Loss of PGRN leads to aberrant growth in cortical organoids. To determine how PGRN deficiency might impact neurodevelopment, we differentiated wild-type (GRN+/+) WTC11 and isogenic GRN–/– iPSCs into cortical organoids using protocols previously established (15–17) (Figure 1A). Using morphological features and cell type–specific markers, we showed that GRN+/+ cortical organoids (organoids from here onward) developed relatively uniform rosettes (22–44 μm in diameter), which contained SOX2+Ki-67+ neural progenitors at 5 weeks. These rosettes grew bigger at 10 weeks but became undetectable at 16 and 25 weeks (Figure 1B and Supplemental Figure 1A; supplemental material available online with this article; https://doi.org/10.1172/JCI190035DS1). In contrast, GRN–/– organoids were larger than GRN+/+ organoids at 5 weeks and developed fewer but larger rosettes (51–173 μm in diameter) that can be detected as early as 4 weeks (Figure 1, B and C, and Supplemental Figure 1B). About 50% of GRN–/– organoids at this early age showed VZ-like morphology. Interestingly, from 10 to 25 weeks, no rosettes were identified in GRN–/– organoids (Figure 1, B and C). To further examine how PGRN deficiency impacts neurogenesis, we stained GRN+/+ and GRN–/– organoids for SOX2, Ki-67, and neuroblast marker DCX. In GRN+/+ organoids, the number of SOX2+DCX– neural progenitors expanded from 5 to 10 weeks followed by a significant reduction at 16 and 25 weeks. In contrast, GRN–/– organoids exhibited an early expansion of SOX2+DCX– progenitors at 5 weeks before dropping down at 10 weeks (Figure 1, D and E). By 25 weeks, GRN–/– organoids showed significantly more SOX2+DCX– progenitors. In addition to the early expansion of SOX2+DCX– progenitors, GRN–/– organoids also had a modest increase in SOX2+DCX+ transitioning neuroblasts at 10 weeks and no significant increase in SOX2–DCX+ young neuroblasts at all stages (Supplemental Figure 1C). Despite the more robust growth in GRN–/– organoids, no difference was observed in the proportion of Ki-67+ cells in SOX2+DCX– progenitors, SOX2+DCX+ transitioning neuroblasts, or SOX2–DCX+ young neuroblasts between GRN+/+ and GRN–/– organoids (Figure 1D and Supplemental Figure 1C).

Modeling progranulin deficiency in neurodevelopment using iPSC-derived cortical organoids. (A) Schematic representation of the generation and analysis of iPSC-derived GRN+/+ and GRN–/– cortical organoids. (B) Confocal images of DCX, Ki-67, and SOX2 in GRN+/+ and GRN–/– cortical organoids at 5, 10, 16, and 25 weeks. DCX, doublecortin. (C) Percentage of organoids exhibiting different rosette morphologies at various developmental time points in GRN+/+ and GRN–/– cases. Rosette morphologies are categorized by average rosette radius: <50 μm (black), >50 μm (gray), VZ-like morphology (white), and no rosettes (striped). Organoids (n = 9) from 3 independent biological replicate experiments were analyzed per time point for each genotype. VZ, ventricular zone. (D) Quantification of the density of SOX2+DCX– radial glia cells at different time points in GRN+/+ (blue) and GRN–/– (red) groups. Inset shows the percentage of Ki-67+ cells among SOX2+DCX– radial glia over time, with no significant differences (NS) observed between groups. Organoids (n = 9) from 3 independent biological replicate experiments were analyzed per time point per genotype. (E) Confocal images of DCX, Ki-67, and SOX2 in GRN–/– and GRN+/+ iPSC-derived cortical organoids at different developmental time points. (F) Confocal images of CTIP2, SATB2 in GRN–/– and GRN+/+ iPSC-derived cortical organoids at different time points. (G) Percentage of CTIP2+SATB2– deep-layer neurons and CTIP2–SATB2+ upper-layer neurons at different time points in GRN+/+ (blue) and GRN–/– (red) groups. Organoids (n = 9) from 3 independent biological replicate experiments were analyzed per time point for each genotype. (H) Confocal images of glial fibrillary acidic protein (GFAP), S100β, SOX9, and NESTIN (NES) in GRN–/– and GRN+/+ iPSC-derived cortical organoids at different time points. (I) Percentage of NES+SOX9–S100β+ differentiating astrocytes and NES–SOX9+S100β+ mature astrocytes at different time points in GRN+/+ (blue) and GRN–/– (red) groups. Organoids (n = 9) from 3 independent biological replicates were analyzed per time point per genotype. All data represent mean ± SEM.

Given the early expansion of SOX2+DCX– progenitors in GRN–/– organoids, we asked if loss of PGRN might lead to precocious neurogenesis. To investigate this, we stained GRN+/+ and GRN–/– organoids for layer-specific cortical neuron marker SATB2 (layers 1–4 or L1–4) and CTIP2 (L5–6). In GRN+/+ organoids, CTIP2+SATB2– neurons exhibited a significant expansion at 10 weeks, followed by a progressive decrease at 16 and 25 weeks, whereas CTIP2–SATB2+ neurons were detected at 16 weeks followed by a decrease at 25 weeks (Figure 1, F and G). In GRN–/– organoids, however, a significant number of CTIP2+ SATB2– neurons could be detected as early as 4 weeks (Supplemental Figure 1D), and these neurons persisted at 10, 16, and 25 weeks. Similarly, GRN–/– organoids showed precocious differentiation of CTIP2–SATB2+ neurons at 10 weeks. These neurons persisted at 16 weeks and disappeared at 25 weeks (Figure 1, F and G). Interestingly, GRN+/+ organoids contained a small number of transient CTIP2+SATB2+ neuron population at 16 weeks; this neuronal population was nearly undetected in GRN–/– organoids at all stages (Supplemental Figure 1E).

