Mgat5 loss sensitizes cancer cells to immune clearance. Analysis of The Cancer Genome Atlas Program (TCGA) and Genotype-Tissue Expression (GTex) project revealed significantly increased Mgat5 expression in human PDAC samples as compared with normal pancreas samples (Figure 1A). To study the function of Mgat5 in an immunocompetent setting, the KPC/Y mouse model of PDAC (KRASG12D, p53R172H, CrePdx, YFP) was utilized, which gives rise to heterogeneous tumors with varying histologies and degrees of immune infiltration (38, 39). We previously reported on a panel of clonal KPC/Y cell lines on the C57BL/6 background that recapitulate the immune heterogeneity in PDAC. When implanted into syngeneic immunocompetent hosts, T cell–inflamed tumor cell clones give rise to tumors characterized by an immunogenic TME containing CD4+ and CD8+ T cells and a paucity of granulocytic myeloid–derived suppressor cells (gMDSCs), while non–T cell–inflamed clones give rise to tumors characterized by a paucity of T cells and an abundance of gMDSCs (40).

Mgat5 loss sensitizes cancer cells to immune clearance. (A) Mgat5 expression in human pancreatic cancer (left, n = 179) and normal pancreas (right, n = 171) from GEPIA2. In the box-and-whisker plot, the lower and upper bounds of the box represent the 25th and 75th percentiles of the data, respectively, with the line within the box set at the median. Whiskers are set at the lowest and greatest values in the data set, excluding the outliers plotted beyond the whiskers. (B) Histogram of PHA-L binding to 2838c3 EV and Mgat5-KO cell lines. (C) Relative growth of T cell–inflamed (2838c3) EV and Mgat5-KO cell lines in vitro. Statistical analysis done using 2-way ANOVA with n = 3 replicates per data point. (D) Growth (mm3) of 2838c3 EV (n = 6), Mgat5-KO-A (n = 7), and Mgat5-KO-B (n = 7) subcutaneous tumors in C57BL/6 mice over time. Statistical analysis done using 2-way ANOVA for this and all following tumor growth curves. Data representative of 2 independent experiments. (E) Tumor weights in T cell–inflamed (2838c3) WT (n = 4) and Mgat5-KO-A (n = 4) cells implanted orthotopically into mouse pancreas. Data represent mean ± SEM. Statistical analysis using unpaired, 2-tailed Student’s t test. (F) Quantification of immunofluorescent staining for PHA-L, CD8+ T cells, granzyme B (GZMB), FOXP3, aSMA, and cleaved caspase 3 (CC3) by percentage area per high-power field (HPF) using ImageJ. Three mice per condition (EV, KO) with 3–5 HPF per tumor. Statistics using unpaired, 2-tailed Student’s t test. (G) Growth (mm3) and weights (mg) of 2838c3 EV (n = 8) and Mgat5-KO-A (n = 10) subcutaneous tumors in NOD/SCID mice. Data represent mean ± SEM. (H) Growth (mm3, left) of 6694c2 EV (n = 8), Mgat5-KO-A (n = 10), and Mgat5-KO-B (n = 10) subcutaneous tumors in C57BL/6 mice. Data represent mean ± SEM. (I) Subcutaneous tumor growth over time of 6419c5 EV (n = 6) and Mgat5-KO (n = 6) tumors in C57BL/6 mice. Data representative of 2 independent experiments. Data represent mean ± SEM. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001.

