Oncogenic mutations in PIK3CA, encoding p110α-PI3K, are a common cause of venous and lymphatic malformations. Vessel type–specific disease pathogenesis is poorly understood, hampering development of efficient therapies. Here, we reveal a new immune-interacting subtype of Ptx3-positive dermal lymphatic capillary endothelial cells (iLECs) that recruit pro-lymphangiogenic macrophages to promote progressive lymphatic overgrowth. Mouse model of Pik3caH1047R-driven vascular malformations showed that proliferation was induced in both venous and lymphatic ECs but sustained selectively in LECs of advanced lesions. Single-cell transcriptomics identified the iLEC population, residing at lymphatic capillary terminals of normal vasculature, that was expanded in Pik3caH1047R mice. Expression of pro-inflammatory genes, including monocyte/macrophage chemokine Ccl2, in Pik3caH1047R-iLECs was associated with recruitment of VEGF-C–producing macrophages. Macrophage depletion, CCL2 blockade, or anti-inflammatory COX-2 inhibition limited Pik3caH1047R-driven lymphangiogenesis. Thus, targeting the paracrine crosstalk involving iLECs and macrophages provides a new therapeutic opportunity for lymphatic malformations. Identification of iLECs further indicates that peripheral lymphatic vessels not only respond to but also actively orchestrate inflammatory processes.

Venous malformations (VMs) and lymphatic malformations (LMs) are chronic diseases characterized by vascular lesions that range from simple skin discoloration to large deformations, or fluid-filled cysts to infiltrative soft-tissue masses, respectively (Queisser et al., 2021; Mäkinen et al., 2021). They are often associated with significant morbidity, and in some cases life-threatening complications, due to pain, bleeding, and functional impairment of nearby organs. Somatic-activating PIK3CA mutations have been identified as causative of the majority of LMs (Luks et al., 2015; Osborn et al., 2015) and a smaller proportion of VMs (Limaye et al., 2015; Castel et al., 2016; Castillo et al., 2016). PIK3CA is frequently mutated also in cancer and other pathologies characterized by tissue hyperplasia, the so-called PIK3CA-related overgrowth spectrum (Madsen et al., 2018; Angulo-Urarte and Graupera, 2022).

PIK3CA encodes the p110α subunit of the phosphoinositide 3-kinase (PI3K) that catalyzes the production of phosphatidylinositol (3,4,5)-triphosphate (PIP3) at the plasma membrane, leading to activation of downstream signaling cascades such as the AKT-mTOR (mammalian target of rapamycin) pathway. PI3K signaling controls a variety of cellular processes in both blood and lymphatic vasculatures, including endothelial cell (EC) migration, survival, and proliferation as well as vessel sprouting, thereby critically regulating vascular maintenance and growth (Angulo-Urarte and Graupera, 2022). Genetic loss-of-function studies in mice have uncovered a critical role of p110α in the normal development of blood and lymphatic vessels (Graupera et al., 2008; Gupta et al., 2007; Stanczuk et al., 2015). Conversely, the expression of an activating PIK3CA mutation in ECs led to vascular overgrowth and malformations in mice (di Blasio et al., 2018; Rodriguez-Laguna et al., 2019; Martinez-Corral et al., 2020). EC-autonomous effects in the pathogenesis of both VM and LM are demonstrated by the presence of PIK3CA mutations specifically in ECs but not in other cell types (Osborn et al., 2015; Blesinger et al., 2018; Boscolo et al., 2015).

PIK3CA mutations frequently occur in two hot spot regions encoding the helical domain and the kinase domain, with an H1047R substitution in the latter representing one of the most frequent VM/LM and cancer mutation (Madsen et al., 2018; Queisser et al., 2021; Mäkinen et al., 2021). Identification of PIK3CA mutations as drivers of vascular malformations has enabled repurposing available in Food and Drug Administration–approved inhibitors of the PI3K pathway for their treatment. For example, rapamycin that targets the PI3K-AKT downstream effector mTOR has shown efficacy in relieving symptoms in VM and LM patients although it rarely results in the regression of lesions (Queisser et al., 2021; Mäkinen et al., 2021). Apart from the identified EC-autonomous mutations driving vascular anomalies, emerging evidence points to synergistically acting paracrine mechanisms that contribute to disease progression (Mäkinen et al., 2021). For example, increased paracrine vascular endothelial growth factor C (VEGF-C) signaling is observed in LMs in mice and human patients (Boscolo et al., 2015; Martinez-Corral et al., 2020; Partanen et al., 2013), and it is required for the growth of Pik3ca-driven LM in mice (Martinez-Corral et al., 2020). Interestingly, the inhibition of VEGF-C was more effective than rapamycin in limiting LM growth in mice, and when administered in combination with rapamycin, it even promoted regression of the abnormal lymphatic vessels (Martinez-Corral et al., 2020). Better understanding of both the aberrant EC-autonomous signaling and the paracrine mechanisms should aid the development of effective and targeted combinatorial therapies for LMs and other vascular malformations.

