Diet-dependent regulation of TGFβ impairs reparative innate immune responses after demyelination

Abstract

Proregenerative responses are required for the restoration of nervous-system functionality in demyelinating diseases such as multiple sclerosis (MS). Yet, the limiting factors responsible for poor CNS repair are only partially understood. Here, we test the impact of a Western diet (WD) on phagocyte function in a mouse model of demyelinating injury that requires microglial innate immune function for a regenerative response to occur. We find that WD feeding triggers an ageing-related, dysfunctional metabolic response that is associated with impaired myelin-debris clearance in microglia, thereby impairing lesion recovery after demyelination. Mechanistically, we detect enhanced transforming growth factor beta (TGFβ) signalling, which suppresses the activation of the liver X receptor (LXR)-regulated genes involved in cholesterol efflux, thereby inhibiting phagocytic clearance of myelin and cholesterol. Blocking TGFβ or promoting triggering receptor expressed on myeloid cells 2 (TREM2) activity restores microglia responsiveness and myelin-debris clearance after demyelinating injury. Thus, we have identified a druggable microglial immune checkpoint mechanism regulating the microglial response to injury that promotes remyelination.

Extended Data Fig.1. The plasma lipidome is altered by Western diet.

a, PCA analysis of CD and WD plasma samples. b, Mol% of the sample occupied by the different lipid classes in CD- and WD-fed mice (mean±SD, two-tailed Welch’s t-test). c,e, Mol% of each sample with lipids containing a certain number of double bonds (c) or a certain acyl chain length (e) (mean±SD, two-tailed Welch’s t-test). d, Heatmap showing the significantly (p value ≤ 0.01, fold ≥2.5) changed lipid species in plasma from CD- and WD-fed mice. Scale indicated on top of the heatmap. Increased values are indicated in orange, while decreased values are in blue. f, Quantification of the glucose level in blood at baseline (0 minutes) and 15, 30, 60 and 120 minutes after intraperitoneal glucose administration. (mean±SD, two-tailed Welch’s t-test). g, PCA analysis of plasma from young (3-months old) versus old (12-months old) mice. h, Mol% of the sample occupied by the different lipid classes in plasma from young and old mice (mean±SD, two-tailed Welch’s t-test). i,k, Mol% of each sample with lipids containing a certain number of double bonds (i) or a certain acyl chain length (k) in plasma from young and old mice (mean±SD, two-tailed Welch’s t-test). j, Heatmap showing the significantly (p value ≤ 0.05, fold ≥1.3) changed lipid species in plasma from young and old mice. Scale indicated on top of the heatmap. Increased values are indicated in orange, while decreased values are in blue. P-values below 0.1 and n numbers are indicated in the figures. PCA: principal component analysis, CD: control diet, WD: Western diet, CE: cholesterol esters, Chol: cholesterol, DAG: diacylglycerol, LPC: lysophosphatidylcholine, PC: phosphatidylcholine, TAG: triacylglycerides, PI: Phosphatodylinositol. In d and j, the lipids are numbered according to the carbon length; number of double bonds; and number of hydroxyl groups (for example TAG 52;3;0).

Extended Data Fig.2. Western diet feeding alters the brain lipidome of mice.