To examine the role of Mgat5 in PDAC tumor cell biology, we used CRISPR to inactivate Mgat5 in tumor cells from the T cell–inflamed clonal line 2838c3. Successful knockout (KO) was confirmed by flow cytometry using Phaseolus vulgaris lectin L (PHA-L), which probes for Mgat5-mediated N-glycans (Figure 1B). Mgat5-deficient lines (KO-A and KO-B) derived from the 2838c3 T cell–inflamed clone had no growth deficiency compared to empty vector (EV) controls in vitro (Figure 1C). In contrast, subcutaneous injection of 2838c3 Mgat5-KO cells into C57BL/6 hosts resulted in an initial period of growth followed by the near-complete elimination of tumors 2 weeks after injection. After 3 weeks, Mgat5-deficient tumors were significantly smaller than EV controls (Figure 1D and Supplemental Figure 1A; supplemental material available online with this article; https://doi.org/10.1172/jci.insight.178804DS1). Clearance of Mgat5-KO tumors was validated following orthotopic implantation into the pancreas (Figure 1E).

Next, we analyzed the tissues histologically to assess changes in tumor architecture. Hematoxylin & eosin (H&E) staining of T cell–inflamed EV and Mgat5-KO tumors harvested 12 days after injection (the time of maximal tumor size) revealed no obvious differences between KO and EV tumors (Supplemental Figure 1B). Immunofluorescence (IF) for PHA-L confirmed Mgat5 KO in vivo (Figure 1F and Supplemental Figure 1B), while further staining revealed significant increases in tumor-infiltrating CD8+ T cells (Figure 1F and Supplemental Figure 1B). A significant increase in non–tumor cell granzyme B content was observed, suggesting an increase in T cell and NK cell cytotoxicity against tumor cells (Figure 1F). Regulatory T cells (Tregs), as captured by FOXP3 expression, were increased in Mgat5-KO tumors (Figure 1F). Mgat5 KO in the T cell–inflamed line resulted in a nonsignificant trend toward increased α-smooth muscle actin+ (aSMA+) fibroblasts (Figure 1F). In addition, the apoptotic marker cleaved caspase-3 (CC3) was significantly increased in Mgat5-KO tumor cells, indicating increased cancer cell death (Figure 1F and Supplemental Figure 1B).

To functionally examine the role of immune pressure on the growth of Mgat5-deficient tumors, we subcutaneously implanted EV or Mgat5-KO tumor cells from a T cell–inflamed clone (2838c3) into NOD/SCID mice lacking functional T cells, B cells, and NK cells. In contrast with the growth inhibition phenotype observed in immunocompetent C57BL/6 mice, Mgat5-KO tumors were able to grow in NOD/SCID mice, albeit not to the same degree as EV control cells (Figure 1G). Mgat5-KO cells were no more sensitive than EV controls to growth in low glucose or low serum — conditions reflecting the more nutrient-deprived TME in vivo (Supplemental Figure 2, A and B). Collectively, these results suggest that immune-mediated clearance is responsible for the growth deficiency associated with Mgat5 loss, with nonimmune factors also playing a role.

Mgat5 loss increases immune clearance in immunosuppressive microenvironments. Human pancreatic tumors typically harbor immunosuppressive microenvironments that hinder the efficacy of immunotherapies such as CAR T cells and ICB (31, 32, 41, 42). Overcoming this immunologic barrier is paramount to expanding options for treatment. To determine the effects of Mgat5 loss on tumor clearance in an immunosuppressive microenvironment, we used CRISPR to KO Mgat5 in 2 non–T cell–inflamed (“cold”) clonal cell lines (6694c2 and 6419c5), which reflect the myeloid-rich TME of most PDAC tumors. Although our clonal PDAC lines exhibit different levels of Mgat5 RNA expression at baseline, all produce similar overall levels of Mgat5-derived N-glycans as assessed by PHA-L binding (Supplemental Figure 3, A and B). Following CRISPR-mediated gene editing, loss of Mgat5 was again confirmed using PHA-L staining (Supplemental Figure 3C). Similar to our observations in the T cell–inflamed line 2838c3, the growth of non–T cell–inflamed lines 6694c2 and 6419c5 lacking Mgat5 was comparable to that of EV controls in vitro (Supplemental Figure 3D, but significantly reduced in vivo (Figure 1, H and I, and Supplemental Figure 3E). Specifically, no tumors formed following implantation of the Mgat5-KO 6419c5 non–T cell–inflamed line, whereas tumors grew only half of the time following implantation of the Mgat5-KO 6694c2 non–T cell–inflamed lines (Table 1). Thus, loss of Mgat5 results in a profound inability of PDAC tumor cells to grow in vivo in the setting of both T cell–inflamed and non–T cell–inflamed tumors.