Here, we investigated the endothelial subtype–specific mechanisms underlying PIK3CA-driven LM in comparison with VM. Analyses of mouse models of Pik3caH1047R-driven vascular malformations revealed lymphatic and blood vessel type–specific responses resulting in distinct lesion characteristics. Selective features of LM were tissue infiltration of myeloid cells producing pro-lymphangiogenic factors during early stages of active vascular growth, which occurred concomitant with an increase in cytokine levels and expansion of an immune-interacting capillary LEC subtype, iLEC, identified through single-cell transcriptomics. Importantly, macrophage depletion, CCL2 blockade, or anti-inflammatory cyclooxygenase-2 (COX-2) inhibition limited Pik3caH1047R-driven lymphangiogenesis in mice. These results show that paracrine immune activation driven by LEC-autonomous oncogenic p110α-PI3K signaling critically contributes to pathological vascular growth in LM and provides a therapeutic target.

Endothelial expression of Pik3caH1047R induces excessive lymphatic vessel sprouting and localized blood vessel dilations without sprouts in the mouse skin (Martinez-Corral et al., 2020). To explore these apparently different cellular responses of dermal lymphatic and blood ECs (LECs and BECs, respectively) to activation of PI3K signaling, we used a mouse model that allows Cre-inducible expression of Pik3caH1047R from the ubiquitously expressed Rosa26 locus in combination with EC-specific Cre lines (Fig. 1 A). LEC-specific Vegfr3-CreERT2 (Martinez-Corral et al., 2016) and pan-endothelial Cdh5-CreERT2 (Wang et al., 2010) lines were complemented with a new transgenic mouse model that allows BEC-specific expression of CreERT2 under the control of Flt1 (encoding VEGFR1) promoter (Fig. S1 A). Flow cytometry and immunostaining analyses confirmed that the Vegfr1-CreERT2 transgene drives efficient recombination of the R26-mTmG reporter allele and GFP expression upon tamoxifen administration specifically in BECs in the skin (Fig. S1, B–F).

To mimic the congenital PIK3CA-driven vascular malformations, we first induced Pik3caH1047R expression in LECs and/or BECs during embryonic development by administering 4-hydroxytamoxifen (4-OHT) to pregnant females at embryonic day (E) 10 or 11 (Fig. 1 A). As previously reported (Martinez-Corral et al., 2020), Vegfr3-CreERT2–driven activation of Pik3caH1047R expression led to hypersprouting of neuropilin-2 (NRP2)+ lymphatic vessels in the thoracic skin of E15 embryos, while blood vessels were not affected (Fig. 1 B). Pan-EC–specific expression of Pik3caH1047R similarly resulted in a hyperbranched lymphatic vasculature but also in multiple blood-filled lesions (Fig. 1 C) that were connected to the blood circulation as evidenced by the evacuation of blood upon application of pressure (Fig. 1 D). BEC-specific activation of Pik3caH1047R expression using the Vegfr1-CreERT2 line at E10 led to formation of blood vessel lesions that resembled those in the Cdh5-CreERT2 embryos but did not affect the lymphatic vasculature (Fig. 1 E). Whole-mount immunofluorescence staining of embryonic back skin showed localized vessel dilations that were positive for the pan-endothelial marker PECAM1 (Fig. 1 C) and the venous/capillary EC marker endomucin (EMCN; Fig. 1 E). In contrast, EMCN-negative and alpha smooth muscle actin (αSMA)–positive arteries were not affected (Fig. 1 F).