a, PCA analysis of white matter (WM) and grey matter (GM) samples from brain of WD- and CD-fed mice. b,c, Lipid classes changed in brain WM (b) and GM (c) between CD- and WD-fed mice (n = 3 for WD WM, CD GM and WD GM. N = 4 for CD WM, data represent mean±SD, two-tailed Welch’s t-test). d,e, Heatmap showing the significantly (p value ≤ 0.5, fold ≥1.3) changed lipid species in the brain WM (d) and in the brain GM (e). Scale indicated on the right side of the heatmap. Increased values are indicated in orange, while decreased values are in blue. f,g, Mol% of each sample with lipids containing a certain number of double bonds (f) or a certain acyl chain length (g) (mean±SD, two-tailed Welch’s t-test). The data is shown for those lipid species significantly (p value ≤ 0.05, fold ?1.3) changed in the WM (n = 3 for WD WM, n = 4 for CD WM, data represent mean± SD, two-tailed Welch’s t-test). h,i, Mol% of each sample with lipids containing a certain number of double bonds (h) or a certain acyl chain length (i). The data is shown for those lipid species significantly (p value ≤ 0.05, fold ?1.3) changed in the GM (n = 3 for both groups, data represent mean±SD, two-tailed Welch’s t-test). j,k, Mol% of the sample occupied by the different lipid classes in the brain WM (j) and GM (k) in CD- and WD-fed mice (mean±SD, two-tailed Welch’s t-test). l, Quantification of the number of lipid droplets detected in the ventricle wall separating the corpus callosum from the lateral ventricles (solid lines indicate the mean, two-tailed Welch’s t-test).m, Representative image of a PLIN2 staining in the ventricle wall demonstrating the accumulation of lipid droplets in this structure. Scale bar: 5μm. n, Images of the ventricle wall separating the corpus callosum from the second ventricle in CD- and WD-fed mice. Lipid droplets are labelled in pale green and marked with white arrows. Scale bar: 5μm. o, Quantification of the percentage of IBA1⁺ cells containing PLIN2⁺ lipid droplets in the corpus callosum (solid lines indicate the mean, two-tailed Welch’s t-test). p, Example images of microglia containing PLIN2⁺ lipid droplets in their cytoplasm. On the top row, the raw image is displayed. On the bottom row, a 3D clip of the corresponding image is displayed, where the PLIN2⁺ signal inside the cell is indicated with a white arrow. Scale bar images left side: 3μm, Scale bar images right side: 2μm. q, Quantification of the percentage of IBA1⁺ area occupied by PLIN2⁺ signal (solid lines indicate the mean, two-tailed Welch’s t-test). r, Quantification of microglia density in the corpus callosum (solid lines indicate the mean, two-tailed Welch’s t-test). s, Measurement of IBA1⁺ signal intensity in the corpus callosum (two-tailed Welch’s t-test). t, Images of the corpus callosum (CC) and cortex (Ctx) stained with IBA1 to label microglia, GFAP to label astrocytes and PLIN2 to label lipid droplets. White arrows indicate lipid droplets within GFAP⁺ cells; blue arrows indicate lipid droplets within IBA1⁺ cells. Scale bar: 100 μm. u, Quantification of the percentage of GFAP⁺ area occupied by PLIN2⁺ signal (solid lines indicate the mean, two-tailed Welch’s t-test). v,w, Area (v) and intensity (w) of GFAP⁺ staining in the corpus callosum of CD- and WD-fed mice. P-values below 0.1 and n numbers are indicated in the figures; each dot represents one mouse. PCA: principal component analysis, CD: control diet, WD: Western diet, WM: white matter, GM: grey matter, LPC: lysophosphatidylcholine, PG: phosphatidylglycerol, PC: phosphatidylcholine, PE: phosphatidylethanolamine, PE O-: Phosphatidylethanolamine-ether, LPE: lysophosphatidylethanolamine, DAG: diacylglycerol, PC O-: Phosphatidylcholine-ether, PS: phosphatidylserine Ctx: cortex, CC: corpus callosum, PLIN2: Perilipin2. In d and e, the lipids are numbered according to the carbon length; number of double bonds; and number of hydroxyl groups (for example LPE 24;4;0).

Extended Data Fig.3. Western diet consumption causes weak microglia activation.

a-c, Quantification of the percentage of CLEC7A⁺/IBA1⁺ (a), AXL⁺/ IBA⁺ (b) and MAC2⁺/IBA1⁺ (c) cells over all the population of IBA1⁺ cells (solid lines indicate the mean, two-tailed Welch’s t-test). d, Quantification of the mean grey value of fluorescently labelled Evans Blue in whole brain sections of CD- and WD-fed mice (solid lines indicate the mean, two-tailed Welch’s t-test). e-g Images of microglia in the corpus callosum labelled with IBA1 and the activation markers CLEC7A (e), AXL (f) and MAC2 (g). White arrows indicate cells positive for both IBA1 and the corresponding activation marker. Scale bars: CLEC7A: 10μm, AXL and MAC2: 20μm. h, Images of two whole brain sections of CD- and WD-fed mice demonstrating the presence of fluorescently-labelled Evans Blue in the brain. Scale bar: 500 μm. P-values below 0.1 and n numbers are indicated in the figure; each dot represents one mouse. CD: control diet, WD: western diet.

