SIS results in Fb accumulation in the reconstructed airway. In our previous work, we showed that ECM turnover and remodeling are affected after airway reconstruction, leading to alterations in the matrisome (23). While ECM remodeling is a normal aspect of wound healing, a dysregulated process might result in pathological scarring concomitant with fibrosis (24). To evaluate ECM remodeling in response to SIS, we developed a preclinical model of airway reconstruction in which a tracheal segment was orthotopically transplanted into a genetically identical host (25). We first investigated the degree to which surgery alters airway homeostasis by examining histological changes in the operative site at early (postoperative day 14 [D14]) and late (D28) time points (Figure 1A). In homeostasis (native trachea hereafter referred to as Control), the epithelial submucosa, the region between the tracheal cartilage and epithelium, is mostly comprised of an acellular matrix, blood vessels, and scarce Fb (Figure. 1B). After reconstruction, evidence of SIS included active remodeling (Figure 1B) and increased cellular infiltration (Figure 1C). The SIS response included increased signs of fibrosis, as evidenced by acute collagen deposition at D14 with spontaneous resolution of this change by D28 (Figure 1D). Changes in the submucosa were also reflected by an increase in submucosal thickness (Figure 1E).

Surgery-induced stress results in fibroblast accumulation in the reconstructed airway. (A) Graphical representation of the microsurgical model of airway reconstruction with a corresponding gross image showing the site of surgery. (B) Representative full and section view of H&E images of homeostatic and reconstructed airways at D14–D28. (C) Quantification of the number of cells per mm2 square in the submucosa (Control, n = 4; D14, n = 4; D28, n = 5). (D) Masson’s trichrome staining shows the luminal surface, epithelium, submucosa area, and cartilage (Control, n = 4; D14, n = 4; D28, n = 5). (E) Quantification of submucosa thickness at different time points following reconstruction. Dots represent the mean, and colored area represents upper and lower limits (Control, n = 4; D14, n = 4; D28, n = 5). (F) UMAP and annotation of all scRNA-Seq cells from the normal airway, and D14 and D28 after surgery (n = 63,561 cells). (G) The proportion of cell lineages in the normal airway and D14 and D28 after reconstruction. (H) Representative immunofluorescence staining showing the presence of fibroblasts (Vimentin+, red). (I) Quantification of Fb per mm2 (Vimentin+, red) per condition (Control n = 4, D14 n = 4, D28 n = 5). For all staining, “C” indicates cartilage, and the dotted line indicates the epithelium. Data are shown as mean ± SD. Statistical analysis was performed using 1-way ANOVA with multiple-comparison test. *P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001. Scale bars: 50 µm, 100 µm, 200 µm, and 500 µm as indicated.

To investigate the cellular aspects of SIS response, Control (native trachea) and SIS (reconstructed tracheas, D14 and D28) transcriptomes (n = 63,561 cells) from our recently published scRNA-Seq data set (22) were reanalyzed and allowed us to map the cells that were infiltrating the airway niche in response to surgery. Unsupervised computational analysis identified 20 discrete clusters corresponding to 11 cell types based on their distinct markers (Figure 1F and Supplemental Figure 1A; supplemental material available online with this article; https://doi.org/10.1172/jci.insight.186263DS1). As shown in Figure 1G, SIS altered the cellular composition within the airway niche, where in contrast to the native trachea, the most abundant cells found in postreconstructed airway were Fb. We performed immunostaining in homeostatic and reconstructed airways and confirmed a significant increase of Fb (Vimentin) within the submucosa in response to surgery (Figure 1, H and I). Together these results demonstrated that SIS altered the airway cellular niche, favoring Fb emergence and accumulation.