Tumor growth outcomes in PDAC cell lines

We then performed a histological analysis of non–T cell–inflamed EV and Mgat5-KO tumors 12 days after implantation. As with our T cell–inflamed tumors (Supplemental Figure 1B), H&E staining failed to show significant histological differences between Mgat5-KO and EV control tumors (Supplemental Figure 4A). IF for PHA-L confirmed loss of Mgat5 activity in KO tumors (Supplemental Figure 4, A and B). CD8+ T cells and Treg cells (FOXP3+) were increased in Mgat5-KO tumors, as was granzyme B expression (Supplemental Figure 4, A and B). Staining for aSMA revealed a significant increase in myofibroblasts, while staining for CC3 in tumor cells revealed a significant increase in apoptotic cell death (Supplemental Figure 4, A and B). These results suggest that Mgat5 loss in immunosuppressive, non–T cell–inflamed tumors is accompanied by an increase in tumor-infiltrating T cells, myofibroblasts, and tumor cell death.

Mgat5 glycans allow cancer cells to evade T cell–mediated clearance. NOD/SCID mice contain an array of immunodeficiencies that could have contributed to the rescue of Mgat5-KO tumor growth. To explore which immune populations mediate tumor rejection, we injected immunodepleting antibodies against either CD4+ and CD8+ T cells or NK cells into C57BL/6 mice bearing either T cell–inflamed EV or Mgat5-KO tumor cells (2838c3). Flow of cytometric analysis of cells from spleen (CD4+ and CD8+ T cells) or liver (NK cells) confirmed efficient depletion (Supplemental Figure 5, A–C). CD4+/CD8+ T cell depletion led to full rescue of Mgat5-KO tumor growth (Figure 2A). By contrast, NK cell depletion had no effect on the ultimate rejection of the KO tumors, although it did result in a small and reproducible enhancement of tumor growth on day 10 after injection (Supplemental Figure 5D). To further explore the role of T cells in the rejection of Mgat5-deficient tumors, we depleted CD4+ and CD8+ T cells separately and found that each depletion led to a partial rescue of Mgat5-KO tumor growth (Figure 2B). These data suggest that both CD4+ and CD8+ T cells are important for the enhanced clearance of Mgat5-deficient tumor cells.

Mgat5 glycans help cancer cells evade clearance by T cells in a cell-autonomous manner. (A) Tumor volumes (mm3) over time of 2838c3 EV (n = 5) and Mgat5-KO-A subcutaneous tumors in the setting of either NK cell depletion (n = 10), CD4+/CD8+ T cell depletion (n = 10), or isotype control (n = 5). Data represent mean ± SEM. Statistical analysis done using 2-way ANOVA for this and all further tumor growth curves. (B) Growth (mm3) of 2838c3 EV and Mgat5-KO-A subcutaneous tumors in the setting of either CD4+ T cell depletion, CD8+ T cell depletion, or isotype control (n = 5 mice/group). Statistical analysis done on day 19. (C) Growth (mm3, left) and weights (right) of 2838c3 EV (n = 5) and Mgat5-KO-A (n = 6) subcutaneous tumors in Batf3–/– mice. Statistical analysis done using unpaired, 2-tailed Student t test for tumor weights. Data representative of 2 independent experiments. (D) Flow cytometric analysis of the indicated immune cell subsets in 2838c3 EV (n = 6) and Mgat5-KO-A tumors (n = 8) harvested on day 12 after subcutaneous injection. Data represent mean ± SEM. Statistical analysis using unpaired, 2-tailed Student’s t test. Data representative of 2 independent experiments. (E) Flow cytometric analysis of T cell cytotoxicity in draining lymph nodes (inguinal, axillary) from 2838c3 EV and Mgat5-KO subcutaneous flank tumor. Data represent mean ± SEM. Statistical analysis using unpaired, 2-tailed Student’s t test. Data representative of 2 independent experiments. (F) Growth (mm3) tumors following the injection of 2838c3 WT cells (n = 6), Mgat5-KO-A cells (n = 4), or a 1:1 mix of WT and KO cells (n = 7). (G) PHA-L staining by flow cytometry of the WT and 1:1 mixed WT + KO tumors. Statistical analysis done using unpaired, 2-tailed Student’s t test. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001.