Taken together, these results demonstrate that chronic activation of p110α signaling triggers a distinct response in different dermal vessel types. Lymphatic capillaries in mutant embryos expand by sprouting, whereas blood capillaries and veins show localized vessel dilations, but arteries are not affected.

To allow analysis of the step-by-step development of Pik3caH1047R-driven lymphatic and vascular overgrowth, we utilized postnatal mouse ear skin as a model (Martinez-Corral et al., 2020). Cre-mediated recombination was induced in 3-wk-old Vegfr3-CreERT2 and Vegfr1-CreERT2 mice by topical application of 4-OHT (Fig. 2 A). To first assess the specificity of Cre-mediated recombination, we analyzed transgenic mice carrying the R26-mTmG reporter allele. Efficient induction of GFP expression was observed in the ear skin vasculature with lower frequency of GFP+ ECs in other analyzed tissues (Fig. 2 B and Fig. S1, G and H), indicating locally restricted recombination as opposed to tissue-wide recombination observed upon systemic 4-OHT administration (Martinez-Corral et al., 2016; and data not shown). As expected, recombination was EC-subtype specific such that dermal LECs were specifically targeted in the Vegfr3-CreERT2 mice (Fig. 2 B and Fig. S1 G) and BECs in the Vegfr1-CreERT2 mice (Fig. 2 B and Fig. S1 H).

Next, we analyzed the progression of the vascular phenotype upon LEC- or BEC-specific induction of Pik3caH1047R expression up to 7 wk after 4-OHT administration (i.e., at 10 wk of age; Fig. 2 A). In agreement with previous data (Martinez-Corral et al., 2020), Vegfr3-CreERT2–driven expression of Pik3caH1047R induced the formation of lymphatic sprouts, which progressively developed into a dense hyperbranched vessel network (Fig. 2, C and D; and Fig. S2, A and C). In contrast, and similar to the embryonic skin, ear skins of Pik3caH1047R;Vegfr1-CreERT2 mice showed localized vessel dilations in both EMCN+ veins and smaller EMCN+ venules and capillaries (Fig. 2, C and E; and Fig. S2, B and C). The lesions progressively increased in number and size, in particular in the smaller caliber vessels (Fig. 2, C and E; and Fig. S2, B and C). EMCN− αSMA+ arteries were not affected, but we observed abnormal coverage of the capillary/venous-derived lesions by αSMA+ smooth muscle cells (Fig. 2 E).

In conclusion, the analyses of the early stages of lesion formation in postnatal ear skin demonstrate different EC-autonomous responses induced by activation of p110α signaling that underlie vessel type–specific lesion morphologies. Locally limited activation of Pik3caH1047R expression induces highly reproducible lesion formation with minimal potentially life-threatening effects in the internal organs, thereby allowing an extended observation period compared to embryonic and systemic models that recapitulates human pathology.

Since Pik3ca-driven LM and VM are somatic diseases, the initial stage of lesion formation likely involves proliferation and selective expansion of the mutant ECs. In support of this, flow cytometry analysis showed an increase in the frequency of ECs expressing the proliferation marker protein Ki67 in the Pik3caH1047R;Cdh5-CreERT2 ear skin, which was apparent already 1 wk after 4-OHT administration and increased after 2 wk (Fig. S2 D). Quantitative RT-PCR analysis of ECs sorted by FACS from the ears of 5-wk-old Pik3caH1047R;Cdh5-CreERT2 mice confirmed upregulation of Mki67 (encoding Ki67) in mutant LECs and BECs compared to controls (Fig. S2 E).

