Reduced mitochondrial calcium uptake in macrophages is a major driver of inflammaging

Abstract

Mitochondrial dysfunction is linked to age-associated inflammation or inflammaging, but underlying mechanisms are not understood. Analyses of 700 human blood transcriptomes revealed clear signs of age-associated low-grade inflammation. Among changes in mitochondrial components, we found that the expression of mitochondrial calcium uniporter (MCU) and its regulatory subunit MICU1, genes central to mitochondrial Ca²⁺ (mCa²⁺) signaling, correlated inversely with age. Indeed, mCa²⁺ uptake capacity of mouse macrophages decreased significantly with age. We show that in both human and mouse macrophages, reduced mCa²⁺ uptake amplifies cytosolic Ca²⁺ oscillations and potentiates downstream nuclear factor kappa B activation, which is central to inflammation. Our findings pinpoint the mitochondrial calcium uniporter complex as a keystone molecular apparatus that links age-related changes in mitochondrial physiology to systemic macrophage-mediated age-associated inflammation. The findings raise the exciting possibility that restoring mCa²⁺ uptake capacity in tissue-resident macrophages may decrease inflammaging of specific organs and alleviate age-associated conditions such as neurodegenerative and cardiometabolic diseases.

Fig. 1. Age-related changes in whole-blood gene expression are associated with increased inflammatory gene transcription and decreased expression of genes encoding mitochondrial Ca²⁺ transport.

a, GTEx database mined for tissue-specific gene expression across five indicated age groups; note the color coding for the age groups. b, Left, PCA of whole-blood gene expression from every sample, color coded according to the age groups. Right, the same data were used and color-coded clusters from each age group were overlaid. Note the variance in gene expression from different age groups. c, PCA plots from b were used to show only samples from the youngest and oldest age groups analyzed. d, Hallmark GSEA based on differential gene expression between the oldest (60–69 years) and youngest (20–29 years) datasets. Pathways were ranked by P value and plotted on the x axis by the normalized enrichment scores. e, GSEA of GSEA hallmark pathway, TNF signaling via NF-κB, based on differential gene expression of oldest (60–69 years) versus youngest (20–29 years) GTEx samples. Enrichment scores are plotted on the y axis and genes ranked in the ordered dataset are plotted on the x axis. f, GSEA of the IL-2–STAT5 GSEA hallmark pathway. g, GSEA of inflammatory response GSEA hallmark pathway. h, GSEA of the oxidative phosphorylation GSEA hallmark pathway. i, Heat map of expression levels of genes associated with the TNF–NF-κB pathway. Expression values were calculated as a fold change from the 20–29-year age group. j, mitoXplorer Pathway analysis based on DSeq2 analysis of oldest (60–69 years) versus youngest (20–29 years) GTEx samples. k, Individual genes in the calcium signaling and transport pathway were identified from mitoXplorer pathway analysis based on DSeq2 analysis of oldest (60–69 years) versus youngest (20–29 years) GTEx samples. Fold change was determined as a relative change in 60–69-year compared to 20–29-year GTEX samples. l, MCU gene counts for each sample in the GTEx database sorted by age. Error bars reflect the s.e.m.; P values were calculated using ordinary one-way analysis of variance (ANOVA). m, MICU1 gene counts for each sample in GTEx database sorted by age. Error bars reflect the s.e.m.; P values were calculated using ordinary one-way ANOVA. Source data

Fig. 2. Macrophages generated from aged mice display decreased mitochondrial Ca²⁺ uptake.

a, Mcu expression in BMDMs. N = 12 biological replicates, from four mice. Error bars reflect the s.e.m.; P = 0.0016 according to Welch’s t-test, two-tailed. b, Representative traces of mCa²⁺ uptake. c, Quantification of b. N = 28 biological replicates. Error bars reflect the s.e.m.; P values were calculated using ordinary one-way ANOVA. RuR, Ruthenium red. d, mCa²⁺ uptake data shown in c—segregated by sex. Error bars reflect the s.e.m.; P values were calculated using Welch’s t-test, two-tailed. e, Representative cCa²⁺ oscillations. f, Maximum cCa²⁺. N = 88 cells, three independent experiments. Whiskers represent the minimum to maximum values for each dataset. The box represents the 75th and 25th percentiles. The line is the median; P < 0.0001 according to one-way ANOVA. g, CALIMA spatiotemporal Ca²⁺ dynamics. h, Number of oscillations in individual cells. N = 88 cells, three independent experiments. Whiskers represent the minimum to maximum values for each dataset. The box represents the 75th and 25th percentiles. Line is at the median; P < 0.0001 according to Welch’s t-test, two-tailed. i, Oscillation length in individual cells. N = 88 cells, three independent experiments. Whiskers represent the minimum to maximum values for each dataset. The box represents the 75th and 25th percentiles. Line is at the median; P < 0.0001 according to Welch’s t-test, two-tailed. NS, not significant. Source data