Next, we asked whether dendritic cells (DCs) or B cells contribute to the Mgat5-KO growth phenotype. To this end, we subcutaneously implanted Mgat5-KO and control wild-type (WT) tumor cells into Batf3–/– hosts, which lack conventional type 1 DCs (cDC1s) that are specialized for CD8+ T cell activation and cross-presentation (43). Tumor implantation into Batf3–/– mice rescued the Mgat5-KO growth deficiency that was most pronounced at early time points (Figure 2C). By contrast, muMT– host mice lacking B cells fully cleared Mgat5-KO tumors (Supplemental Figure 5E). Taken together, these results suggest that CD4+ and CD8+ T cells, and cDC1s, play a dominant role in the clearance of Mgat5-deficient tumors.

Mgat5 deficiency confers a tumor cell–autonomous sensitivity to immune pressure. To gain further insights into immune changes within the TME, we performed immune profiling of T cell–inflamed (2838c3) EV and Mgat5-KO tumors (Supplemental Figure 6A). Given that our standard injection approach resulted in Mgat5-KO tumors that were too small for immune profiling (even at the point of maximal size; 12 days), 10-fold more tumor cells (2 × 106) were injected into C57BL/6 mice to obtain tumors that would be adequate for flow cytometry. Mgat5-deficient tumors exhibited a significant increase in total T cells (CD3+), CD8+ T cells, and NK cells; the activation marker CD44 and exhaustion marker PD-1 were both significantly upregulated on CD8+ T cells (Figure 2D). In addition, Mgat5-deficient tumors exhibited a significant decrease in myeloid cells (CD45+CD11b+), macrophages (CD11b+F4/80+), and gMDSCs (Ly-6G+Ly-6C+). Similar changes were observed in Mgat5-KO tumors derived from a non–T cell–inflamed line (6694c2) (Supplemental Figure 7A).

To further deconstruct the immune response to Mgat5-KO tumors, draining lymph nodes (inguinal, axillary) from subcutaneous flank tumors were isolated 12 days after tumor cell injection. This allows for dissection of the T cell response at a more granular level than is possible in primary tumors, given limited tumor-infiltrating lymphocytes. Markers of T cell cytotoxicity, including TNF-α, IFN-γ, and granzyme B were significantly upregulated in both CD8+ T cells (Figure 2E) and CD4+ T cells (Supplemental Figure 7B) within the draining lymph node, along with significant increases in T cell (Ki67+) and degranulation (CD107a/LAMP-1). These results indicate that the T cells that infiltrate Mgat5-KO tumors are activated and functional in the immune response.

We next determined whether the eradication of Mgat5-KO tumors can be attributed to the changes in the TME or cell-autonomous effects induced by Mgat5 deficiency. We reasoned that if changes in the TME brought about by Mgat5 deficiency underlie the phenotype, then such changes in immune infiltration should also result in the eradication of cells with intact Mgat5. To this end, we mixed WT and Mgat5-KO cells at a 1:1 ratio and subcutaneously injected them into C57BL/6 mice. The resulting tumors from the mixed injection grew at a comparable rate as the WT controls (Figure 2F). However, most surviving tumor cells were PHA-L+ (Figure 2G), indicative of an immune response that cleared the Mgat5-KO cells and spared the Mgat5-WT cells. These results suggest that the immune-mediated elimination of Mgat5-deficient cells is cell autonomous and that the observed changes in immune infiltration are a consequence rather than a cause of the tumor rejection mechanism.