Next, we performed whole-mount immunofluorescence of the ear skin to localize the proliferating ECs within the abnormal vascular structures and to correlate proliferation with changes in vessel morphology. Pik3ca-driven vascular overgrowth was induced specifically in LECs or BECs, using the previously validated mouse models (Fig. 2 C). S-phase cells were labeled by intraperitoneal injection of EdU 16 h prior to analysis, and combined with Ki67 staining of all cycling cells. The abnormal lymphatic sprouts in the Pik3caH1047R;Vegfr3-CreERT2 mice frequently contained proliferating LECs (Fig. 3 A and Fig. S2 F). Quantification of the frequency of PROX1+LYVE1+ LECs that were positive for EdU and/or Ki67 revealed a ∼20-fold higher level of proliferation in the mutant 1 wk after 4-OHT administration (i.e., 4 wk of age) that was sustained at approximately sixfold higher level compared to control up to at least 7 wk after induction (i.e., 10 wk of age; Fig. 3 B). A similar proliferative response was observed in BECs within developing lesions of EMCN+ veins and venules of Pik3caH1047R;Vegfr1-CreERT2 mice during the first 3 wk after 4-OHT induction (Fig. 3, C and D). However, 6 wk after 4-OHT induction, i.e., at 9 wk of age, BEC proliferation rate in the lesions was reduced to that of controls (Fig. 3, C and D). Flow cytometry analysis of Pik3caH1047R;Vegfr3-CreERT2 ear skin confirmed a sustained increase in the frequency of Ki67+ LECs (Fig. 3 E), and consequently a dramatic increase in the proportion of LECs of the total dermal EC population (Fig. 3 F). In contrast, the increase in Ki67+ BECs was observed only at the early stage of vascular lesion formation in the Pik3caH1047R;Vegfr1-CreERT2 mice (Fig. 3 E), resulting in a small rise in total BEC numbers at 10 wk of age (Fig. 3 F).

In summary, the above data demonstrate that the initial stage of Pik3ca-driven vascular pathology involves increased EC proliferation both in lymphatic and blood vessels, likely through cell-autonomous mechanisms. However, in advanced lesions, the proliferation of BECs ceased whereas LEC proliferation was sustained.

To investigate the mechanisms underlying sustained proliferation of LECs in advanced LM lesions, we focused on the potential contribution of the immune infiltrate as a source of pro-lymphangiogenic factors such as VEGF-C (Harvey and Gordon, 2012; Kerjaschki, 2005). Increased abundance of immune cells, measured as CD45+ area, was observed in the ear skin of Pik3caH1047R;Vegfr3-CreERT2 mice already 1 wk (i.e., 4 wk of age) after induction of vascular overgrowth (Fig. 4 A). In contrast, there was no apparent increase in CD45+ area around the vascular lesions in Pik3caH1047R;Vegfr1-CreERT2 mice (Fig. 4 B). Staining for F4/80 confirmed an increased presence of myeloid cells, which constitute the majority of dermal CD45+ cells (Yu et al., 2016), in the Vegfr3-CreERT2 (Fig. 4, C and D) but not in the Vegfr1-CreERT2 (Fig. 4, C and E) ears 2 wk after 4-OHT induction.

To assess the inflammatory status of the ears, we performed multiplex ELISA that allows simultaneous measurement of multiple pro-inflammatory cytokines and chemokines. The levels of pro-inflammatory proteins associated with the recruitment and/or activation of antigen-presenting myeloid cells, including CCL2 (also known as monocyte chemoattractant protein MCP1), IL1β, IL6, and IL12, were significantly increased in ear skin lysates of 5-wk-old Pik3caH1047R;Vegfr3-CreERT2 mice (Fig. 4 F), but not of Pik3caH1047R;Vegfr1-CreERT2 mice (Fig. S3 A). Proteins associated with the recruitment and/or activation of B cells (IL4, IL5) or T cells (IL2, IL9, IL15, IL17A) were unaltered in both models (Fig. S3, A and B). The major pro-inflammatory cytokines TNFα and INFγ were also unaltered in the blood sera of Pik3caH1047R;Vegfr3-CreERT2 mice (Fig. S3 C), thereby excluding systemic inflammation. TNFα levels were increased in the mutant in comparison with control ear skin lysate (Fig. 4 F), but the low concentration likely reflects low-grade local chronic inflammation (Li et al., 2009).