Extended Data Fig.4. The differential production of endogenous LXR ligands does not explain the poor induction of the LXR pathway observed in WD-fed mice.

a, Quantification of IBA1⁺ cell density in the demyelinated lesions at 4 and 7 dpi in CD- and WD-fed mice. b, Images demonstrating the density of IBA1⁺ cells in demyelinated lesions at 4 and 7dpi. Scale bar: 20μm. c, Quantification of the increase in APOE levels from 2 to 7 dpi in CD- and WD-fed mice (two-tail Welch’s t-test). d, Example images of the Western blots used for quantification of APOE levels. Molecular weights are indicated on the left side. APOE levels were normalized to α-TUBULIN (α-TUB). e,f, Quantification of the number of myelin- (e) and crystal- (f) loaded IBA1⁺ cells per mm in lesion of CD-, WD-, WD + FF- and WD+ RG-fed mice. FF and RG treatments successfully promoted myelin clearance by phagocytes in WD-fed mice (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). The references groups, CD and WD, are from Fig. 4e,f. g, Images of the demyelinated lesion in the corpus callosum at 14dpi exemplifying myelin- and crystal-loaded IBA1⁺ cells in all treatment groups. Scale bar: 20μm. h, Images demonstrating the co-localization of the cholesterol crystal signal obtained by reflection microscopy with either PLIN2 (green) or CD68 signal (magenta). Original images and 3D clips are shown. Scale bar: 2 μm. i, Diagram illustrating the production of the various natural liver X receptor (LXR) ligands measured in our assay. j-l, Quantification of the amounts of the endogenous LXR agonists desmosterol (j), 24-hydroxycholesterol (k) and 27-hydroxycholesterol (l) in the demyelinated lesions at 4 and 7dpi in CD- and WD-fed mice. Each LXR ligand was normalized to the cholesterol amounts in the same lesion (two-way ANOVA followed by multiple comparisons correction with Sidak test). Solid lines in the graphs indicate the mean. P-values below 0.1 and n numbers are indicated in the figure; each dot represents one mouse. dpi: days post injection, CD: control diet, WD: Western diet, α-TUB: α-tubulin, Chol: cholesterol, FF: Fenofibrate, RG: rosiglitazone.

Extended Data Fig.5. TGFβ signaling is increased in the unlesioned brain of WD-fed mice.

a,b, Overview images of MHCII⁺IBA1⁺ (a) and MAC2⁺IBA1⁺(b) cells in the demyelinated lesions at 4dpi. Scale bar: 20μm. c, Images of the unlesioned corpus callosum of CD- and WD-fed mice demonstrating the accumulation of Tgfb1 and Tgfb2 particles visualized by RNA in situ hybridization. Scale bar: 20μm. d, Fold change in Tgfb1 and Tgfb2 expression in the brain of WD-fed mice relative to CD-fed mice (two-tailed Welch’s t-test). e, Quantification of the number of RNA particles of Tgfb1 and Tgfb2 per nuclei in the corpus callosum in CD- and WD-fed mice (two-tailed Welch’s t-test). f, Images of the unlesioned corpus callosum of CD- and WD-fed mice demonstrating the Tgfb1 and Tgfb2 particles accumulating within GFAP&ALDH1L1⁺ cells in the unlesioned corpus callosum of CD- and WD-fed mice. Scale bar: 20μm. g,h, Quantification of the number of Tgfb1 and Tgfb2 particles within IBA1⁺ (g) or GFAP&ALDH1L1⁺ cells (h) in the unlesioned corpus callosum of CD- and WD-fed mice (two-tailed Welch’s t-test). i, Quantification using ELISA of TGFβ1 in the 2 dpi lesions in CD and WD mice. No significant differences were observed (p = 0.14, two-tailed Welch’s t-test). j, Quantification of the pSMAD2⁺ area within IBA1⁺ area in the unlesioned corpus callosum (two-tailed Welch’s t-test). k, Images of the unlesioned CC of CD- and WD-fed mice demonstrating accumulation of pSMAD2⁺ signal within IBA1⁺ cells. White arrows point to IBA1⁺ cells accumulating low amounts of pSMAD2⁺ signal within their nucleus. Scale bar: 40 μm. Solid lines in the graphs indicate the mean. P-values below 0.1 and n numbers are indicated in the figure. dpi: days post injection, CD: control diet, WD: Western diet. CC: corpus callosum, Ctx: cortex.