Classification of Fb heterogeneity by scRNA-Seq reveals 5 subpopulations. Next, we evaluated whether these Fb constitute a uniform or a transcriptionally distinct cell population. We first identified all stromal cell populations (Supplemental Figure 2A) and removed cells such as smooth muscle cells (Acta2) and chondrocytes (Col2a1, Sox9). Using this strategy and Uniform Manifold Approximation and Projection (UMAP) visualization, we identified 5 discrete clusters within the Fb subset of native and reconstructed airways (n = 28,808 Fb) (Figure 2A and Supplemental Figure 2B). By cross-referencing differentially expressed genes in each cluster with previously published cell type–specific markers and manual annotation, these were named: Cthrc1+ Fb (Cluster 1: Cthrc1, Postn, Col1a1, Col3a1, C1qtnf3), Adventitial-Fb (Cluster 2: Clec3b, Pcolce2, Fmod2, Gsn, Pi16), perichondral Fb (PC-Fb) (Cluster 3: Chad, Wif1, Clu, Cytl1, Hspb1), immune-recruiting Fb (IR-Fb) (Cluster 5: Cd74, Ligp1, H2-K1, Cxcl10, H2-D1), and Airway-Fb (Cluster 9: Gm42418, Ppa1, Cpe, Scgb1a1, Lasrs2) (Figure 2B). Each subpopulation of Fb had a characteristic gene expression profile (Figure 2, C and D, and Supplemental Figure 2C). Comparing the Fb cluster by time points revealed transient shifts in Fb gene signatures in response to SIS (Figure 2E). Together, these findings indicate that Airway-Fb constitute a heterogeneous population, with distinct transcriptomic signatures during homeostasis and repair.

Airway fibroblast heterogeneity identified by scRNA-Seq. (A) UMAP and annotation displaying fibroblast subclustering in 5 subpopulations: Airway-Fb, Adventitial-Fb, PC-Fb, CP-Fb, and IR-Fb (n = 28,808 Fb). (B) Heatmap showing the 10 most differentially expressed genes of each fibroblast cluster, as provided by Seurat. Each column represents a single cell, and each row represents an individual gene. All marker genes per cluster are shown on the left. Yellow indicates maximum gene expression, and purple indicates no expression in scaled log normalized UMI counts. (C) Violin plots showing representative expressed genes among Fb subtypes. (D) Dot plot showing the expression of the top marker of each fibroblast subset among conditions. (E) Fb cells in UMAP are colored by their origin: normal airway and D14 and D28 after reconstruction.

SIS selectively alters Fb proportions. Since we identified 5 distinct Airway-Fb subpopulations, we then measured the effect of SIS on their abundance (Figure 3A). In homeostasis, we found that the most abundant Fb subtypes were adventitial (52%), followed by perichondrial (32%) and airway (13%) with immune-recruiting and Cthrc1+ subtypes comprising scarce proportions (2%, 1% respectively). In contrast, during SIS both Cthrc1+-Fb (D14, 74%; D28, 33%) and IR-Fb (D14, 13%; D28, 47%) became the most abundant subpopulations with PC-Fb (D14, 9%; D28, 15%) Adventitial (D14, 2%; D28, 3%) and Airway (D14, 1%; D28, 1%) becoming the least abundant (Figure 3B).

Surgery-induced stress selectively alters subtypes proportion of the fibroblast landscape in response to early and late repair events. (A) Fb clusters in UMAP are colored by their subtype from the normal airway and D14 and D28 after reconstruction. (B) The proportion of Fb subtypes in the normal airway and D14 and D28 after reconstruction. (C) Monocle analysis of Fb subsets trajectory as indicated by the black lines, with cells colored by pseudotime (upper panel) or their origin: normal, D14, and D28 (lower panel). (D) UMAP shows the expression levels of Sfrtp2, Sfrtp1, and Cthrc1 in pseudotime. Sfrp2 and Sfrp1 were expressed more highly by cells clustered earlier in pseudotime, corresponding to Airway-Fb and Adventitial-Fb (left upper panel and right upper panel, respectively). Cthrc1 was more highly expressed later in pseudotime, corresponding to CP-Fb identified in UMAP. (E) GO-enriched pathways corresponding to Airway-Fb during homeostasis and D14 after reconstruction (left panel and right panel, respectively). (F) GO-enriched pathways corresponding to Adventitial-Fb during homeostasis and D14 after reconstruction (left panel and right panel, respectively). FDR < 10%.

Given the dramatic reduction in the Adventitial-Fb proportion, we used pseudotime analysis to assess the fate of this subpopulation during SIS. Adventitial-Fb have a potential capacity to differentiate toward a Cthrc1+ phenotype in response to lung injury (26). Although in the lung Cthrc1+ Fb emerge from alveolar Fb (27), in the airway, we found that Airway-Fb and Adventitial-Fb differentiated into a Cthrc1+ cell state in response to SIS (Figure 3C). Overexpression of transitional state markers Sfrp1 and Sfrp2 demonstrated a high probability that these cell states are precursors of Cthrc1+ activated Fb state (Figure 3D), which is consistent with previous studies (28, 29).