Further analysis of innate and adaptive immune cells by flow cytometry showed increase in the frequency (Fig. 4 G and Data S1) and number (Fig. S3 D) of CD45+CD11b+F4/80+ myeloid cells in the ears of Pik3caH1047R;Vegfr3-CreERT2 mice compared to controls. Additional myeloid markers revealed selective increase in macrophages (Cd11b+MerTK+CD64+) at two time points of disease progression at 5 and 7 wk of age (Fig. 4 H). The frequency of dendritic cells (MerTK−CD64−CD11c+MHCII+) was modestly increased only at 5 wk, while the total monocyte (Cd11b+low-SSC F4/80+Ly-6C+MHCII+) abundance was not significantly altered at either time point (Fig. 4 H). Interestingly, however, the frequency of monocytes expressing the CCL2 ligand CCR2 that represented 20–30% of the total monocyte population was increased in mutant in comparison with control ears at 7 wk of age (Fig. 4 H). Advanced lesions, analyzed by FACS at 10 wk of age (7 wk after 4-OHT administration) additionally showed an increased frequency of T cells (CD45+CD3+CD4/CD8+) and B cells (CD45+CD3−B220+NK1.1−), while neutrophils (CD45+CD11b+Ly6G+) or natural killer (NK) cells (CD45+CD3−NK1.1+) did not show significant alterations (Fig. 4 G). Immunofluorescence staining confirmed an increased abundance of F4/80+ myeloid cells in the Pik3caH1047R;Vegfr3-CreERT2 ears until the analysis at 10 wk of age (Fig. S3 E).

Selective myeloid cell recruitment during the first weeks of Pik3ca-driven vessel growth was only observed in LM, since CD45+CD11b+F4/80+ myeloid cells were not significantly increased in the ears of Pik3caH1047R;Vegfr1-CreERT2 mice compared to controls at 5 wk of age (Fig. S3 G). Advanced venous lesions at 10 wk of age instead showed an increased frequency of several immune populations including myeloid cells, but also, and different from LM, neutrophils, and B cells (Fig. S3 H). The delayed immune response is likely secondary to disruption of vessel integrity and leakage in this model.

To assess the pro-lymphangiogenic nature of the myeloid infiltrate in Pik3caH1047R;Vegfr3-CreERT2 ears, we assessed Vegfc transcript levels. qRT-PCR analysis of FACS-sorted CD45+CD11b+F4/80+ myeloid cells showed higher Vegfc levels in mutant in comparison with control mice (Fig. 4 I). Notably, macrophages in mutant ears showed a strong increase in Vegfc expression, while the levels were low and not altered in dendritic cells (Fig. 4 I) as well as in total CD45− non-immune dermal cells (Fig. S3 F).

Collectively, the above data demonstrate that infiltration of macrophages, as well as the upregulation of pro-inflammatory cytokines and chemokines promoting their recruitment, are selective features of and account for increased production of Vegfc in Pik3caH1047R-driven LM.

The pro-inflammatory molecules specifically upregulated in the Pik3caH1047R;Vegfr3-CreERT2 skin are expressed in a variety of cell types, including the infiltrating myeloid cell themselves (Farnsworth et al., 2019). To determine the contribution of LEC-autonomous PI3K signaling in promoting a pro-inflammatory environment, we applied single-cell RNA sequencing (scRNA-seq). LECs were isolated by flow cytometry from the ear skin of Pik3caH1047R;Cdh5-CreERT2 (n = 5) and Cre− littermate (n = 2) mice 2 wk after 4-OHT treatment, and subjected to scRNA-seq using Smart-Seq2 (Picelli et al., 2013; Fig. 5 A). Additional controls included a separately bred untreated wild-type (C57BL/6J) mouse to control for possible effects of the treatment in littermate controls, and 2–4-wk-old mice from a previous study (Korhonen et al., 2022).