Next, we used astrocyte markers GFAP, S100B, and SOX9 to capture different stages of astroglial differentiation and determine how PGRN deficiency impacted this process. In addition, we included radial glia marker NESTIN (NES) to distinguish radial glia from astrocytes (Figure 1H). Recognizing that astroglial differentiation likely occurs much later than neurogenesis, we extended our analyses on GRN+/+ and GRN–/– organoids to 30 weeks. Compared with GRN+/+ organoids, GRN–/– organoids exhibited no difference in the number of astroglial progenitor populations (NES+SOX9+S100B– and NES–SOX9+S100B–) (Supplemental Figure 1F). Rather, GRN–/– organoids consistently contained more differentiating astrocytes (NES+SOX9+S100B+) at 16, 25, and 30 weeks and mature astrocytes (NES–SOX9+S100B+) at 16 weeks (Figure 1, H and I). The percentage of GFAP+ astrocytes in each of these subgroups did not differ between genotypes (Supplemental Figure 1G). One notable feature of GRN–/– astrocytes was bulky soma compared with GRN+/+ astrocytes at all ages (Figure 1H).

Precocious neurogenesis and astrogliogenesis in GRN–/– cortical organoids. To provide further insights into how PGRN deficiency impacts the developmental trajectories of different cell types in organoids, we conducted scRNA-seq on GRN+/+ and GRN–/– organoids at 5, 16, and 25 weeks (Figure 1A). In total, we used 4–6 biological replicates and 2 experimental replicates for each time point and genotype. After quality control, we obtained 29,757–54,465 cells per time point/genotype, with 8,930 reads and 3,180 genes per cell (Supplemental Figure 2, A–D). Unsupervised clustering resulted in 18 clusters, including 3 clusters of radial glia, early neuroblasts, cortico-thalamic (CT) neuroblasts, 2 clusters of inhibitory neurons with features characteristic of lateral ganglionic eminence (LGE) origin, 6 clusters of excitatory neurons, glioblasts, astrocytes, oligodendroglial precursors (OPC), ependymal cells, and 1 cluster with mixed identity (Supplemental Table 1, A and B). Of the 3 radial glia clusters, all identified at 5 weeks, GRN+/+ organoids were more enriched in RG1 and RG2, whereas GRN–/– organoids were more enriched in RG3 (Figure 2, A–C). No differences were noted in several transient cell populations, including the early neuroblasts (cluster 3), CT neuroblasts (cluster 4), or ependymal cells (cluster 16), though a modest increase in OPCs (cluster 15) at 5 weeks in GRN+/+ organoids was noted. Consistent with the data in Figure 1, F and G, GRN–/– organoids contained more CTIP2+ neurons (cluster 7) than GRN+/+ organoids at 5 weeks (Figure 2, A–C). Compared with GRN–/– organoids, GRN+/+ organoids had many more CTIP2+SATB2+ neurons (clusters 8–9) and SATB2+ neurons (clusters 10–12) at 16 and 25 weeks (Figure 2B). GRN–/– organoids generated more LGE-type inhibitory neurons (clusters 5–6) at 16 and 25 weeks. Consistent with histological data (Figure 1I), GRN–/– organoids had significantly more cells in the astrocyte cluster (cluster 14) than GRN+/+ organoids at 16 and 25 weeks (Figure 2, A and B). In addition, GRN–/– organoids contained more cells with mixed neuron-glia identity (cluster 17) at 16 and 25 weeks. Finally, we projected our datasets onto the cortical organoid datasets previously published by our group (16). As expected, essentially all the major cell clusters identified in our previous cortical organoids, including the radial glia, excitatory neurons, inhibitory neurons, and astrocytes, were represented in both GRN+/+ and GRN–/– cortical organoids in this study (Figure 2, D and E). Taken together, our scRNA-seq data not only validated the relative abundance of radial glia, excitatory neurons, and astrocytes in GRN–/– organoids at 16 and 25 weeks but also revealed the expansion of LGE-type inhibitory neurons and the mixed-identity cluster. The presence of LGE-type inhibitory neuron clusters most likely represented the inhibitory neurons that arise de novo in the cerebral cortex (18, 19).

Single-cell transcriptomics of GRN+/+ and GRN–/– cortical organoids. (A) Uniform manifold approximation and projections (UMAPs) of combined (left), GRN+/+ (center), and GRN–/– (right) cortical organoids grouped by cluster with an overlay of RNA velocity vectors (top row) and UMAPs of GRN+/+ (center) and GRN–/– (right) cortical organoids grouped by age (bottom row). (B) Bar graphs of the percentage of cells in each cluster split by age and genotype. (*P ≤ 0.05, **P ≤ 0.01, ***P ≤ 0.001.) Statistics used unpaired 2-tailed t-test for normally distributed data and Mann-Whitney U test for not normally distributed data. (C) Dot plots of representative genes used to identify each cluster. (D and E) UMAPs comparing the scRNA-seq dataset from Bhaduri et al. (16) grouped by Bhaduri clusters (D) and the scRNA-seq dataset from GRN+/+ and GRN–/– cortical organoid datasets (this study) projected onto the Bhaduri UMAP clusters (E).