With the suspicion that Airway-Fb and Adventitial-Fb are transitioning to other Fb subtypes, specially to Cthrc1+, we further characterized differentiation reprogramming by SIS using gene ontology (GO) analysis. As expected for Fb during homeostasis, we found that ECM organization was one of the most enriched pathways (Figure 3, E and F) for both the airway and Adventitial-Fb and that they had similar expression of common transcription factor regulators Cebpb, Pax6, and Sp1 (Supplemental Figure 3A). However, SIS rewired cellular processes such as oxidative phosphorylation and mitochondrion organization, cellular response to TGF-β stimulus, response to wounding, tissue remodeling, and regeneration to predominantly support differentiation (Figure 3, E and F). Collectively, these results suggest that SIS induces transcriptomic reprogramming of homeostatic Fb subpopulations into activated states.

PC-Fb differentiate into chondrocytes after airway reconstruction. Fb are a potential chondroprogenitor for repair of acutely damaged cartilage (30). In the trachea, previous evidence has identified PC-Fb as an intermediate state on the trajectory from Adventitial-Fb to chondrocyte (31). In our model of airway reconstruction, PC-Fb showed temporal changes to their proportion, starting with a reduction from homeostasis to D14 (32%–9%) with a modest increase to 15% by D28 (Figure 3, A and B). To further investigate the differentiation commitment in this subset, we conducted a trajectory analysis, and we found that during homeostasis, PC-Fb showed a similar probability of commitment to differentiate into chondrocytes or to undergo self-renewal (Figure 4A). However, after reconstruction, PC-Fb lost their self-renewal commitment and showed a higher probability of acquiring a chondrocyte identity (Figure 4A). This process was likely to be mediated by the chondrocyte maturation inducer (32) Runx2 (Figure 4B). Violin plots of chondrocyte fate–associated genes confirmed relatively increased expression of Col2a1, Acan, Sox9 (chondrogenic genes) and relative reduction of the Fb marker (Vim) by PC-Fb (Figure 4C) in response to SIS.

Perichondral fibroblasts modulate their identity to chondrocytes during repair. (A) Monocle analysis of Fb subsets trajectory as indicated by the black lines, with cells colored by pseudotime in normal airway (left panel), D14 (middle panel), and D28 (right panel). (B) Bar graph showing identified potential transcription factors in perichondral Fb at D14 compared with Control. (C) Violin plots showing representative expressed fibroblast or chondrocyte marker genes in the PC-Fb cluster during homeostasis and repair. (D) Representative H&E staining shows the fibrocartilage-like structure closed to the cartilage. (E and F) Quantification of fibrocartilage-like frequency (presence/cartilage per animal) (E) and area (F) (Control, n = 4; D14, n = 4; D28, n = 3; D60, n = 7; 1 year [Y]; n = 5). (G) Representative immunofluorescence and alcian blue staining from serial sections show ROI indicating Vimentin (red) and alcian blue+ cells between the cartilage and next to the cartilage. Region of interest (ROI) 1–3 reminiscent of PC-Fb at different stages toward the chondrocyte identity (left panels). (H) Quantification of fibrocartilage-like proteoglycan content in the normal airway and following reconstruction (Control, n = 4; D14, n = 4; D28, n = 3; D60, n = 7; 1Y, n = 5). (I–K) Representative images of immunofluorescence analysis of normal (right panels) and reconstructed airway sections (D14) (left panels) demonstrating the appearance of COL1/SOX9–double-positive cells (white/red) and COL2+ cells (red) and corresponding quantification of all conditions (Control, n = 4; D14, n = 4; D28, n = 3; D60, n = 7; 1Y, n = 5). For all staining, “C” indicates cartilage, and ROI dotted line indicates the fibrocartilage-like structure. Statistical analysis was performed using 1-way ANOVA with Dunnett’s multiple-comparison test. *P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001. Scale bars: 20 µm and 100 µm as indicated.

To further evaluate the implications of perichondrial Fb differentiation in vivo, we performed an exhaustive histologic evaluation of the reconstructed airway in a longitudinal study encompassing data from 1 year after surgery (Figure 4D and Supplemental Figure 4A). This analysis revealed the presence of fibrocartilage-like structures adjacent to the cartilage rings (Figure 4D), which appeared to be most prominent in size and frequency at D14 compared with D28. At D60, both frequency and size returned to normal and remained stable at 1 year (Figure 4, D–F, and Supplemental Figure 4A).