Extended Data Fig.6. Distribution of TGFβ particles in the demyelinated lesion.

a,b, Images of the fluorescent in situ hybridization of Tgfb1 and Tgfb2 in the demyelinated lesion at 2 dpi showing accumulation within IBA1⁺ (a) cells or within GFAP&ALDH1L1⁺ cells (b). Scale bar: 20μm in the overview, 10μm in the Zoom-in. c, Quantification of the percentage of Tgfb1 and Tgfb2 mRNA particles in IBA1⁺ or in GFAP&ALDH1L1⁺ cells over the total number of cells in a demyelinated lesion at 2 dpi. ((mean±SD, two-tailed Welch’s t-test). d-f, Expression change in Tgfb1 and Tgfb2 induced by high glucose concentrations in cultured primary microglia (d), high lipid concentrations in cultured primary microglia (e) and high lipid concentrations in cultured primary astrocytes (f) (two-tailed paired t-test). Solid lines in the graphs indicate the mean. P-values below 0.1 and n numbers are indicated in the figure. dpi: days post injection, CD: control diet, WD: Western diet.

Extended Data Fig.7. Blocking TGFβ signaling does not improve repair in old mice.

a, Fold change in Tgfbr2 expression in the demyelinated lesions of Tgfbr2 KO and control mice (two-tailed Welch’s t-test). b, Quantification of the number of Tgfbr2’ microglia in the unlesioned brains of Tgfbr2 KO and control mice (two-tailed Welch’s t test). c, Images of the unlesioned brain of Tgfbr2 KO and control mice demonstrating the accumulation of Tgfbr2 RNA particles within IBA1⁺ microglia. Scale bar: 20μm. d, Quantification of the ratio of TGFβR2 signal over GAPDH signal in microglia isolated from Tgfbr2 KO and control mice (two-tailed t-test). e, Example images of the Western blots used for quantification of TGFβR2 levels of isolated microglia from Tgfbr2 KO and control mice. TGFβR2 levels were normalized to GAPDH. f,g, Quantification of the demyelination (f) and IBA1⁺ (g) volume at 4 dpi in Tgfbr2 KO and control mice fed WD. h,i, Quantification of the demyelination (h) and IBA1⁺ (i) volume at 4dpi in Tgfbr2 control and KO mice fed CD. j, Quantification of Tgfbl and Tgfb2 expression in the unlesioned brain of young (3-months old) and old (12-months old) mice by RT-qPCR (two-tailed Welch’s t-test). k,l, Quantification of demyelination k) and IBA1⁺ (l) volume at 14 dpi in young, old and old+GS mice (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). m, Images of corpus callosum lesions of old and old+GS mice at 14dpi. Scale bar: 200μm. n,o, Quantification of the number of myelin- (n) and crystal- (o) loaded IBA1⁺ cells per mm of lesion (two-tailed Welch’s t-test). p, Images of the demyelinated lesion in the corpus callosum at 14dpi exemplifying myelin- and crystal-loaded IBA1⁺ cells in old and old+GS mice. Scale bar: 20μm. N numbers are indicated in the figure; each dot represents one mouse. Solid lines in the graphs indicate the mean. CD: control diet, WD: Western diet GS: Galunisertib, dpi: days post injection.