To define the normal transcriptome of dermal LECs, we analyzed 1,019 single-cell transcriptomes from control mice that passed the quality controls. The cells distributed into five clusters after applying the canonical correlation analysis method for batch correction and Seurat graph–based clustering approach (Stuart et al., 2019), and visualization using the Uniform Manifold Approximation and Projection (UMAP; McInnes et al., 2020; Fig. 5 B). As expected, all clusters were characterized by high expression of pan-endothelial (Cldn5) and LEC-specific marker genes (Flt4, Prox1), and lack of BEC marker expression (Flt1; Fig. 5 C). Based on the expression of known LEC subtype markers, the clusters were annotated as valve LECs (Cldn11+; Takeda et al., 2019), collecting vessel LECs (Foxp2+; Hernández Vásquez et al., 2021), and capillary LECs (Lyve1high; Fig. 5 C). In addition, we observed a previously unknown population of LECs defined by high expression of Ptx3, which encodes the humoral pattern recognition molecule Pentraxin 3 (Doni et al., 2016). Ptx3high LECs included two clusters of non-proliferating and proliferating Lyve1high capillary LECs, the latter recognized by their high expression of cell-cycle genes (e.g., Mki67; Fig. 5 C). Interestingly, Ptx3 was recently shown to define a subpopulation of lymph node LECs, characterized by high expression of genes involved in the regulation of lymphangiogenesis and immune response (Xiang et al., 2020). Ptx3high dermal LECs shared a set of their marker genes and were enriched in transcripts encoding regulators of innate and adaptive immune responses including Ptx3 itself, as well as phagocytic pathogen (Mrc1) and chemokine (Ackr2) receptors, and regulators of T cell activation (Cd276, Cd200; Fig. 5 C and Data S2). Additional cluster markers are shown (Fig. 5 D) and listed (Data S2), and the data are available for browsing at https://makinenlab.shinyapps.io/DermaLymphaticEndothelialCells/. The proportion of cells that contributed to each cluster by the five control samples was proportional to the input, except for the proliferative cluster that was composed mainly of LECs isolated from the younger 4-wk-old mice (Fig. S4 A).

Ordering of cells based on similarities in their expression patterns generated a linear trajectory across the clusters with Ptx3high LECs at the end of the trajectory (Fig. 5, B and D; and Data S3). The observed phenotypic progression, termed “zonation” (Fig. 5 D), mirrors anatomical positioning of so-called pre-collectors that share molecular and functional features of lymphatic capillaries and collecting vessels (Petrova and Koh, 2020). Whole-mount immunofluorescence of non-permeabilized ear skin of wild-type mouse revealed high cell surface PTX3 at blunt-ended terminals of lymphatic capillaries (Fig. 5 E and Fig. S4 E), thereby indicating a distinct anatomical location of PTX3+ LECs in normal vasculature. A subset of valves of pre-collecting vessels was also PTX3+ (Fig. S4 E).

In summary, scRNA-seq identifies dermal LEC hierarchy that recapitulates lymphatic vascular architecture and defines a previously unknown molecularly distinct Ptx3high population within dermal capillary terminals as a putative immune-interacting LEC subtype—termed here as iLEC.

Next, we performed a similar analysis of LECs isolated from the Pik3caH1047R;Cdh5-CreERT2 mice. We obtained, in total, 1,187 quality-controlled single-cell transcriptomes that distributed into six clusters (Fig. 6 A). Based on the expression of the LEC subtype markers identified in the control skin dataset (Data S2), we defined clusters of valve, collecting vessel and capillary LECs. We also observed a large population of Ptx3high capillary LECs that included two clusters of non-proliferating and proliferating LECs (Fig. 6, A and B; and Fig. S4 B). One cluster was characterized by an intermediate identity with expression of both capillary (e.g., Lyve1) and collecting vessel (e.g., Mmrn2) genes (Fig. 6, A and B; and Fig. S4 B). Enriched genes for each cluster are listed in Data S4. Cluster level analysis thus suggested active expansion of the Ptx3high iLEC population in Pik3caH1047R mutant mice, which was also evident in the subtype composition of LEC populations in the mutant in comparison with control skin (Fig. 6 C).

For the identification of potential pathological cell populations, we integrated the LEC single-cell transcriptomes from 5-wk-old control and Pik3caH1047R mutant mice (after removal of contaminants in total 1,594 cells) using Harmony and identified seven LEC clusters (Fig. 6 D). Marker expression defined six clusters corresponding to the same identities than those in the Pik3caH1047R mutant mice, including non-proliferating and proliferating Ptx3high capillary LECs (Fig. 6, D and E; Fig. S4 C; and Data S5), but also an additional Ptx3high cluster characterized by high expression of metabolic genes (Fig. S4 C and Data S5). Trajectory analysis based on gene expression data suggested linear phenotypic progression between the non-proliferative and proliferative Ptx3high clusters (Fig. 6 D). Assessment of the relative contribution of cells originating from the different genotypes of mice revealed that the Ptx3 capillary LEC clusters, as well as the cluster of mixed identity, were almost exclusively composed of LECs isolated from the Pik3caH1047R mutant mice (Fig. 6, F and G). Ptx3high capillary LEC clusters further showed enrichment of cells expressing the transgene-encoded Pik3caH1047R transcript (Fig. 6, F and G; and Fig. S4 D), which was expressed at a similar level compared to the endogenous mouse Pik3ca transcript (Fig. S4 D). Whole-mount immunofluorescence confirmed increased expression of PTX3 (Fig. 6 H and Fig. S4 E) in the abnormal lymphatic vessel sprouts in Pik3caH1047R;Vegfr3-CreERT2 mice, further supporting the selective expansion of the Ptx3 capillary iLEC population in the mutant skin.