Loss of Mgat5 increases the immunogenicity of existing tumor antigens. We considered several possible mechanisms by which loss of Mgat5 could lead to improved T cell recognition and killing. These included (i) the creation of neoantigens, potentially via the addition of new sugar moieties to (normally) unmodified mannose moieties; (ii) uncloaking of existing antigens whose processing and presentation are blocked via steric hindrance in Mgat5-WT cells; and (iii) changes in tumor cell glycosylation resulting an enhanced ability of T cells to recognize and/or kill target cells.

To address the possibility that the immune system was responding to neoantigens emerging in Mgat5-KO cells (possibilities i and ii), we examined T cell repertoires for evidence of T cell subclones specific for Mgat5-KO tumors. To this end, we isolated splenocytes from naive C57BL/6 mice or mice injected with Mgat5-WT or Mgat5-KO tumor cells for T cell receptor Vβ repertoire analysis of both CD4+ and CD8+ T cells. A review of the T cell repertoires revealed an enrichment of several Vβ receptors in tumor-bearing mice compared with naive C57BL/6 controls, notably Vβ2, Vβ3, Vβ7, and Vβ8.1 (Figure 3A). Notably, these same Vβ receptor subtypes were enriched in both CD4+ and CD8+ T cells, suggesting a polyclonal T cell response to tumor-associated antigens in Mgat5-WT tumors.

Mgat5 loss increases the immunogenicity of existing tumor antigens. (A) Vβ repertoire analysis of CD4+ and CD8+ T cells in the spleens of naive mice (n = 5, combined from 2 independent experiments), mice bearing 2838c3 WT tumors (n = 3), or mice that had cleared Mgat5-KO-A tumors (n = 5). Data represent mean ± SEM. Statistical analysis by 2-way ANOVA for this and all further tumor growth curves. (B) Growth (mm3) of subcutaneous tumors arising from 2838c3 WT cells injected into either naive mice or mice previously immunized (4 weeks earlier) with 2838c3 Mgat5-KO-A cells (n = 6 mice/group). Data represent mean ± SEM. (C) Growth (mm3, left) and weights (right) of 6694c2 WT cells subcutaneous injected into either naive mice or mice previously immunized (4 weeks earlier) with 2838c3 Mgat5-KO-A cells (n = 6 mice/group). Data represent mean ± SEM. Statistical analysis by unpaired, 2-tailed Student t test for tumor weights. (D) Growth (mm3) of 2838c3 WT cells subcutaneously injected into naive mice, mice previously immunized with irradiated, dead 2838c3 EV cells (dEV immunization), or mice previously immunized with dead 2838c3 KO-A cells (dKO immunization) (n = 7 mice/group). Data represent mean ± SEM. (E) Vβ repertoire analysis of CD4+ and CD8+ T cells in the spleens of naive mice (n = 5, from A), immunized mice challenged with 2838c3 WT tumor cells day 3 after subcutaneous injection (n = 3), or immunized mice challenged with 2838c3 WT tumor cells on day 10 after subcutaneous injection (n = 3). Data represent mean ± SEM. Statistical analysis by 2-way ANOVA. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001.

Next, we examined mice bearing Mgat5-KO tumors to determine whether there was an expansion of T cells expressing Vβ alleles that differed from naive and WT tumor–bearing mice, which might reflect a T cell response to antigens present exclusively in Mgat5-KO cells. Our analysis failed to reveal changes in the Vβ repertoire fitting this pattern. Instead, the T cell subsets enriched in response to Mgat5-KO tumors were the same as those that had expanded in response to Mgat5-WT tumors (Figure 3A). These results suggest that Mgat5-deficient cancer cells do not provoke a T cell response against a new set of antigens, but rather increase the strength of the response to preexisting antigens present in Mgat5-WT cells.