Extended Data Fig.8. 4D9 treatment prevents myelin-induced TREM2 shedding.

a,d, Quantification using ELISA of cellular TREM2 in the unlesioned brain of old (12-months old) and young (3-months old) mice (a) and of CD- and WD-fed mice (d) (two-tailed Welch’s t-test). b,e, Quantification using ELISA of soluble TREM2 in the unlesioned brain old and young mice (b) and of CD- and WD-fed mice (e) (two-tailed Welch’s t-test). c, Change in expression of Trem2 in the demyelinated lesions of old mice at 2 dpi when compared to young mice (two-tailed Welch’s t-test). f,g, Quantification of the band density in Western blots of TREM2-labelled (f) and sTREM2-labelled (g) bands normalized by the density of the bands labelled by α-TUBULIN (α-TUB). Microglia were treated with myelin for 24 hours (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). h, Example images of the Western blots used for quantification of TREM2 and sTREM2 densities. Molecular weight ladders are indicated on the left side. i, Quantification by ELISA of the amounts of sTREM2 found in the media in different conditions. Microglia were treated with 20μg/mL of 4D9 antibody or IgG isotype control for 16hours, followed by 24hours of myelin treatment (two-tailed Welch’s t-test). P-values and n numbers are indicated in the figure. Solid lines in the graphs indicate the mean. dpi: days post injection, CD: control diet, WD: Western diet, sTREM2: soluble TREM2, Mye5: 5μg/mL myelin treatment, Mye8: 8μg/mL myelin treatment, Mye30: 30μg/mL myelin treatment, 4D9: TREM2 enhancing antibody.

Fig. 1. WD impairs lesion recovery after demyelinating injury.

a, Schematic representation of the diet and timeline. b, Illustration showing the percentage of crude nutrients in CD and WD. c, Illustration of the percentage of metabolizable energy contained in fat, proteins and carbohydrates. d, Violin plot of the body weight of mice fed WD or CD for 10 weeks. Solid lines indicate the 25%, 50% and 75% quartiles. For CD, n = 52; for WD, n = 54 (two-tailed Welch’s f-test). e, Body weight increase over time either under the CD or WD (n = 10 for both groups, data represent mean±s.d., two-tailed Welch’s f-test). f,g, Demyelination (f) and IBA1 ⁺ (g) volume at 4 and 14dpi in CD- and WD-fed mice. Solid lines indicate the mean (two-tailed Welch’s f-test). h,i, Images of corpus callosum lesions in CD- and WD-fed mice at 4 (h) and 14 (i) dpi. Scale bar, 200 μm. j, Quantification of the number of CC1⁺ cells per mm of lesion. Solid lines indicate the mean (two-tailed Welch’s f-test). k, Images of the demyelinated lesions in the corpus callosum at 14 dpi exemplifying the numbers of CC1⁺ cells at the demyelination-remyelination edge. White arrows indicate CC1⁺ cells. Scale bar, 20 μm. l,m, Demyelination (l) and IBA1⁺ (m) volume at 4 and 14dpi in lep^wt/ob and lep ^ob/ob mice. Solid lines indicate the mean (two-tailed Welch’s f-test). n,o, Images of corpus callosum lesions in lep^wt/°^b and lep^ob/lbmice at 4 (n) and 14 (o) dpi. Scale bar, 200μm. P values below 0.1 and n numbers are indicated in the figure; each dot represents one mouse.

Fig. 2. Correcting metabolic alterations induced by WD improves lesion recovery after demyelination.

a,b, Quantification of demyelination (a) and IBA1⁺ (b) volume at 14dpi in CD-, WD-, WD+FF- and WD+RG-fed mice (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). c, Images of corpus callosum lesions of all treatment groups at 14 dpi. Scale bar, 200 μm. d, Quantification of the demyelination volume at 14 dpi in old, old+FF and old+RG mice. We observed no differences between treatment groups (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). P-values below 0.1 and n values are indicated in the figure; each dot represents one mouse. Solid lines in the graphs indicate the mean. WD+FF, WD supplemented with FF; WF+RG, WD supplemented with RG; Old+FF, old mice fed FF-containing chow; Old+RG, old mice fed RG-containing chow.