Fig. 3. Store-operated Ca²⁺ entry responses in macrophages generated from aged mice.

a, ITPR1, ITPR2, ITPR3, ORAI1, STIM1 and STIM2 gene counts for each sample in whole-blood GTEx database sorted by age. Error bars reflect the s.e.m.; P values were calculated using ordinary one-way ANOVA. b, Representative cCa²⁺ oscillations in BMDMs-Y and BMDMs-O. Bold lines indicated the mean of individual traces. c, Quantification of ER Ca²⁺. N = 150 cells, three independent experiments. Error bars represent the s.e.m.; P values were determined by one-way ANOVA. d, Quantification of ORAI Ca²⁺. N = 150 cells, three independent experiments. Error bars represent the s.e.m.; P value determined by one-way ANOVA. e, Fold change expression at baseline for SOCE genes. N = 6 biological replicates, two independent experiments. Error bars represent the s.e.m.; P value determined by Welch’s t-test, two-tailed. Source data

Fig. 4. BMDMs-O and young Mcu^−/− macrophages show signatures of senescence.

a, SA-β-gal activity. Scale bar, 10 µm. N = 6 biological replicates. b, SA-β-gal activity. Scale bar, 10 µm. N = 8 biological replicates. In a and b, error bars reflect the s.e.m., and P values were calculated using Welch’s t-test, two-tailed. Source data

Fig. 5. Mitochondrial Ca²⁺ uptake buffers cytosolic Ca²⁺ to control inflammatory output in macrophages.

a, IL-6 and IL-1β mRNA expression from indicated BMDMs. Representative experiment, from two independent experiments. Error bars represent the s.e.m.; P < 0.0001 according to one-way ANOVA. b, Representative images from indicated BMDMs stimulated with zymosan for 30 and 60 min. Magenta shows immunostaining of NF-κB p65 subunit; cyan shows DAPI staining of nuclei. c, Nuclear to cytoplasmic ratios of the fluorescence intensity of NF-κB. N = 45 cells, three independent experiments. Bars reflect means of ratios; P values were determined by one-way ANOVA. d, Model depicting how mCa²⁺ uptake affects cCa²⁺ and inflammatory gene expression in response to zymosan. e, Effect of ionomycin on IL-1β and IL-6 mRNA expression in WT and Mcu^−/− macrophages. Representative experiment, from two independent experiments. Error bars represent the s.e.m.; P values were determined by two-way ANOVA. f, Effect of BAPTA-AM on IL-1β and IL-6 expression in WT and Mcu^−/− macrophages. Representative experiment, from two independent experiments. Error bars represent the s.e.m.; P value determined by two-way ANOVA. g, Representative images from WT and Mcu^−/− macrophages, untreated or stimulated with zymosan for 30 min and immunostained for NF-κB p65 subunit and nuclei (DAPI). h, Nuclear to cytoplasmic ratios of the fluorescence intensity of NF-κB. N = 25 cells, from three independent experiments. Whiskers represent the minimum to maximum values for each dataset. The box represents the 75th and 25th percentiles. The line is the median; P < 0.0001 according to one-way ANOVA. i, Representative analysis of fluorescence intensity of p65 staining along a line drawn across the cytoplasm and nucleus (DAPI staining), which is shaded blue. Source data

Fig. 6. Mcu^−/− macrophages display increased inflammasome activation and output.