When we stained the fibrocartilage-like structures for glycosaminoglycans (GAG), a vital constituent of cartilage, and Fb markers (Vimentin), we found that these regions were in different states of differentiation, exclusively in groups following airway reconstruction. Particularly, we identified 3 different states; 1 composed of Fb-shaped cells and 2 other states composed of chondrocyte-shaped cells which differed based on ECM composition (Figure 4, G and H). We then quantified GAG content in the fibrocartilage-like structures. Mirroring the changes of size and frequency, fibrocartilage-like structures expressed more GAG at D14 compared with any other time point (Figure 4H and Supplemental Figure 4B). Pursuing the idea that fibrocartilage-like structures were still expressing both Fb and chondrocyte markers, we costained homeostatic and reconstructed airways for COL1 and SOX9, and we found that the double-positive area was significantly higher at D14 compared with other time points (Figure 4, I and J, and Supplemental Figure 4C). Similarly, COL2 area in fibrocartilage-like structures was highest at D14 (Figure 4, I and K, and Supplemental Figure 4D).

Taking into consideration that PC-Fb differentiation to chondrocytes occurs in response to cartilage damage (31), we subsequently evaluated the effect of SIS on cartilage/chondrocytes. μ-CT showed increased Hounsfield units of the airway cartilage at both postsurgical time points (D14 and D28) compared with homeostasis (Supplemental Figure 5, A and B), indicating increased cartilage calcification after reconstruction. At the transcriptomic level, evaluation of DEGs in the chondrocyte cluster revealed upregulated expression of hypertrophic remodeling (Col11a1, Col3a1, Col1a1, Col9a1) and stress response genes (Hspb1, Hspa1a, Hspa1, Dnajb1, Cdkn1a) (Supplemental Figure 5C) in response to SIS. At the functional level, GO analysis showed enrichment of pathways associated with cellular response to stress and cell cycle regulation (Supplemental Figure 5, C and D) controlled by the transcription factor Cebpb (Supplemental Figure 5E). Collectively, these findings indicate that perichondrial Fb form fibrocartilage-like structures, potentially differentiating into chondrocytes, most likely in response to mild cartilage damage.

IR-Fb expansion coincides with immune cell recruitment and infiltration after reconstruction. We then focused our attention to the Fb subpopulations that increased in response to SIS. First, we found that immune recruiting Fb subpopulation (characterized by the expression of Ccl19 and Cxcl12) increased in a time-dependent manner (from 1% during homeostasis to 13% and 47% at D14 and D28, respectively) (Figure 3, A and B, and Figure 5A). Evaluation of the IR-Fb DEGs showed an upregulation of ECM components and regulators at D14 and increased expression of immune recruitment factors at D28 (Figure 5B). At the later time point, GO analysis confirmed that this Fb subset exhibited enriched expression of pathways associated with antigen processing and presentation, positive regulation of immune response, and neutrophil chemotaxis (Figure 5C), aligning with an observed increase in immune cells, particularly neutrophils (Figure 5, D and E). Supporting these transcriptomic results, immunofluorescence analysis at D28 after SIS revealed immune cell infiltration (CD45+) and neutrophil accumulation (Neutrophil Elastase+) within the graft (Figure 5, F and G).

IR-Fb concomitant with immune cell recruitment and infiltration after reconstruction. (A) Ccl19 and Cxcl12 expression plots on UMAP layout in the normal airway and SIS at D14 and D28. (B) Volcano plot of dysregulated expressed genes according to their statistical P value (y axis) and their relative abundance ratio (log2 fold change) between SIS at D28 and D14 identifying immunomodulator-associated genes (B2m, Psmb9, Cd74, H2-Ab1, Cxcl19, Prg45, and Igtp). (C) GO-enriched pathways corresponding to changes at D28. FDR < 10%. (D and E) Percentage of immune linages (D) and neutrophils (E) at normal and D28 after reconstruction obtained from the scRNA-Seq analysis. (F and G) Representative immunofluorescence staining and corresponding quantification showing the presence of immune cells (CD45+, green) (F) and neutrophils (ELASTASE+, red) (G). Yellow arrowheads indicate immune cells expressing CD45. “C” indicates cartilage, and the dotted line indicates the region of interest in the submucosa. (H) Circle plots showing the CXCL signaling pathway network between fibroblasts and other airway cell types in the normal airway (upper panel) and in SIS at D28 (lower panel). (I) Inferred Fb-immune cell communication ligand-receptor interactions. (J and K) Violin plots showing Cxcl12 expression levels in IR-Fb (J) and its corresponding receptor Cxcr4 in neutrophils (K). Statistical analysis was performed using unpaired, 2-tailed Student’s t test (F) and Mann-Whitney test (G). *P < 0.05, ****P < 0.0001. Scale bars: 10 µm.