To ensure that our cortical organoids shared the areal identity with the brain regions vulnerable to disease in FTLD, we examined the expression of marker genes that defined different regions in the prenatal human brain (20). This approach revealed that both GRN+/+ and GRN–/– cortical organoids had high expression of pallium markers EMX2, FOXG1, and PAX6 but no expression of subpallium marker NKX2-1 or midbrain marker WNT1 (Supplemental Figure 2E). Furthermore, we leveraged regional transcriptomic signatures for prenatal human brain (Supplemental Table 1C) and showed that our cortical organoids exhibited robust transcriptomic profiles resembling the somatosensory cortex but had modest to minimal expression profiles for other cortical regions, including the motor, prefrontal, temporal, parietal, and visual cortex. No gene expression profiles for striatum, thalamus, or cerebellum were identified (Supplemental Figure 2F), though the expression of several FTLD-related genes, including PSAP, TMEM106B, GRN, and STMN2, was detected in most cell clusters (Supplemental Figure 2E). These results supported that iPSC-derived cortical organoids are a suitable model to investigate disease mechanisms for FTLD.

Immune activation and decreased synaptic support in GRN–/– astrocytes. Given the robust expansion of GRN–/– astrocytes in cortical organoids, we asked whether loss of PGRN altered the composition and properties of different astrocyte subtypes. To test this, we combined glioblast and astrocyte clusters and conducted unsupervised reclustering that resulted in 7 subtypes, Ast0–Ast6 (Figure 3A and Supplemental Table 2A). To investigate the identities of these subclusters, we probed the expression of canonical astrocyte markers; reactive astrocyte markers (15); progenitor markers; ER stress–related markers; immune markers, such as the major histocompatibility complex I (MHCI) genes; CD44, an activation marker for memory T helper 1 (Th1) cells (21, 22); and FTLD proteinopathy markers (Supplemental Figure 3A and Supplemental Table 2, B and C). This approach revealed that the canonical astrocyte pathways were most highly enriched in Ast0 and Ast4 (Supplemental Figure 3, B and C). Ast2 was enriched in pathways related to cell cycle, indicating that these astrocytes were actively proliferating and thus represented the most immature among all subtypes (Supplemental Figure 3, B and C). Ast1 was enriched in pathways related to translation and mitochondrial function, whereas immune activation pathways were enriched in Ast3, Ast5, and Ast6 (Supplemental Figure 3B). Among the 7 astrocyte subtypes, Ast0, Ast1, and Ast2 were the most enriched at 16 weeks. By 25 weeks, Ast3 and Ast5 showed a significant expansion (Figure 3, B and C). Notably, Ast6 was a small cluster that existed only in GRN–/–, but not in GRN+/+, astrocytes (Figure 3, A and C).

Transcriptomic profiles of astrocyte subclusters in GRN+/+ and GRN–/– cortical organoids. (A and B) UMAP of astrocytes grouped by subclusters Ast0-Ast6 split by genotype (A) and age (B). (C) Bar graphs of the total number of cells in each astrocyte subcluster by age and genotype. (D) Bar graphs of the top Gene Ontology (GO) terms defined by up- and downregulated genes in GRN–/– astrocytes compared with GRN+/+ astrocytes in 16- and 25-week organoids. G-score refers to avgFC*-log(adj_P_val). (E) Heatmap showing the G-scores of top up- and downregulated GO terms in each subcluster of GRN–/– astroglia compared with GRN+/+ astroglia. Genes listed are top DEGs in the GRN–/– astroglia in the listed GO term. G-score refers to avgFC*-log(adj_P_val). (F and G) Immunostaining of HLA-D, CTSB, and GFAP (F) or HLA-D, CTSB, and CD44 (G) in GRN+/+ and GRN–/– iPSC-derived cortical organoids at 16 and 25 weeks. (H) Quantification of CTSB+GFAP+, HLA-D+GFAP+, and CD44+ astrocytes in GRN+/+ and GRN–/– cortical organoids at 25 weeks. Statistics used Student’s t test; data represent mean ± SEM. (I) Top row has Ramsey GRN+/+ and GRN–/– astroglia clusters projected onto the Sadick UMAPs of control (Ctrl) and Alzheimer’s (AD) astrocytes (25), respectively. Bottom row has Sadick UMAPs of Ctrl and AD astrocytes grouped by Sadick clusters.

To further characterize the stage-dependent transcriptomic changes in GRN–/– astrocytes, we first combined all astrocyte subclusters and analyzed their differentially expressed genes (DEGs) and pathway enrichment at 16 and 25 weeks. Compared with GRN+/+ astrocytes, GRN–/– astrocytes were more enriched in pathways related to glutamate metabolism at 16 weeks, whereas by 25 weeks GRN–/– astrocytes were more enriched in pathways related to immune activation (Figure 3D and Supplemental Table 2, D and E). Next, we analyzed the DEGs and pathway enrichment in each individual astrocyte subcluster and showed that subclusters Ast3 and Ast5 in GRN–/– astrocytes exhibited significant upregulation in immune activation pathways, such as antigen presentation and adaptive immunity (Figure 3E and Supplemental Table 2, F and G). In support of these results, immunostaining revealed more prominent HLA-D proteins in GFAP+GRN–/– astrocytes than in GRN+/+ astrocytes at 16 and 25 weeks where no HLA-D was detected (Figure 3, F and H). Like the lysosomal phenotypes in GRN–/– microglia (7, 23, 24), many GRN–/– astrocytes contained more abundant lysosomal protein CTSB (Figure 3, F and H), supporting immune activation and potential lysosomal dysfunction in GRN–/– astrocytes. In addition, GRN–/– astrocytes also had more abundant CD44 expression than GRN+/+ astrocytes at 25 weeks (Figure 3, G and H). In addition to the upregulated immune response pathways, subclusters Ast2, Ast3, and Ast5 in GRN–/– astrocytes showed downregulation in pathways related to synaptic support, including synaptic signaling and regulation of membrane potential, whereas subclusters Ast2, Ast3, Ast4, and Ast5 in GRN–/– astrocytes exhibited downregulation in pathways related to cell signaling (Figure 3E and Supplemental Table 2, F and G). Consistent with these results, confocal microscopy revealed increased neuronal stress and cell death in GRN–/– organoids at 25 weeks (Supplemental Figure 3, D and E).