a, IL-1β enzyme-linked immunosorbent assay (ELISA) of cell supernatants collected from WT and Mcu^−/− macrophages. Cells were stimulated with zymosan for 3 h followed by nigericin (5 µM) overnight. N = 3 biological replicates. Error bars represent the s.e.m.; P values were determined by one-way ANOVA. b, LDH levels in cell supernatants were collected from WT and Mcu^−/− macrophages. N = 6 biological replicates. Error bars represent the s.e.m.; P < 0.0001 determined by one-way ANOVA. c, IL-1β ELISA of cell supernatants collected from WT and Mcu^−/− macrophages. Cells were stimulated with LPS for 3 h followed by nigericin (5 µM) overnight. N = 2 biological replicates. Error bars represent the s.e.m.; P values were determined by one-way ANOVA. d, LDH levels in cell supernatants collected from WT and Mcu^−/− macrophages. N = 6 biological replicates. Error bars represent the s.e.m.; P < 0.0001 determined by one-way ANOVA. e, Representative images of Mcu^−/− and WT macrophages immunostained for ASC and nuclei (DAPI). Cells were stimulated with zymosan for 3 h followed by nigericin (5 µM) for 1 h. f, Quantification of ASC specks, average number of specks counted per cell, for WT and Mcu^−/− macrophages. N = 3 biological replicates. Error bars represent the s.e.m.; no significance was determined by the one-way ANOVA. g, Western blot analysis of cell lysates from WT and Mcu^−/− macrophages stimulated with zymosan for 3 h followed by nigericin (5 µM) for 1 h. Cell lysates were immunoblotted for caspase-1 (p20), GSDMD and GAPDH. h, Western blot analysis of supernatants corresponding to samples shown in g. N = 1 representative replicate, from two independent experiments. Cell supernatants were immunoblotted for caspase-1 (p20), GSDMD and GAPDH. Source data

Fig. 7. RNA-seq analysis of Mcu^−/− and BAPTA-AM-loaded BMDMs reveals transcripts sensitive to mCa²⁺ uptake.

a, Volcano plot showing increased expression of inflammatory genes in Mcu^−/− BMDMs, compared to WT BMDMs, treated with zymosan for 3 h. Data normalization, dispersion estimates and model fitting (negative binomial) were carried out with the DESeq function (DESeq2 R package). Wald statistics were used for the significance tests. b, Volcano plot showing reduced expression of inflammatory genes in BAPTA-AM loaded BMDMs, when compared to unloaded BMDMs, treated with zymosan for 3 h. Data normalization, dispersion estimates and model fitting (negative binomial) were carried out with DESeq. Wald statistics were used for the significance tests. c, GSEA pathway analysis of Mcu^−/−, BAPTA-AM loaded (WT) and unloaded WT BMDMs stimulated with zymosan for 3 h. MΦ, macrophage. d, Normalized counts for representative genes in the GSEA hallmark inflammatory response pathway. N = 3–5 biological replicates. Error bars represent the s.e.m.; P values were determined by one-way ANOVA. e, Schematic showing gene transcripts used for BART analysis. f, BART analysis of 668 mCa²⁺-sensitive genes identified in a. Transcription factor (TF) rank was plotted against the −log(P value) for each identified transcription factor. g, Volcano plot showing gene expression of the GSEA inflammatory response pathway in unstimulated Mcu^−/− macrophages, compared to their WT counterparts. Data normalization, dispersion estimates and model fitting (negative binomial) were carried out with DESeq. Wald statistics were used for the significance tests. h, Volcano plot showing expression of genes of the GSEA TNF–NF-κB pathway in unstimulated Mcu^−/− macrophages, compared to their WT counterparts. Data normalization, dispersion estimates and model fitting (negative binomial) were carried out with DESeq. Wald statistics were used for the significance tests. i, Normalized counts for representative genes in the GSEA hallmark inflammatory response pathway. N = 4 biological replicates. Error bars represent the s.e.m.; P value was determined by Welch’s t-test, two-tailed. Source data

Fig. 8. siRNA-mediated depletion of MCU in human monocyte-derived macrophages renders them hyper-sensitive to inflammatory stimuli.