Further elucidation of the interplay between IR-Fb and immune cells using CellChat confirmed communication of IR-Fb with immune cells, especially neutrophils (Figure 5H). Ligand-receptor interaction analysis demonstrated that Fb communication with immune cells was potentially mediated by 2 main pathways, the CXCL pathway, specifically facilitated by Cxcl12-Cxcr4, and the Collagen pathway, specifically facilitated by Col1a1-Cd44 (Figure 5I). Furthermore, increased expression of Cxcl12 by IR-Fb at D28 was consistent with increased Cxcr4 expression in neutrophils at the same time point (Figure 5, J and K). Together, our data suggest the increased presence of an IR-Fb subpopulation that plays a modulatory role in immune cell interactions, presumably leading to neutrophil recruitment.

SIS selectively increases the abundance of Cthrc1+ Fb at sites of injury. Cthrc1+ Fb were the most abundant subtype in response to SIS and were likely to be differentiating from Adventitial-Fb (Figure 3, A and B). Following a similar pattern of their abundance, we confirmed that Cthrc1 expression in pseudotime was mainly restricted to this subpopulation and was higher at D14 compared with other time points (Figure 6A). Consistent with this transcriptomic signature, immunostaining confirmed the presence of activated Fb at D14 after SIS using CTHRC1 as well as additional markers, COL1 and Periostin (Figure 2B and Supplemental Figure 6A).

CTHRC1+ collagen-producing Fb spatially localize at the sites of injury and has a distinct collagen production. (A) Cthrc1 expression plot on UMAP layout in normal airway and SIS at D14 and D28. (B) Heatmap showing the expression levels of genes from Collagens (Matrisome category) in each fibroblast cluster. Red indicates upregulation, and blue indicates downregulation. (C) Representative immunofluorescence staining showing the presence of fibroblasts (Vimentin+, red) and Cthrc1+ Fb (Vimentin+, red; CTHRC1+, green). (D) Quantification of individual Cthrc1+ Fb per mm2 (Vimentin+CTHRC1+ cells) per condition (Control, n = 4; D14, n = 4; D28, n = 5). (E) Violin plots showing higher Col1a1 and Col3a1 expression in Cthrc1+ Fb during homeostasis and D14 and D28 after reconstruction. (F) Spearman correlation analysis of collagen density and Cthrc1+ Fb numbers. (G) Representative immunofluorescence staining showing proliferation (Ki-67, white) of activated Cthrc1+ Fb (Vimentin+, red; CTHRC1+, green) and quantification of individual proliferative Cthrc1+ Fb per mm2 (Vimentin+CTHRC1+Ki-67+ cells) per condition (Control, n = 4; D14, n = 4; D28, n = 5). (H) Violin plots showing higher Pcna, Mki67, and Nasp expression in Cthrc1+ Fb during homeostasis and D14 and D28 after reconstruction. Data are shown as mean ± SD. Statistical analysis was performed using 1-way ANOVA with Dunnett’s multiple-comparison test. ***P <0. 001. Scale bars: 5 µm and 20 m as indicated.

Consistent with previous studies where CTHRC1 expression in Fb has been associated with an activated phenotype characterized by increased collagen production (26), Cthrc1+ Fb, among all identified Fb subtypes, showed the highest expression levels of collagen genes (matrisome category) (32). Specifically, we found that the main fibrotic-associated collagens Col1a1 and Col3a1 were the most upregulated (Figure 6B and Supplemental Table 2).