Fig. 3. Demyelinated lesions of WD-fed mice accumulate myelin- and crystal-loaded phagocytes.

a,b,d, Quantification of the number of myelin- (a), PLP- (b) and crystal-loaded (d) IBA1⁺ cells per mm of lesion at 14dpi (two-tailed Welch’s f-test). c, Images of the demyelinated lesions in the corpus callosum at 14dpi showing myelin- and crystal-loaded IBA1⁺ cells in CD- and WD-fed mice. White arrows indicate myelin- and crystal-loaded IBA1⁺ cells. Blue arrows indicate myelin-loaded IBA1⁺ cells. Scale bar, 20μm. e, Quantification of foam cells per mm of lesion at 21 dpi (two-tailed Welch’s f-test). f, Images of demyelinated lesions in the spinal cord of CD- and WD-fed mice at 21 dpi demonstrating foam-cell accumulation. Examples of foam cells are circled with a solid black line. The demyelinated area is indicated with a dashed line. The zoom-in regions are indicated in the overview as squares. Scale bar, overview 50 μm, zoom-in 20μm. g, Electron microscopy images demonstrating crystal accumulation in the cytoplasm (left), lipid droplets (top right) and lysosomes (bottom right). Blue arrows indicate crystals shown in the magnification on the top left corner of each image. Scale bar, 2.5μm. h, Quantification of the percentage of lesion area occupied by LAMP1⁺ signal in the 14dpi lesion (two-tailed Welch’s f-test). j, Images demonstrating accumulation of myelin debris in LAMP1⁺ lysosomes of IBA1⁺ cells in demyelinated lesions at 14dpi. White arrows point to myelin-debris accumulation within LAMP1⁺ organelles of IBA1⁺ cells. Yellow arrows indicate crystal accumulation within an IBA1⁺ cell. Scale bar, 5μm. i,k, Quantification of myelin-loaded IBA1⁺ cells (i) and the percentage of PLIN⁺CD68⁺ signal (k) in demyelinated lesions at 4dpi. l, Images of demyelinated lesions in the corpus callosum at 4dpi demonstrating myelin accumulation within IBA1⁺ phagocytes. Scale bar, 20μm. m, Images of demyelinated lesions at 4 dpi demonstrating PLIN⁺ signal within CD68⁺ phagocytes. Scale bar, 20μm. P-values below 0.1 and n numbers are indicated in the figure; each dot represents one mouse. Solid lines in the graphs indicate the mean.

Fig. 4. The LXR pathway is insufficiently activated in WD-fed mice.

a, Quantification of the increase in mRNA expression of Apoe, Abca1 and Abcg1 from 2 to 7 dpi lesions from CD- and WD-fed mice by RT-qPCR (two-tailed Welch’s t-test). b, Quantification of the numbers of Abca1 and Abcg1 RNA particles visualized by in situ RNA hybridization within the demyelinated lesions at 14dpi in CD- and WD-fed mice (two-tailed Welch’s t-test). c,d, Quantification of demyelination (c) and IBA1 ⁺ (d) volume at 14dpi in CD-, WD- and WD+GW-fed mice (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). The reference groups (CD and WD) are from Fig. 2a,b. e,f, Quantification of the number of myelin- (e) and crystal-loaded (f) IBA1⁺ cells per mm of lesion (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). g, Images of corpus callosum lesions of all groups at 14 dpi. Scale bars, 200 μm. h, Images of the demyelinated lesion in the corpus callosum at 14 dpi, exemplifying myelin- and crystal-loaded IBA1⁺ cells in all treatment groups. White arrows indicate myelin- and crystal-loaded IBA1⁺ phagocytes. Scale bars, 20μm. P-values below 0.1 and n numbers are indicated in the figure; each dot represents one mouse. Solid lines in the graphs indicate the mean. WD+GW, WD supplemented with GW3965.