a, Representative trace for a mCa²⁺ uptake in permeabilized siNT and siMCU-transfected HMDMs. Right, quantification of mCa²⁺ uptake. N = 5–8 biological replicates. Error bars represent the s.e.m.; P = 0.0012 determined by t-test. b, cCa²⁺ oscillations in siNT and siMCU-transfected HMDMs. ΔF/F₀ values for Fura-2-AM loaded macrophages were plotted. Images were taken every 3 s. c, Maximum cCa²⁺. N = 88–98 cells, three independent experiments. Whiskers represent the minimum to maximum values for each dataset. The box represents the 75th and 25th percentiles. The line is the median; P < 0.0001 according to Welch’s t-test, two-tailed. d, CALIMA maps depicting spatiotemporal aspects of cCa²⁺ elevations. e, Oscillation frequency was determined for individual cells. N = 88–98 cells, three independent experiments. Whiskers represent the minimum to maximum values for each dataset. The box represents the 75th and 25th percentiles. The line is at the median; P < 0.0001 according to Welch’s t-test, two-tailed. f, Oscillation length was determined for individual cells. N = 88–98 cells, three independent experiments. Whiskers represent the minimum to maximum values for each dataset. The box represents the 75th and 25th percentiles. The line is the median; P < 0.0001 according to Welch’s t-test, two-tailed. g, Gene expression of IL-1β, IL-6, TNF and IL-10 mRNA. N = 3 biological replicates. Error bars represent the s.e.m.; P values were determined by one-way ANOVA. Source data

Extended Data Fig. 1. GTEx analysis of human whole blood transcriptomes.

a. Variance in gene expression in whole blood of different age groups based on Principal Component analysis on GTEx samples. b. GO pathway enrichment analysis based on DSeq2 from GTEx samples. Differential gene expression is plotted for ages 60–69 vs 20–29. Significance determined by Dotplot function (clusterProfiler R package). c. Pipeline used for the analysis of genes encoding for mitochondria-localized proteins (mito-genes). d. Principal component analysis on mito-genes from GTEx samples. Variance in gene expression is shown for individual age groups. e. Variance in gene expression shown for age 20–29 vs 60–69, 30–39 vs 60–69, 40–49 vs 60–69, and 50–59 vs 60–69. f. Volcano plot of mito-genes expression levels in old (60–69y) vs young (20–29y) samples. Data normalization, dispersion estimates, and model fitting (negative binomial) were carried out with the DESeq function (DESeq2 R package). Wald statistics were used for the significance tests. g. MICU2, EMRE, and MCUB gene counts for each sample in GTEx database sorted by age. Error bars reflect SEM; p-values were calculated using one-way ANOVA. Source data

Extended Data Fig. 2. Age-associated changes in MCU expression in different human tissues.

a. Heat map for fold change gene reads of MCU across different tissues. b. MCU gene counts for each sample in GTEx database sorted by 4-point Hardy-Scale. Error bars reflect SEM; p-values were calculated using one-way ANOVA. c. MCU gene counts for each sample in GTEx database sorted by age for all death circumstance 0 on 4-point Hardy-Scale. Error bars reflect SEM; p-values were calculated using one-way ANOVA. Source data

Extended Data Fig. 3. Expression of MCU components in BMDMs.

a. Western blot analysis of MCU, TOM20, and MICU1 protein. N = 5–15 mice, error bars reflect SEM; p-value determined by Welch’s t-test, two-tailed. b. Quantitative-PCR of Mcu and its regulatory subunits. N = 3 mice. Error bars reflect SEM; p-value determined by Welch’s t-test, two-tailed. c. Resolution of MCU complex in non-reducing conditions and immunoblotting for MCU and MICU1, N = 1 mouse. d. Pulsed mitochondrial Ca²⁺ uptake. N = 15 biological replicates. Source data

Extended Data Fig. 4. Analysis of mitochondria and Ca²⁺ responses in BMDMs.