To further evaluate the spatiotemporal emergence of Cthrc1+ Fb in the reconstructed airway, we employed a multiplex immunofluorescence approach. As expected, we found very few Cthrc1+ Fb during homeostasis. However, SIS transiently increased their abundance (Figure 6, C and D, and Supplemental Figure 6B). Spatially, Cthrc1+ Fb were found in the sites of injury in submucosal, paratracheal, and anastomotic regions, surrounded by collagen fibers (Figure 6C and Supplemental Figure 6, A and C).

Considering that Cthrc1+ Fb have been implicated in regulating pathologic scarring in fibrotic conditions (26, 30), we next examined the proximity of this population with respect to dense collagen areas. Regionally, Cthrc1+ Fb correlated with collagen deposition after reconstruction (Supplemental Figure 6C). To further understand the connection between high collagen deposition and Cthrc1+ Fb abundance, we performed a correlation analysis. Using this strategy, we showed that the levels of collagen deposition coincided with the abundance of Cthrc1+ Fb and was independent of SIS (Figure 6, E and F). To further characterize if SIS also promotes shifts in Cthrc1+ Fb collagen expression, we measured the level of expression of Col1a1 and Col3a1 in homeostasis and postsurgical reconstruction at D14 and at D28 in the Cthrc1+ Fb. Mirroring the fibrosis trend, Cthrc1+ Fb–mediated expression of Col1a1 and Col3a1 was transiently increased at early time points (Figure 6E). Furthermore, GO analysis of the biological function of Cthrc1+ Fb DEGs revealed enrichment of pathways associated with ECM remodeling, respiratory tube development, and glucose homeostasis (Supplemental Figure 6D). Notably, potential transcription regulators included Jun and Smad3, downstream factors of the fibrotic master regulator TGF-β (Supplemental Figure 6E).

Beyond differentiation from Adventitial-Fb, we then explored the contribution of proliferation on Cthrc1+ Fb abundance (Figure 6, G and H). SIS increased Ki-67 expression in Cthrc1+ Fb, histologically (Figure 6G). Transcriptomic analysis revealed that Cthrc1+ Fb exhibited elevated expression of proliferation-associated genes (Pcna, Mki67, and Nasp) (Figure 6H), thus confirming that cell proliferation significantly contributes to the expansion of this subpopulation. Together, our findings indicate that SIS leads to the transient emergence of a unique collagen-producing Fb subpopulation that accumulates at the injury site.

Fb-airway basal cell crosstalk via TGF-β and ncWNT modulates activation. To identify potential cellular interactions that regulate Fb transitional states and activation, we used the CellChat package (33). SIS response showed a significant increase in the number (Supplemental Figure 6F) and strength (Supplemental Figure 6G) of inferred interactions compared with homeostasis. We then visualized the crosstalk of inferred interactions between Fb and other airway cell types in response to SIS using chord plots (Supplemental Figure 6H). Among all cell types, Fb showed the highest autocrine and paracrine signaling communications in response to SIS (Supplemental Figure 6H)

Subsequent analysis using sender-receiver interaction revealed that Fb preferentially communicated with airway basal epithelial cells in a bidirectional manner in response to SIS (Figure 7, A and B). To further explore the basis of this communication, we evaluated activated signaling pathways in airway basal cells and found that Notch, TGF-β, and WNT pathways were more active in basal cells responding to SIS compared with during homeostasis (Figure 7C), and we found that TGF-β signaling had the highest relative strength when compared with control levels. Remarkably, during homeostasis, we could not identify any inferred communication via the TGF-β signaling pathway among the different airway cell types. However, in response to SIS, TGF-β–dependent communication increased, and Fb were receiving both autocrine and basal cell–mediated paracrine signals facilitated by this pathway, especially at the early repair time point (Figure 7D). Notably, Fb also sent paracrine TGF-β signals to the basal cells, confirming a bidirectional intercellular communication.