To explore potential clinical relevance of the findings, we analyzed PTX3 expression in normal human skin and in LMs. Clinical features of three LM patients with a PIK3CAH1047R mutation selected for the study are summarized in Table S1. Immunofluorescence staining of paraffin sections of normal skin showed deposition of PTX3 around PDPN+ lymphatic vessels in control tissue but low levels in LECs themselves (Fig. 7, A–C). In contrast, LECs within LM lesions showed strong immunoreactivity (Fig. 7, A–C). PTX3 immunostaining intensity, measured as corrected total cell fluorescence, was fivefold higher in LECs from LM in comparison with control tissue (Fig. 7 D), and covered a twofold larger area of PDPN+ lymphatic vessels (Fig. 7 E).

Taken together, the expansion and active proliferation of the Ptx3high capillary iLECs in the mouse model of Pik3caH1047R-driven LM, and high lymphatic endothelial expression and deposition of PTX3 in human LM suggest PTX3high LECs as pathogenic cells in these vascular lesions.

To identify LEC-autonomous Pik3ca-driven transcriptional changes, we next focused on the pathological Ptx3 capillary LEC clusters representing iLECs. To avoid the confounding effect of the cell cycle (Chen and Zhou, 2017), we determined differentially expressed genes (DEG) between the non-proliferative Ptx3 clusters in mutant mice in comparison with Ptx3 capillary LECs from control mice (Data S6). Gene Ontology (GO) analysis of DEGs revealed enrichment of biological processes related to metabolic processes, cell-cycle transition, cell migration, and cell-matrix adhesion in the mutant clusters (Datas S7 and S8), consistent with the established role of the PI3K pathway (Graupera and Potente, 2013) and previously reported migratory phenotype of Pik3caH1047R-expressing LECs in vitro and in vivo (Martinez-Corral et al., 2020). Both mutant clusters also showed enrichment of processes and genes related to immune regulation (Fig. 8, A and B; and Data S7 and S8). The latter include upregulation of genes encoding pro-inflammatory cytokines (Ccl2, Ccl7), (scavenger) receptors (Ackr2, L1cam), as well as extracellular matrix proteins (Lgals3) and proteinases (Adam17, Adam8, Mmp14, Mmp2) implicated in inflammatory processes (Fig. 8 C and Data S6). Conversely, downregulated biological processes include negative regulation of inflammatory processes. Lymphatic endothelial expression of the key monocyte/macrophage chemokine CCL2/MCP1 in Pik3caH1047R;Vegfr3-CreERT2 mice was confirmed by whole-mount immunofluorescence, while no staining was detected in the control skin (Fig. 8 D and Fig. S4 F).

To assess if oncogenic PI3K directly regulates Ccl2 expression in LECs, in the absence of immune cells, we isolated primary dermal LECs from Pik3caH1047R;Vegfr3-CreERT2 mice and analyzed transcript levels by qRT-PCR after induction of Cre recombination by supplementation of 4-OHT to the culture medium. We observed a significant upregulation of Ccl2 transcript after induction of Pik3caH1047R expression, while the levels of the general LEC marker Prox1 were not altered (Fig. 8 E).

Taken together, single-cell transcriptomics revealed that Pik3caH1047R promotes a pro-inflammatory transcriptome in LECs.

Based on the increased lymphatic endothelial expression of immune-related molecules and pro-lymphangiogenic myeloid cell infiltrate, we hypothesized that paracrine LEC-myeloid cell crosstalk may critically contribute to promoting pathological vessel growth in the Pik3caH1047R mice. To inhibit the expansion and differentiation of macrophages (MacDonald et al., 2010), we administered a blocking antibody against the macrophage colony-stimulating factor 1 receptor (CSF1R) from the time of induction of Pik3caH1047R expression (