a. Mitochondrial membrane potential. N = 90 cells, 3 independent experiments. Error bars reflect SEM; p-value determined by one-way ANOVA. b. Normalized luminescent measurements of ATP. N = 6 biological repeats. Error bars reflect SEM; p-value determined by one-way ANOVA. c. Mitochondrial counts. N = 30–45 cells, 3 independent experiments. Error bars reflect SEM; p-value significance according to Welch’s t-test, two-tailed. d. Mitochondrial area. N = 30–45 cells, 3 independent experiments. Error bars reflect SEM; not statistically significant according to Welch’s t-test, two-tailed. e. Mitochondrial roundness. N = 30–45 cells, 3 independent experiments. Error bars reflect SEM; not statistically significant according to Welch’s t-test, two-tailed. f. Mitochondrial branches. N = 30–45 cells, 3 independent experiments. Error bars reflect SEM; not statistically significant according to Welch’s t-test, two-tailed. g. Representative images of BMDMs-Y and BMDMs-O immunostained for TOM20. Scale bar at 10 µm. h. Cytosolic Ca²⁺ Oscillations in BMDMs-Y (n = 88 cells) and BMDMs-O (n = 87 cells). i. Cytosolic Ca²⁺ Oscillations with ATP. j. Maximum cytosolic Ca²⁺. N = 112 cells, 2 independent experiments. Whiskers represent the min to max values for each data set. Box represents 75^th and 25^th percentile. Line is at the median; p-value according to Welch’s t-test, two-tailed. k. Number of oscillations in individual cells. N = 112 cells, 2 independent experiments. Whiskers represent the min to max values for each data set. Box represents 75^th and 25^th percentile. Line is at the median; p<value according to Welch’s t-test, two-tailed. l. Oscillation length in individual cells. N = 112 cells, 2 independent experiments. Whiskers represent the min to max values for each data set. Box represents 75^th and 25^th percentile. Line is at the median; p<0.0001 according to Welch’s t-test, two-tailed. m. Cytosolic Ca²⁺ Oscillations with OxPAPC. n. Maximum cytosolic Ca²⁺. N = 104 cells, 2 independent experiments Whiskers represent the min to max values for each data set. Box represents 75^th and 25^th percentile. Line is at the median; p-value according to Welch’s t-test, two-tailed. o. Number of oscillations in individual cells. N = 104 cells, 2 independent experiments. Whiskers represent the min to max values for each data set. Box represents 75^th and 25^th percentile. Line is at the median; p<value according to Welch’s t-test, two-tailed. p. Oscillation length in individual cells. N = 104 cells, 2 independent experiments. Whiskers represent the min to max values for each data set. Line is at the median; p<0.0001 according to Welch’s t-test, two-tailed. Source data

Extended Data Fig. 5. cCa²⁺ dynamics in Mcu−/− BMDMs-Y.

a. Cytosolic Ca²⁺ Oscillations in wt and Mcu−/− BMDMs. b. Maximum cytosolic Ca²⁺. N = 83 cells, 2 independent experiments. Error bars represent SEM; p<0.0001 according to Welch’s t-test, two-tailed. c. Maximum cytosolic Ca²⁺. N = 83 cells, 2 independent experiments. Error bars represent SEM; p<0.0001(****), p≤0.001(***), p≤0.01(**), p≤0.05(*) determined by the Brown-Forsythe and Welch ANOVA test. d. Maximum cytosolic Ca²⁺. N = 83 cells, 2 independent experiments. Error bars represent SEM of two independent experiments; p<0.0001(****), p≤0.001(***), p≤0.01(**), p≤0.05(*) determined by the Brown-Forsythe and Welch ANOVA test. e. CALIMA maps depicting spatiotemporal aspects of cytosolic Ca²⁺ elevations. f. Average number of oscillations per cell, seen during zymosan stimulation. N = 83 cells, 2 independent experiments Error bars represent SEM; p<0.0001 according to Welch’s t-test, two-tailed. g. Mean of oscillation lengths during zymosan stimulation. N = 83 cells, 2 independent experiments Error bars represent SEM; p<0.0001 according to Welch’s t-test, two-tailed. Source data

Extended Data Fig. 6. Analysis of NFkB translocation in response to C. albicans.

a. Representative images for data shown in Fig. 3g shown as single channels. b. Representative images from wt and Mcu−/− BMDMs, untreated or stimulated with C. albicans, for 30 or 60 minutes and immunostained for NFκB p65 subunit and nuclei (DAPI). The outline of cells was determined by bright field images. c. Nuclear to cytoplasmic ratios of the fluorescent intensity of NFκB for images shown in panel b. N = 30–72 cells, 2 independent experiments. Whiskers represent the min to max values for each data set. Box represents 75^th and 25^th percentile. Line is at the median; p-value according to one-way ANOVA. d. Representative analysis of fluorescent intensity of p65 staining along a line drawn across the cytoplasm and nucleus, as determined by DAPI staining (shaded blue). e. Zymosan-induced IL-1b expression (qPCR) in indicated BMDMs. N = 3 biological replicates. Error bars represent SEM, p-value calculated by one-way ANOVA. Source data