Fibroblast-basal cell communication mediated by TGF-β. (A and B) Heatmap of the inferred interaction between sender and receiver in SIS at D14 (A) and D28 (B) versus Control. (C) Heatmap of top inferred pathways. Stemness pathways (TGF-β, NOTCH, WNT, and FGF) activated in the basal cell cluster in response to SIS at D14 are highlighted in a dotted box. (D) Circle plots showing the TGF-β network between fibroblasts and other airway cell types in response to SIS at D14 (left) and D28 (right). (E) Heatmap of the outgoing signals driven by all identified airway cell types during homeostasis or at early repair time points (D14). Green intensity indicates strength of the signal. (F) Circle plots showing the ncWNT network between fibroblasts and other airway cell types in response to SIS at D14. (G) Volcano plot of dysregulated expressed genes according to their statistical P value (y axis) and their relative abundance ratio (log2 fold change) between normal airway and SIS at D14 identifying stemness-associated genes (Krt14, Itga6, Krt17, Col17a1, Klf6, Sdc4, Krt13, Krt5, Jun, and Atf3). (H) Representative immunofluorescence staining basal cells (KRT5) or activated basal cells (KRT5/KRT14–double-positive cells) in the homeostatic airway (left panel) or reconstructed airway at D14 (right panel). White asterisks indicate double-positive cells, and the dotted line indicates the epithelium from the submucosa. Scale bars: 50 µm.

To explore additional potential pathways that could be participating in Fb-basal cell communication, we determined the outgoing signals sent by Fb (Figure 7E). We found that noncanonical WNT (ncWNT) was a signal exclusively driven by Fb at early but not late time points and that they operated in both an autocrine and paracrine manner (Figure 7F). In the airway, it has been previously reported that initiation of ncWNT signaling is necessary during injury/repair and that impaired initiation results in inadequate upregulation of basal cells activation programs (34). Previously, we found that airway basal cells are activated and respond to injury following airway reconstruction (22). In alignment with those findings, examination of the DEG profile of airway basal cells showed upregulation of genes related to basal cell activation including Krt14, Krt13, Krt17, Krt5, Col17a1, and Klf6 (Figure 7G) and the ncWNT key downstream transcription factor, Jun (Figure 7G). Furthermore, immunostaining for activated basal cells (KRT5/KRT14) revealed their presence exclusively in response to SIS (Figure 7H).

Given that previous evidence has shown that TGF-β can induce CTHRC1-dependent Fb activation during tissue repair (26), we hypothesize that, similarly in SIS, TGF-β signaling activation contributes to this phenomenon. Consistent with this idea, we found that the 3 TGF-β receptors (Tgfbr1, Tgfbr2, and Tgfbr3) were expressed in the Cthrc1+ Fb at all time points; however, Cthrc1+ Fb preferentially expressed Tgfbr2 in response to SIS (Supplemental Figure 7A). Additionally, we observed a similar pattern of expression when we explored canonical TGF-β downstream genes: Smad3, Smad4, and Fn1 in Cthrc1+ Fb in response to SIS, confirming activation of this signaling in Cthrc1+ Fb (Supplemental Figure 7B). Collectively, these findings suggest that SIS is characterized by increased cellular interactions promoting mutual activation of Fb and basal cells, potentially mediated by the TGF-β pathway.

TGF-β induces CTHRC1+ Fb activation and modulates collagen production in human Airway-Fb. To identify clinical translatability of our findings, we conducted transcriptomic analysis in the human tracheobronchial airway using the Tabula Sapiens data set (35) (Supplemental Figure 7, C and D, and Supplemental Figure 8, A–E). We identified human Fb subpopulations that exhibited similar transcriptomic profiles to the 5 identified mouse Fb subpopulations (10 gene markers set of each mouse Fb subset). Using this strategy, we confirmed the presence of cells expressing selected gene sets corresponding to Adventitial-Fb (Supplemental Figure 8A), Airway-Fb (Supplemental Figure 8B), PC-Fb (Supplemental Figure 8C), CTHRC1+ Fb (Supplemental Figure 7D), and IR-FB (Supplemental Figure 8D). Furthermore, histogram representation of each set mean intensity confirmed the variation of the expressed gene sets among the total Fb population (Supplemental Figure 8E).

After we identified the presence of CTHRC1+ Fb in the human airway, we stained CTHRC1 in pediatric tracheobronchial airway tissue from resected specimens obtained during airway reconstruction surgeries. In parallel with the preclinical model, where Cthrc1+ Fb were localized within fibrotic regions (Supplemental Figure 6, A and B), CTHRC1+ cells were similarly distributed within fibrotic areas in the human reconstructed airway (Supplemental Figure 8, F–H).