Since polymorphisms in GRN gene have been implicated as a risk factor for late-onset Alzheimer’s disease (LOAD), we projected the transcriptomes of GRN+/+ and GRN–/– astrocytes to those from patients with LOAD (25–28) (Figure 3I, Supplemental Figure 4A). This comparison showed that GRN–/– astrocytes were more enriched with cluster 4 astrocytes of the LOAD dataset, which expressed genes related to cell-matrix adhesion, including CD44 (25). In addition, GRN–/– astrocytes and LOAD astrocytes shared 187 upregulated genes, most of which were involved in apoptotic process, response to xenobiotic stimulus, autophagy, B cell receptor signaling, innate immune response, and canonical NF-κB signaling (Supplemental Figure 4B and Supplemental Table 2, H and I). Finally, we compared the DEGs in astrocyte clusters in GRN–/– cortical organoids with DEGs of astrocyte clusters from the frontal cortex of controls and patients with FTLD-GRN and thalami of 12- and 19-month-old Grn+/+ and Grn–/– mice (15, 24). These comparisons revealed significant overlaps in DEGs in astrocyte clusters across GRN–/– cortical organoids, frontal cortex from patients with FTLD-GRN, and thalami from Grn–/– mice (Supplemental Figure 4, C and D). Collectively, these results support the highly conserved astroglial phenotypes caused by PGRN deficiency across different species.

Activation of TGF-β signaling pathway in GRN–/– astrocytes. To investigate how GRN–/– astrocytes impacted other cell types in the cortical organoids, we performed MultiNicheNet analyses (29), focusing on the top 50 signaling pathways mediating cell-cell communications via ligand-receptor pairing and downstream signaling targets among astrocytes, radial glia, CTIP2+ neurons, CTIP2+SATB2+ neurons, SATB2+ neurons, and inhibitory neurons at 16 and 25 weeks. Since CTIP2+ neurons and CTIP2+SATB2+ neurons did not show any significant differences in interaction, they were excluded from the final analyses. In GRN+/+ organoids, astrocytes and SATB2+ neurons used a range of signaling pathways to communicate within themselves and with each other, including using GRN-EGFR as a cell-autonomous signal in astrocytes. Only very limited ligand-receptor pairs were identified between astrocytes and SATB2+ neurons and inhibitory neurons. In GRN–/– organoids, however, astrocytes underwent a drastic expansion of signaling pathways to astrocytes themselves and to inhibitory neurons (Supplemental Figure 5A). Among the signaling pathways, TGFB1 and EGF signals appeared to act cell-autonomously on GRN–/– astrocytes by interacting with SDC2 and ITGB1, and with ERBB2, respectively. In support of these results, gene network interaction revealed several prominent “interacting nodes” in GRN–/– astrocytes with TGFB1 as the most prominent node (Supplemental Figure 5B). Since ITGB1 has been known to dimerize with ITGAV to activate TGF-β (30, 31), we examined the expression of ITGAV using immunostains for ITGAV, SOX9, and SATB2 in organoids at 16 and 25 weeks. These results showed elevated ITGAV expression in GRN–/– organoids at both 16 and 25 weeks, especially in SOX9+ cells (Supplemental Figure 3F). Unlike GRN+/+ astrocytes, GRN–/– astrocytes showed downregulation in LAMA1-ITGA2/ITGB8 and BMP7-BMPRA1 pathways and progressive upregulation in VEGFA-GPC1, TGFB1-ITGB1, SPP1-CD44, and FN1-CD44 signaling from 16 weeks to 25 weeks (Figure 4, A and B). In addition, GRN–/– astrocytes also deployed multiple ligands that converged on GRN–/– radial glia via ITGB1, EGFR, and APLP2 (amyloid beta precursor like protein 2) (Supplemental Figure 3G).

MultiNicheNet analyses of the signaling mechanisms mediating cell-cell communications in GRN+/+ and GRN–/– cortical organoids. (A) Heatmap of astrocyte-to-astrocyte ligand-receptor pairs split by age and genotype. (B) Violin plots for the expression of TGFB1, ITGB1, ITGAV, SDC2, CD44, and FN1 in GRN+/+ and GRN–/– astrocytes. Data represent mean + SEM. (C and D) Confocal images and quantification of SOX9+pSMAD3+ cells in GRN+/+ and GRN–/– cortical organoids at 25 weeks. (E and F) Confocal images and quantification of NF-κB mean fluorescence intensity (MFI) in GRN+/+ and GRN–/– iPSC-derived cortical organoids at 25 weeks. (G and H) Confocal images and quantification of pTDP-43+SOX9+ cells in GRN+/+ and GRN–/– cortical organoids at 25 weeks. In addition, confocal images of TDP-43, pTDP-43, and GFAP in 25 weeks GRN+/+ and GRN–/– organoids show nuclear depletion of TDP-43 and the presence cytoplasmic pTDP-43 in GFAP+GRN–/– astrocytes. All data represent mean ± SEM. (I) Immuno-gold electron microscopy (IEM) of total TDP-43 (left column) and pTDP-43 (right column) in GRN+/+ and GRN–/– cortical organoids at 25 weeks. Arrows in first image highlight TDP-43+ structures in the nucleus of a GRN+/+ astrocyte, whereas arrowheads highlight many total TDP-43+ and pTDP-43+ structures in GRN–/– astrocytes (middle). (J) Western blots and quantification of the relative abundance of pSMAD3, pNF-κB, CD44, pTDP-43, and TTBK2 in GRN+/+ and GRN–/– cortical organoids at 25 weeks. Statistics used Student’s t test; data represent mean ± SEM.