Extended Data Fig. 7. Effects of BTP2 and AZD7545 on inflammatory gene expression and analysis of macrophage activation.

a. Fold change expression of IL-1β and IL-6. N = 3 biological replicates. Error bars represent SEM; p-value determined by one-way ANOVA. b. Nuclear NFκB. N = 36–50 cells, 3 independent experiments. Error bars represent SEM; p-value determined by one-way ANOVA. c. Fold change expression of IL-1β and IL-6. N = 3 biological replicates. Error bars represent SEM; p-value determined by one-way ANOVA. d. Assessment of M1 polarization in wt and Mcu−/− BMDMs. N = 6 biological replicates. Error bars represent SEM; p-value determined by one-way ANOVA. e. Assessment of M2 polarization in wt and Mcu−/− BMDMs. N = 6 biological replicates. Error bars represent SEM; p-value determined by one-way ANOVA. Source data

Extended Data Fig. 8. Zymosan induced peritonitis in mice wherein Mcu is deleted selectively in myeloid cells (Mcu(M)−/− mice).

a. Percent weight change for wt and Mcu(M)−/− mice in a model of Zymosan Induced Peritonitis. N = 9–10 mice. b. Clinical Scores for wt and Mcu(M)−/− mice in a model of Zymosan Induced Peritonitis. N = 9–10 mice. Error bars represent SEM; p≤0.05(*) determined by the one-way ANOVA. c. ELISA determined serum cytokines in wt and Mcu(M)−/− mice, at 24 hours, in a model of Zymosan Induced Peritonitis. N = 5 mice. Error bars represent SEM; p<0.0001 according to Welch’s t-test, two-tailed. d. Peritoneal lavage cytokines at 24 hours. N = 4–5 mice. Error bars represent SEM of two independent experiments: p-values according to Welch’s t-test, two-tailed. Source data

Extended Data Fig. 9. RNA-seq analysis of Mcu−/− macrophages and analysis of IRF3 translocation.

a. GSEA hallmark gene set enrichment analysis based on DSeq2 analysis of Mcu−/− versus wt BMDMs at baseline (untreated). b. Gene set enrichment analysis of GSEA pathways that are differentially expressed in Mcu−/− versus wt BMDMs at baseline (unstimulated). Enrichment scores (ES) are plotted on y-axis and genes ranked in ordered dataset are plotted in x-axis. c. Representative images from wt and Mcu−/− macrophages, untreated or stimulated with zymosan (30 min) and immunostained for IRF3 and nuclei (DAPI). Outline of cells was determined by bright field image. d. Quantified nuclear to cytoplasmic ratios of IRF3 fluorescence intensities in wt and Mcu−/− macrophages, unstimulated and zymosan-stimulated. N = 35–50 cells, 3 independent experiments. Box and whisker plot represents the min to max values for each data set. Line is at the median; p value calculated by one-way ANOVA test (found insignificant). e. Heatmaps show comparison of gene expression changes in the TNFα signaling via NFκB pathway from human and mice. Venn-diagram indicates similar genes upregulated in Human 60–69 compared to young Mcu−/− at baseline and following zymosan stimulation. Source data

Extended Data Fig. 10. Validation of HMDMs and analysis of LPS response in HMDMs.

a. Schematic for isolation and differentiation of HMDMs from human buffy coats. b. Flow cytometry-based validation of enriched human monocytes and differentiated HMDMs. c. Upregulation of CXCL10 and CD86 in HMDMs after differentiation from monocytes. d. MCU mRNA levels in siNT and siMCU-transfected HMDMs. N = 3 biological replicates. Error bars represent SEM; p values determined by unpaired t-test. e. Fold changes in the gene expression of IL-1β, IL-6, TNFα, and IL-10 mRNA. N = 3 biological replicates. Error bars represent SEM; p-values determined by the one-way ANOVA. Source data