Fig. 5. Impaired microglia activation correlates with increased TGFβ signalling in the brain after WD feeding.

a,c, Quantification of the percentage of MHCII⁺IBA1⁺ cells (a) and MAC2⁺IBA1⁺ cells (c) over IBA1⁺ cells in the demyelinated lesion at 4dpi (two-tailed Welch’s f-test). b,d, Images of MHCII⁺IBA1⁺ (b) and MAC2⁺IBA1⁺ (d) cells in the demyelinated lesions at 4dpi. Scale bar, 10 μm. e, Quantification of Tgfbl and Tgfb2 expression in the 2 dpi lesion by RT- qPCR (two-tailed Welch’s t-test). f,g, Quantification of Tgfbl and Tgfb2 RNA particles visualized by RNA in situ hybridization within IBA1⁺ cells (f) or within GFAP⁺ALDH1L1⁺ cells (g) (two-tailed Welch’s f-test). h, Images of the demyelinated lesions at 2 dpi demonstrating the accumulation of Tgfbl and Tgfb2 transcripts in GFAP⁺ALDH1L1⁺ cells. Scale bar, 20 μm. White arrows indicate the cell shown in the zoom-in panel. j,k, Quantification of lesion area covered by GFAP⁺ signal at 4dpi (j) and 14dpi (k) (two-tailed Welch’s f-test). l,m, Quantification of the lesion area covered by pSMAD2 over the number of nuclei (l) and the number of nuclei per mm of lesion (m) in the demyelinated lesions at 4dpi (two-tailed Welch’s f-test). n,o, Quantification of the pSMAD2⁺ signal within CD68⁺ area (n) and of the pSMAD3⁺ signal within IBA1⁺ area (o) in the demyelinated lesions at 4dpi (two-tailed Welch’s f-test). p, Images of the demyelinated lesion at 4 dpi demonstrating the accumulation of GFAP⁺ signal. Scale bar, 20 μm. q, Images of demyelinated lesions at 4 dpi showing pSMAD2 and DAPI staining and nuclear translocation of pSMAD2. Scale bar, 20 μm in overview, 5μm in the images demonstrating nuclear translocation of pSMAD2. r, Images of the demyelinated lesion at 4dpi demonstrating pSMAD2 and CD68 staining. White arrows point to CD68⁺ cells accumulating pSMAD2⁺ signal within their nucleus. Scale bar, 20μm. s, Images of the demyelinated lesion at 4dpi demonstrating pSMAD3 and IBA1 staining. Scale bar, 20μm. Solid lines in the graphs indicate the mean. P-values below 0.1 and n numbers are indicated in the figure; each dot represents one mouse.

Fig. 6. TGFβ blocks cholesterol efflux gene induction after myelin uptake.

a, Schematic representation of the in vitro experimental approach to analyse induction of Abca1 and Abcg1 in microglia upon myelin treatment and TGFβ treatment. LPDS, lipoprotein-deficient serum; L929, L929 cell line conditioned media. b, Quantification of the average number of PLP⁺ myelin particles within phagocytes after 2 hours of incubation with myelin in TGFβ-treated and control cells. c,d, Quantification of the increase in mRNA expression of Abca1 and Abcg1 4hours (c) and 24hours (d) after myelin phagocytosis with or without TGFβ treatment in primary microglia (two-tailed Welch’s f-test). e, Quantification of the increase in mRNA expression of Abca1 and Abcg1 4hour after myelin phagocytosis with or without TGFβ treatment in BMDMs (two-tailed Welch’s f-test). f, Quantification of the increase in mRNA expression o’ Abca1 and Abcg1 induced by TGFβ in TGFβ-treated and control cells. No significant differences were observed (two-tailed Welch’s f-test). Solid lines in th graphs indicate the mean. P-values below 0.1 and n numbers are indicated in the figure.