To further characterize the aberrant activation of TGF-β1 signaling in GRN–/– astrocytes and how this might impact their phenotypes, we used pSMAD3 and NF-κB as markers for the canonical and noncanonical TGF-β signaling pathways, respectively (32). Using confocal microscopy, we showed that GRN+/+ organoids contained very few pSMAD3+SOX9+ cells at 16 and 25 weeks (Figure 4, C and D). Like GRN+/+ organoids, GRN–/– organoids contained few pSMAD3+SOX9+ cells at 16 weeks. By 25 weeks, however, significantly more pSMAD3+SOX9+ cells were present in GRN–/– organoids, many with intense pSMAD3 nuclear staining (Figure 4, C and D). No pSMAD3+ was detected in SATB2+ neurons in GRN+/+ or GRN–/– organoids at both stages (Figure 4C). Similar to pSMAD3, many SOX9+ cells in GRN–/– organoids showed robust NF-κB and GFAP staining at 25 weeks (Figure 4, E and F). Finally, we asked whether GRN–/– organoids could recapitulate TDP-43 proteinopathy, a diagnostic feature of FTLD-GRN (2, 13). While GRN+/+ organoids had rare pTDP-43+ cells at 16 and 25 weeks, GRN–/– organoids had significantly more pTDP-43+ cells at both ages (Figure 4, G and H). To determine which cells contained these pTDP-43+ fibrils, we stained GRN+/+ and GRN–/– organoids with SOX9, pTDP-43, and CTIP2 antibodies or with TDP-43, pTDP-43, and GFAP antibodies. In GRN+/+ organoids, SOX9+ or GFAP+ cells contained no detectable pTDP-43 immunofluorescent signals in the cytoplasm (Figure 4G). In contrast, GRN–/– organoids contained a thick layer of pTDP-43+ granules or fibrils, especially at the outer edge of the organoids (Figure 4G). Some pTDP-43 in GRN–/– organoids was identified in the cytoplasm of GFAP+ astrocytes that had lost their nuclear TDP-43 (Figure 4G). To investigate the ultrastructural characteristics of these pTDP-43+ structures, we performed immuno-gold electron microscopy (IEM) in 25-week GRN+/+ and GRN–/– cortical organoids using antibodies for total TDP-43 or pTDP-43. These results showed that in GRN+/+ organoids TDP-43 proteins were detected in the nuclei of astrocytes, whereas only very few pTDP-43 proteins were detected in the cytoplasm (Figure 4I, top). In contrast, astrocytes in GRN–/– cortical organoids contained TDP-43+ and pTDP-43+ proteins, and many were embedded within granules or fibril-like structures (Figure 4I, middle). Together, these IEM results confirmed the results from confocal microscopy and supported that PGRN deficiency in cortical organoids can lead to mislocalization and aggregation of pTDP-43 protein in astrocytic cytoplasm. To validate the phenotypes in GRN–/– cortical organoids, we performed Western blots and confirmed the significant upregulation of pSMAD3, pNF-κB, CD44, and pTDP-43 in GRN–/– cortical organoids (Figure 4J). In addition, several kinases have been implicated in the phosphorylation of cytoplasmic TDP-43, including casein kinase 1/2 (33), CDC7 (34), tau-tubulin kinase 1/2 (TTBK1/2) (35), and IκB kinase (36). To this end, we leveraged our scRNA-seq datasets to show that TTBK2 and CDC7 were more abundant in GRN–/– astrocytes than GRN+/+ astrocytes, whereas TTBK1 showed much lower expression (Supplemental Figure 6, A–F). Consistent with these results, Western blots showed that the protein level of TTBK2 was upregulated in GRN–/– cortical organoids (Figure 4L). In contrast, CDC7 protein levels showed no difference, whereas TTBK1 proteins were below detectable levels, between GRN+/+ and GRN–/– cortical organoids (Supplemental Figure 6, G and H).