Given these findings, we hypothesized that Mgat5 deficiency results in improved immunogenicity, possibly by enhancing T cell–target cell interactions. To test this hypothesis, we performed tumor immunization studies to determine whether live cell interactions are required for the immune response to Mgat5-KO cells. First, C57BL/6 mice were subcutaneously injected with 2838c3 Mgat5-KO cells, and tumors were allowed to fully clear over 4 weeks. These “cured” mice were then challenged with WT cells, using naive mice injected with Mgat5-WT cells as a control. Mice previously injected (immunized) with Mgat5-KO cells were able to fully clear parental T cell–inflamed Mgat5-WT cells (Figure 3B) and to control the growth of an unrelated non–T cell–inflamed Mgat5-WT line (6694c2) (Figure 3C), indicating that the strong immune response to the Mgat5-deficient cells generated memory against antigens present across the PDAC clonal lines, as previously described (40). We then used 2 methods (sonication and ionizing radiation) to kill EV and Mgat5-KO cells. Mice were then immunized with the dead cells and then challenged with WT cells using identical methodology as described above. In contrast with the protective effects conferred by live Mgat5-KO cells, mice immunized with dead EV or Mgat5-KO cells were susceptible to tumor rechallenge, with Mgat5-WT cells able to grow at the same rate as they did in a naive host (Figure 3D and Supplemental Figure 8A). These findings indicate that a live tumor cell–T cell interaction is necessary for the strong immune reaction against Mgat5-KO cells; likewise, these data fail to provide evidence that a strong tumor antigen is created upon Mgat5 loss.

Returning to Vβ repertoire analysis, we immunized mice with 2838c3 Mgat5-KO cells as above and then challenged them with 2838c3 WT cells. As noted in Figure 3B, clearance of the WT tumors in immunized mice occurs prior to the initiation of tumor measurements at 7 days after injection. We therefore evaluated the CD4+ and CD8+ T cell receptor repertoire at 3 and 10 days after injection. Notably, the same receptor subtypes (Vβ2, Vβ7, and Vβ8.1) that were expanded upon clearance of Mgat5-KO tumors (Figure 3A) were also found to be expanded on day 3 after challenge with Mgat5-WT tumor cells, along with Vβ3 and Vβ5 (Figure 3E). These expansions returned to the naive baseline by day 10, suggesting that these T cell subsets are responsible for responding to and clearing the tumors. These results lend further support to the notion that Mgat5 loss does not lead to the creation of a strong tumor antigen that evokes a T cell response; rather, an enhancement of the immunogenicity of existing tumor antigens appears to allow for a polyclonal T cell response and robust immune memory.

Mgat5 deficiency results in enhanced sensitivity to TNF-α– and TRAIL-mediated cell death. T cells kill their targets through multiple mechanisms, including perforin, granzyme B, and induction of the extrinsic cell death pathway induced by several members of the TNF superfamily: TNF-α, TRAIL, and Fas ligand (FasL) (44–46). As noted previously, Mgat5-KO tumors exhibited a notable increase in the apoptosis marker CC3 compared with EV tumors. We therefore hypothesized that heightened sensitivity to apoptosis underlies the immune-mediated clearance of tumor cells. To test this possibility, we cultured T cell–inflamed Mgat5-KO or EV tumor cells with increasing concentrations of TNF-α, TRAIL, or FasL, and measured cell death. Cell viability staining revealed a significant increase in the death of T cell–inflamed Mgat5-KO cells (2838c3) compared with EV controls at low concentrations of TNF-α, whereas neither TRAIL nor FasL stimulation had this effect (Figure 4A). This increased cell death in KO cells upon stimulation with TNF-α was verified using Annexin V/PI staining (Supplemental Figure 9A). The non–T cell–inflamed line 6694c2 exhibited a similar increase in TNF-α sensitivity (Figure 4B), but no consistent increase in sensitivity to TRAIL or FasL (Supplemental Figure 9B).