Fig. 7. Blocking TGFβ signalling in microglia of WD-fed mice promotes recovery from demyelinating inj’ury.

a, Quantification of the increase in mRNA expression of Apoe, Abca1 and Abcg1 from 2 to 7dpi lesions from Cx3cr1^creERT,wt:Tgfbr2^fí/f, (Tgfbr2 KO) or Cx3cr1^wt,wt:Tgfbr2^fl/fl (Tgfbr2 Control) mice fed a WD (two-tailed Welch’s t-test). b,d, Quantification of demyelination (b) and IBA1⁺ (d) volume at 14dpi in Tgfbr2 control and KO mice treated with tamoxifen 14 days before lesion induction and fed WD (two-tailed Welch’s t-test). c,f, Quantification of demyelination (c) and IBA1⁺ (f) volume at 14dpi in Tgfbr2 control and KO mice treated with tamoxifen 14 days before lesion induction and fed CD (two-tailed Welch’s t-test). e, Images of corpus callosum lesions at 14 dpi. Scale bar: 200 μm. g,h Quantification of the number of myelin- (g) and crystal-loaded (h) IBA1⁺ cells per mm of lesion (two-tailed Welch’s t-test). i, Images of the demyelinated lesion in the corpus callosum at 14dpi showing myelin- and crystal-loaded IBA1⁺ cells. White arrows point to myelin- and crystal-loaded IBA1⁺ cells. Scale bar, 20 μm. j, The site of action of the conditional genetic knock-out and mode of action of GS in the TGFβ pathway. GS, galunisertib. k,l, Quantification of demyelination (k) and IBA1⁺ (l) volume at 14dpi (one-way Brown-Forsythe and Welch ANOVA tests with multiple comparisons corrected by Dunnett T3 test). m, Images of corpus callosum lesions at 14 dpi. Scale bar, 200 μm. n,o, Quantification of the number of myelin- (n) and crystal-loaded (o) IBA1⁺ cells per mm of lesion (two-tailed Welch’s t-test). p, Images of the demyelinated lesion in the corpus callosum at 14dpi exemplifying myelin- and crystal-loaded IBA1⁺ cells. White arrows point to myelin- and crystal-loaded IBA1⁺ cells. Scale bar, 20μm. P-values below 0.1 and n numbers are indicated in the figure; each dot represents one mouse. Solid lines in the graphs indicate the mean.

Fig. 8. Treatment with TREM2-activating monoclonal antibodies 4D9 improves lipid clearance in phagocytes after demyelinating injury.

a, Quantification of the induction of the Trem2 and Prgn expression by myelin intake (P for Trem2 induction = 0.03, one sample f-test) and the influence of TGFβ on :his induction (P for Trem2 = 0.02, two-tailed Welch’s f-test). No significant differences were observed for Prgn. b, Quantification of the induction of Trem2 expression in demyelinated lesions from 2 to 7 dpi (two-tailed Welch’s f-test). c, Quantification of TREM2 levels in FluoroMyelin⁺ (FM⁺) cells n the demyelinated lesions at 14dpi (two-tailed Welch’s f-test). d, Images of the demyelinated lesions at 14dpi demonstrating TREM2 expression in myelin-loaded IBA1⁺ cells. Scale bar, 20μm. e, Quantification of the expression change in Abca1 and Abcg1 upon myelin intake in BMDMs incubated with 4D9 or its isotype control (paired f-test). f, Quantification of lesion area occupied by foam cells at 14dpi in WD-fed mice treated intraperitoneally with 100 mg/kg (body weight) of 4D9 antibody or its isotype control (two-tailed Welch’s f-test). g, Quantification of the number of foam cells per mm of esion at 14 dpi in 12-month-old mice treated intraperitoneally with 100 mg/kg (body weight) 4D9 antibody or its isotype control (two-tailed Welch’s :-test). h, Quantification of the number of remyelinated axons per mm of lesion at 21dpi in 12-month-old mice treated intraperitoneally with 100 mg/kg fbody weight) of 4D9 antibody or its isotype control (two-tailed Welch’s f-test). i, Electron microscopy images of the demyelinated lesions in the spinal :ord at 14 dpi exemplifying foam-cell accumulation within the lesion. Scale bar, 10 μm. j, Electron microscopy images of the demyelinated lesions in the spinal cord at 14dpi exemplifying accumulation of foam cells within the lesion. Scale bar, 10μm. k, Electron microscopy images of the demyelinated lesions n the spinal cord at 21 dpi exemplifying remyelinated axons. Scale bar, 10μm. Pvalues below 0.1 and n numbers are indicated in the figure. Solid lines in he graphs indicate the mean.