Given the robust upregulation of pSMAD3 and NF-κB in GRN–/– astrocytes, we asked whether activation of TGF-β signaling might be responsible for the increased pTDP-43 in GRN–/– organoids. To test this, we treated GRN+/+ and GRN–/– organoids with TGF-β receptor inhibitors, LDN193189 (20 nM) or SB431542 (150 nM), from 20 to 25 weeks. In GRN–/– organoids, both inhibitors significantly reduced the intensity of NF-κB+ staining, the percentage of pSMAD3+SOX9+ cells, pTDP-43+ fibrils, and HLA-D expression in GRN–/– astrocytes (Figure 5, A–D, and Supplemental Figure 7A). Both TGF-β receptor inhibitors also restored the synaptic density in GRN–/– organoids and reduced cellular stress (Figure 5, D and E, and Supplemental Figure 7, B–D). Western blot analyses confirmed the effects of TGF-β receptor inhibitors to rescue pSMAD3, pNF-κB, and upregulation of TTBK2 in GRN–/– organoids (Figure 5, E and F). In contrast, the same treatment in GRN–/– organoids did not reduce the number of pTDP-43+CTIP2+ cells, nor did it affect the number of SOX9+ cells or apoptotic cell death in GRN–/– organoids (Supplemental Figure 7, A–D). These results support the importance of aberrant TGF-β signaling in promoting immune activation and TDP-43 proteinopathy in GRN–/– astrocytes. Finally, we treated GRN+/+ and GRN–/– organoids with recombinant PGRN from 16 to 25 weeks and showed that PGRN replacement significantly reduced the number of pSMAD3+SOX9+, NF-κB+SOX9+, and pTDP-43+SOX9+ cells in GRN–/– organoids (Supplemental Figure 8). Together, these results support that activation of TGF-β pathway is key to the phenotypes observed in astrocytes in GRN–/– organoids.

Inhibition of TGF-β signaling reduces pTDP-43 in GRN–/– astrocytes and restores synaptic density in GRN–/– cortical organoids. (A–D) Immunostaining of pSMAD3, SOX9, CTIP2 (A); NF-κB, SOX9, GFAP (B); SOX9, pTDP-43, CTIP2 (C); and PSD95, Bassoon (BSN), GFAP (D) in GRN+/+ and GRN–/– cortical organoids cultured under control media or treated with TGF-β receptor inhibitor LDN193189 (20 nM) or SB431542 (150 nM) from 20 to 25 weeks and harvested for histopathological characterizations at 25 weeks. (E and F) Western blots and quantification of the relative abundance of pSMAD3, pNF-κB, TTBK2, and pTDP-43 in GRN+/+ and GRN–/– cortical organoids cultured under control media or treated with LDN193189 or SB431542 from 20 to 25 weeks. Organoids (n = 3) from 3 independent biological replicates. All data represent mean ± SEM. Statistics used 2-way ANOVA with multiple comparisons.

Given the significant overlap in the transcriptomic profiles in astrocytes in GRN–/– cortical organoids, Grn–/– mice, and patients with FTLD-GRN (Supplemental Figure 4, C and D), we asked whether similar histopathological features in astrocytes of GRN–/– organoids could be identified in Grn–/– mice and patients with FTLD-GRN. Using confocal microscopy, we showed that astrocytes in the sensorimotor cortex of 19-month-old Grn–/– mice and frontal cortex of patients with FTLD-GRN also exhibited robust expression of pSMAD3, NF-κB, and pTDP-43 (Figure 6, A–D). Next, we asked whether GRN–/– cortical organoids also exhibited cryptic exon retention as seen in patients with FTLD-TDP (37, 38). Using reverse transcription quantitative PCR (RT-qPCR), we showed that the genes implicated in cryptic exon retention, such as UNC13A, KALRN, STMN2, SYT7, were significantly downregulated in GRN–/– cortical organoids at 16 and 25 weeks and in the frontal cortex of patients with FTLD-GRN (Figure 6, E and F). Consistent with these results, scRNA-seq data from GRN+/+ and GRN–/– organoids revealed that KALRN and STMN2 transcripts were modestly downregulated in several neuronal clusters, e.g., LGE inhibitory neurons and CTIP2 and SATB2 neurons, whereas no significant downregulation of SYT7 or UNC13A was observed (Supplemental Figure 9A). However, while the frontal cortex of patients with FTLD-GRN showed robust cryptic exon retention in UNC13A, KALRN, STMN2, and SYT7, no cryptic exon retention in these genes was detected in GRN–/– cortical organoids after 16 or 25 weeks in cultures (Figure 6G). The lack of cryptic exon retention phenotypes in GRN–/– cortical organoids indicated that the culture conditions for cortical organoids may need to be optimized to recapitulate loss of TDP-43 in neurons, which promotes splicing defects seen in the aging brain (38) and in iPSC-derived motor neurons (37).

Conserved TGF-β activation in PGRN-deficient astrocytes is independent of cryptic exon retention phenotype. (A) Confocal images of pSMAD3, SOX9, and GFAP (upper row); NF-κB, SOX9, and GFAP (middle row); and pTDP-43 and Sox9 (lower row) in the sensorimotor cortex of 19-month-old Grn+/+ and Grn–/– mice. (B) Quantification of pSMAD3+Sox9+, NF-κB+Sox9+, and pTDP-43+Sox9+ astrocytes in sensorimotor cortex of 19-month-old Grn+/+ and Grn–/– mice. (C) Confocal images of pSMAD3, SOX9, and GFAP (upper row); NF-κB, SOX9, and GFAP (middle row); and pTDP-43 and SOX9 (lower row) in the frontal cortex of controls and patients with FTLD-GRN. (D) Quantification of pSMAD3+SOX9+, NF-κB+SOX9+, and pTDP-43+SOX9+ astrocytes in frontal cortex of controls and patients with FTLD-GRN. N = 8 for each group; data represent mean ± SEM. Statistics used Student’s t test. (E) Confocal images of NeuN, pTDP-43, GFAP, and DAPI in the middle frontal gyrus of control and FTLD-GRN patients. Insets in the bottom panels from FTLD-GRN frontal cortex highlight NeuN+;pTDP-43+ fibril (left panel, pTDP-43+;GFAP+ fibrils (middle panel), and cytoplasmic pTDP-43+ aggregate in NeuN+ neuron (right panel). (F and G) Quantification of the relative abundance (upper graphs) and cryptic exon retention (lower graphs) of UNC13A, KALRN, STMN2, and SYT7 in GRN+/+and GRN-/- cortical organoids at 16 and 25 weeks (E) and in the frontal cortex of control and FTLD-GRN patients (F). Data represent mean ± SEM. Statistics used two-way ANOVA with multiple comparisons.