To further corroborate the effect of TGF-β signaling in modulating CTHRC1+ activation and collagen production in Fb in response to SIS, we isolated primary human tracheal Fb (HTrFb) from pediatric tracheobronchial airway tissue from resected specimens obtained during airway reconstruction surgeries and treated them with TGF-β. Since resected samples vary in size and are obtained from different areas, we evaluated the heterogeneity of our cultures by immunostaining for PI16 and quantifying positive and negative cells. We found that the frequency of Adventitial-Fb in each culture varied from 31% to 53% prior stimulation and that TGF-β treatment reduced this proportion to 16%–33% (Supplemental Figure 7, E and F). In contrast, we found that TGF-β increased the frequency of CTHRC1+ Fb, while vehicle-treated Fb expressed scarce levels of CTHRC1 (Supplemental Figure 7, G and H). To confirm the critical role of TGF-β in CTHRC1+ Fb activation and collagen production, we abrogated TGF-β signaling and evaluated Fb activation (CTHRC1+) and collagen synthesis (COL1). We found that TGF-β treatment not only induced CTHRC1+ activation and collagen production but promoted the formation of focus-like structures. Abrogation of TGF-β signaling by SB431542 was sufficient to decrease CTHRC1 and COL1 protein expression in Airway-Fb to vehicle levels and inhibit the formation of focus-like structures (Supplemental Figure 7, I–K). Overall, our findings indicate that Fb become activated during SIS, presumably through the TGF-β pathway, thereby promoting excessive collagen production.

Repeated SIS favors the emergence of activated CTHRC1+ Fb, affecting Fb-basal cell crosstalk. To further address the clinical significance of SIS on Fb activation, we evaluated the expression of CTHRC1 in Fb isolated from airway tissue resected from pediatric patients who were or were not subjected to SIS and categorized them based on their surgical history. Our findings revealed that levels of CTHRC1 correlate directly with the number of airway surgical interventions (prior SIS) performed on the airway before sample collection (Figure 8, A and D). Furthermore, human CTHRC1+ Fb increased both collagen production and proliferation in response to SIS, mirroring the mouse model findings. (Figure 8, B–D). Since our cell-to-cell communication analysis identified Fb-basal communication after SIS, we wanted to determine if differentiation into the CTHRC1+ activation state would have an effect on basal cell function. To address this question, we performed a functional analysis using our previously described monolayer coculture model (36, 37), in which Fb with low (CTHRC1lo Fb) or high (CTHRC1hi Fb) CTHRC1 expression levels were used as irradiated feeders (Figure 8, E–G). Primary human basal cells formed well-defined colonies among normal Fb feeders (37). Similarly, when human basal cells were cocultured with CTHRC1lo Fb, they formed colonies with a defined edge of KRT5/KRT14–double positive cells (Figure 8, E and F). In contrast, coculture with CTHRC1hi Fb affected basal cell colony morphology, resulting in irregular and larger colonies of KRT5/KRT14–double positive cells (Figure 8, E–G). Collectively, our findings indicated that differentiation into a CTHRC1+ Fb, enhanced by repeated SIS, influenced basal cell activation, thereby promoting KRT5/KRT14 expression and increased surface area, likely by stimulating basal cell proliferation.

Repeated SIS in the airway leads to CTHRC1+ Fb activation and affects fibroblasts-basal cell crosstalk. (A–C) Schematic of surgical resection and quantification of the fluorescence intensity within the boundaries of a single cell of CTHRC1 (A), COL1 (B), and Ki-67 (C) in fibroblasts isolated from patients that were or were not subjected to SIS before sample collection (x axis represents number of prior SIS of a particular patient, n = 6). (D) Representative immunofluorescence staining of CTHRC1, COL1, and Ki-67 on human isolated fibroblast from patients with different surgical clinical history. (E) Schematic of basal cell collection and representative light microscope images of images of cocultures containing human basal cells and an irradiated fibroblast feeder layer composed of cells expressing low or high levels of CTHRC1 (CTHRC1lo Fb, upper panels; CTHRC1hi Fb, bottom panels). (F) Representative immunofluorescence staining of basal cell activation markers KRT5 and KRT14 and Vimentin in cocultures. (G) Quantification of total basal cell area after 5 days of coculture on fibroblasts expressing different levels of CTHRC1. Statistical analysis was performed using Kruskal-Wallis test (A–C) and unpaired, 2-tailed Student’s t test (G). **P < 0.01, ****P < 0.0001. Scale bars: 100 µm and 200 µm as indicated.