged canonical NOTCH ligand 1 (JAG1) (Ugarte et al., 2009), LRP6 (Peröbner et al., 2012), SMOC2 (Nie and Sage, 2009), and Tribbles homolog 2 (TRIB2) (Naiki et al., 2007). The above findings indicate that, compared with ScASCs, donor-matched IPFSCs exhibit less potential to differentiate toward adipose tissue.

Our study did not find a significant difference in expression levels of osteogenic markers between ScASCs and donor-matched IPFSCs after induction. It has long been speculated that IPFSCs have a higher chondrogenic potential than other fat depots in the body (Sun et al., 2018), which might be due to the IPFP’s anatomic site that is closer to synovium and cartilage; it is regarded as a special form of fibro-adipose tissue (Macchi et al., 2016), or a continuation of synovium. IPFSCs may share some common characteristics with synovium-derived stem cells, a tissue-specific stem cell for chondrogenesis (Jones and Pei, 2012). A study comparing IPFSCs with near knee joint ScASCs from donor-matched osteoarthritis patients found that IPFSCs had a superior chondrogenic potential; ScASCs were superior in osteogenesis while both were similar in adipogenic capacity (Lopa et al., 2014). In this study with donor-matched normal adipose stem cells, we observed clear superiority of IPFSCs for chondrogenesis. However, we obtained divergent results on adipogenic and osteogenic potential. There were two possible explanations for the discrepancy; first, species differences between humans and rabbits can lead to considerable diversity, and secondly, Lopa et al. harvested IPFSCs from aged patients affected by osteoarthritis (Lopa et al., 2014) while we harvested from young healthy rabbits. The adult stem cell profile could be greatly affected by disease and aging (Li and Pei, 2012; Lynch and Pei, 2014).

Taken together, by donor-matched comparison and high throughput assay of transcriptome and proteomics, this study investigated the variance of depot-specific adult stem cells from adipose tissues. The findings might shed some light on the hypothesis that adipose stem cells have a depot-dependent lineage preference. Here, we have profiled RNA and protein levels to identify unique transcriptional programs, signaling components, and matrix environments that reveal novel insights into the higher chondrogenic potential of IPFSCs.

The RNA-Seq datasets generated for this study can be found in the GEO, under the accession number GSE142626, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE142626. The data that support the findings of this study are available from the corresponding author upon reasonable request.

The animal study was reviewed and approved by IACUC of West Virginia University, protocol number 1608003840.

TW contributed to the conception and design, collection and/assembly of data, data analysis and interpretation, manuscript writing, and final approval of the manuscript. RH and MD contributed to the collection and/assembly of data, data analysis and interpretation, manuscript writing, and final approval of the manuscript. AI, GH, LZ, and KH contributed to the data analysis and interpretation, manuscript writing, and final approval of the manuscript. MP contributed to the conception and design, financial support, data analysis and interpretation, manuscript writing, and final approval of the manuscript.

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.