GRNR493X cortical organoids phenocopy astroglial phenotypes in GRN–/– cortical organoids. To determine whether the astroglial phenotypes in GRN–/– cortical organoids also exist in cortical organoids that contain human disease–relevant mutations, we obtained CRISPR-engineered iPSCs that carry humanized GRNR493X mutation (39), including GRNR493X/+ and GRNR493X/R493X iPSCs and their isogenic control GRN+/+ (Kolf2.1J). We used the same conditions in Figure 1A to prepare GRN+/+ (Kolf2.1J), GRNR493X/+, and GRNR493X/R493X cortical organoids and collected them for morphological analyses at 5, 10, 16, and 25 weeks. Using antibodies for CTIP2 and SATB2, we showed that, compared with GRN+/+ (Kolf2.1J) cortical organoids, GRNR493X/+ and GRNR493X/R493X cortical organoids exhibited significantly more CTIP2+SATB2– L5–6 cortical neurons at 5 weeks (Figure 7, A and B). In addition, GRNR493X/+ and GRNR493X/R493X cortical organoids contained more CTIP2–SATB2+ L1–4 cortical neurons and CTIP2+SATB2+ transitioning cortical neurons at 10 weeks (Figure 7, C and D). Using markers for astrocytes, including SOX9, S100b, and GFAP, we further showed that GRNR493X/+ and GRNR493X/R493X cortical organoids consistently had more astroglial progenitors at 16 weeks and more differentiating astrocytes and mature astrocytes at 16 and 25 weeks (Figure 7, E–H). Together, these results support that, like GRN–/– cortical organoids (Figure 1), both GRNR493X/+ and GRNR493X/R493X cortical organoids exhibited similar precocious neurogenesis and astrogliogenesis.

Precocious neurogenesis and astrogliogenesis in GRNR493X/R493X cortical organoids. (A) Confocal images of CTIP2, SATB2, and DAPI in GRN+/+, GRNR493X/+, and GRNR493X/R493X cortical organoids at 5, 10, and 15 weeks. (B–D) Quantification of the number of CTIP2+SATB2– L5–6 cortical neurons (B), CTIP2–SATB2+ L1–4 cortical neurons (C), and CTIP2+SATB2+ transitioning cortical neurons (D) at different time points in GRN+/+ (blue circle), GRNR493X/+ (red triangle), and GRNR493X/R493X (red square) cortical organoids at 5, 10, and 15 weeks. Organoids (n = 9) from 3 independent biological replicate experiments were analyzed per time point per genotype. (E) Confocal images of NESTIN, SOX9, GFAP, and S100b in GRN+/+, GRNR493X/+ and GRNR493X/R493X cortical organoids at 10, 16, and 25 weeks. (F–H) Quantification of the number of NES+SOX9+S100b– astroglial progenitors (F), NES+SOX9+S100b+ differentiating astrocytes (G), and NES–SOX9+S100b+ mature astrocytes (H) at different time points in GRN+/+ (blue circle), GRNR493X/+ (red triangle), and GRNR493X/R493X (red square) cortical organoids at 10, 16, and 25 weeks. Organoids (n = 9) from 3 independent biological replicate experiments were analyzed per time point per genotype. Statistics used Student’s t test. All data represent mean ± SEM.

Given the remarkably similar phenotypes in GRNR493X/+ and GRNR493X/R493X cortical organoids, we performed scRNA-seq using GRN+/+ (Kolf2.1J) and GRNR493X/R493X cortical organoids at 5, 16, and 25 weeks (Figure 8, A and B). In total, we used 4 biological replicates and 2 experimental replicates for each time point and genotype. After quality control, we obtained 30,343–46,141 cells per time point/genotype, with 4,076 reads and 1,982 genes per cell (Supplemental Figure 10). Unsupervised clustering resulted in 18 clusters, including 4 clusters of radial glia, neuroblasts, 2 clusters of LGE inhibitory neurons, 4 clusters of excitatory neurons, glioblasts, astrocytes, OPCs, ependymal cells, and 1 cluster with mixed identity (Supplemental Table 3, A and B). Similar to GRN+/+ and GRN–/– cortical organoids, all 4 radial glia clusters were identified at 5 weeks (Figure 8, A and B). Consistent with the data in Figure 7, A and B, GRNR493X/R493X organoids contained more CTIP2+ neurons (cluster 7) than GRN+/+ organoids at 5 weeks (Figure 8, A–C). Compared with GRN+/+ organoids, GRNR493X/R493X organoids had more SATB2+ neurons (clusters 9–10) at 25 weeks (Figure 8, A–C). Consistent with histological data (Figure 7, E–H), GRNR493X/R493X organoids had significantly more cells in the astrocyte cluster (cluster 12) than GRN+/+ organoids at 16 and 25 weeks (Figure 8, C –E).

Single-cell transcriptomics of GRN+/+ and GRNR493X/R493X cortical organoids. (A) UMAPs of combined (left), GRN+/+ (center), and GRNR493X/R493X (right) cortical organoids grouped by cluster with an overlay of RNA velocity vectors. (B) UMAPs of GRN+/+ (left) and GRNR493X/R493X (right) cortical organoids grouped by age. (C) Bar graphs of the percentage of cells in each cluster split by age and genotype. (D) Dot plots of representative genes used to identify each cluster. (E) Violin plots show the expression of GRN transcripts in all cell clusters in control and GRNR493X/R493X organoids.

Next, we combined glioblast and astrocyte clusters in GRN+/+ (Kolf2.1J) and GRNR493X/R493X cortical organoids and used unsupervised reclustering to identify 7 subtypes, Ast0–Ast6, which emerged primarily at 16 and 25 weeks (Figure 9, A–C, and Supplemental Table 4A). Similar to GRN+/+ and GRN–/– cortical organoids, GRN+/+ (Kolf2.1J) and GRNR493X/R493X cortical organoids expressed canonical astrocyte markers; reactive astrocyte markers (15); progenitor markers; ER stress–related markers; immune markers, such as the MHCI genes; CD44, an activation marker for memory Th1 cells (21, 22); and FTLD proteinopathy markers (Supplemental Figure 11 and Supplemental Table 4B). The canonical astrocyte pathways were most highly enriched in Ast0 and Ast4 (Figure 9D). Ast1 and Ast2 were enriched in pathways related to mitochondrial function, whereas immune activation pathways were enriched in Ast1, Ast2, and Ast5 (Figure 9D). Comparisons between the astrocyte subclusters between GRN+/+ (Kolf2.1J) and GRNR493X/R493X cortical organoids showed that Ast0, Ast1, and Ast2 exhibited downregulation of genes related to synaptic support, but upregulation of genes related to immune activation and inflammation, whereas Ast0, Ast1, Ast2, Ast4, and Ast5 showed mostly downregulation of genes related to protein and lipid metabolism (Figure 9, E and F, and Supplemental Table 4, C–G). Interestingly, comparison of the transcriptomes of GRN+/+ (Kolf2.1J) and GRNR493X/R493X astrocytes revealed genes enriched in mitochondrial ATP synthesis, fatty acid metabolic process, and antimicrobial immune response at 16 and 25 weeks (Figure 9, F and G). Finally, comparison of GRN–/– astrocyte dataset with GRNR493X/R493X astrocyte dataset revealed extensive overlaps in the transcriptomic profiles (Figure 9, H and I). Furthermore, GRN–/– and GRNR493X/R493X astrocyte clusters shared 100 DEGs, which belonged to GO terms including innate immune response, microtubule cytoskeleton organization, mitotic cell cycle, and negative regulation of neuron development (Figure 9J). Given the significant similarities between the transcriptomic profiles of GRN–/– and GRNR493X/R493X astrocytes, we asked whether they also share similar histopathological characteristics. In support of this idea, GRNR493X/+ and GRNR493X/R493X astrocytes showed significantly more pSMAD3, NF-κB, and pTDP-43, whereas GRNR493X/+ and GRNR493X/R493X CTIP2+ neurons also had increased pTDP-43 expression, albeit not as robust compared with GRNR493X/+ and GRNR493X/R493X astrocytes (Figure 10, A and B).

Transcriptomic profiles of astrocyte subclusters in GRN+/+ and GRNR493X/R493X cortical organoids. (A and B) UMAP of astrocyte subclusters 0 to 6 (Ast0_R-Ast6_R) split by genotype (A) and by age (B). (C) Bar graphs of the total number of cells in each astrocyte subcluster by age and genotype. (D) Heatmap showing the G-scores of top up- and downregulated GO terms in each subcluster compared with the other subclusters. Genes listed are top DEGs in the listed GO term. (E) Heatmap showing the G-scores of top up- and downregulated GO terms in each subcluster of GRNR493X/R493X astrocytes compared with GRN+/+ astrocytes. Genes listed are among the top DEGs in GRNR493X/R493X astrocytes in the listed GO term. G-score in D and E refers to avgFC*-log(adj_P_val). (F and G) Bar graphs of the top GO terms defined by up- and downregulated genes in GRNR493X/R493X astrocytes compared with GRN+/+ astroglia in 16- and 25-week organoids. Genes listed are top DEGs in GRNR493X/R493X astrocytes. G-score refers to avgFC*-log(adj_P_val). (H) GRN+/+ and GRN–/– astrocyte clusters projected onto the GRN+/+ and GRNR493X/R493X astroglia UMAP. (I) GRN+/+ and GRNR493X/R493X astrocyte clusters projected onto the GRN+/+ and GRN–/– astrocyte UMAP. (J) Venn diagram showing the overlap of the upregulated DEGs between GRN–/– vs. GRN+/+ and GRNR493X/R493X vs. GRN+/+ datasets with hypergeometric P value. Right panel is a bar graph showing GO terms based on the overlapping DEG list (left).

TGF-β activation and pTDP-43 in GRN-mutant astrocytes in GRNR493X/+ and GRNR493X/R493X cortical organoids. (A) Confocal microscopic images of pSMAD3, SOX9, and CTIP2 (upper row); NF-κB, SOX9, and GFAP (middle row); and SOX9, pTDP-43, and CTIP2 (lower row) in GRN+/+, GRNR493X/+, and GRNR493X/R493X cortical organoids at 25 weeks. (B) Quantification of pSMAD3+SOX9+ cells, NF-κB MFI, pTDP-43+SOX9+ cells, and pTDP-43+CTIP2+ cells in GRN+/+, GRNR493X/+, and GRNR493X/R493X cortical organoids. All data represe