Mgat5 glycans impede cell killing via extrinsic cell death pathways. (A) Viability of 2838c3 EV and Mgat5-KO cells in vitro following exposure to varying concentrations of TNF-α, TRAIL, or Fas ligand (FasL). Statistics from 2 μg/mL TNF-α, 16 ng/mL TRAIL, and 0.4 μg/mL FasL. Analysis using 2-way ANOVA for this and all further cell death figures at specified concentrations. (B) Viability of 6694c2 EV and Mgat5-KO cells in vitro following exposure to varying concentrations of TNF-α. Statistics from 400 ng/mL TNF-α. (C) Viability of 6499c4 EV and Mgat5-KO cells in vitro following exposure to varying concentrations of TNF-α or TRAIL. Statistics from 2 μg/mL TNF-α and 80 ng/mL TRAIL. (D) Viability of 6419c5 EV and Mgat5-KO cells in vitro following exposure to varying concentrations of TNF-α or TRAIL. Statistics from 2 μg/mL TNF-α and 500 ng/mL TRAIL. All previous data representative of at least 2 independent experiments. (E) Viability of 2838c3 EV and Mgat5-KO-A cells in vitro following exposure to varying concentrations of TNF-α with or without the pan-caspase inhibitor z-VAD (left) or the necroptosis inhibitor necrostatin-1 (right). Statistics from 16 ng/mL TNF-α. (F) Viability of 6499c4 EV and Mgat5-KO-A cells in vitro following exposure to varying concentrations of TRAIL with or without the pan-caspase inhibitor z-VAD (left) or the necroptosis inhibitor necrostatin-1 (right). Statistics from 10 ng/mL TRAIL. *P < 0.05; ****P < 0.0001.

We then expanded our analysis by evaluating the existing 6419c5 (non–T cell–inflamed) EV and Mgat5-KO lines and knocking out Mgat5 in an additional T cell–inflamed line (6499c4) to assess sensitivity to TNF-related ligands (Supplemental Figure 9C). As with all other lines tested, 6499c4 Mgat5-KO cells had similar growth in vitro compared to EV controls (Supplemental Figure 9D). Surprisingly, the 6419c5 and 6499c4 lines were resistant to TNF-α–induced cell death (both EV and Mgat5-KO), but were instead sensitive to TRAIL-induced cell death, with Mgat5-deficient cells exhibiting greater sensitivity to these agents (Figure 4, C and D). Consistent with earlier observations, both lines were insensitive to FasL-induced cell death regardless of Mgat5 status (Supplemental Figure 9, E and F). These results suggest that pancreatic tumor lines lacking Mgat5 are more sensitive to the death-inducing activity of ligands belonging to the TNF superfamily, with some Mgat5-KO lines exhibiting enhanced sensitivity to TNF-α and others exhibiting enhanced sensitivity to TRAIL. This dichotomy may reflect the underlying sensitivities of the parental cell lines, as the 2838c3 and 6694c2 lines exhibited approximately 25%–50% cell death at the highest TNF-α concentrations, whereas the 6419c5 and 6499c4 lines were insensitive to TNF-α.

Mgat5 loss increases susceptibility to both apoptosis and necroptosis. TNF-α can have dichotomous effects on tumor growth and survival via canonical signaling through its 2 receptors, TNFR1 and TNFR2. Specifically, while TNFR1 signaling typically promotes cell death, stimulation of TNFR2 typically promotes cell survival and proliferation through the NF-κB signaling pathway (47, 48). To confirm that the enhanced sensitivity of TNF-α was mediated by TNFR1 signaling, we used CRISPR to KO TNFR1 in 2838c3 Mgat5-KO cells; as expected, double-KO cells were completely resistant to the death-inducing effects of TNF-α (Supplemental Figure 10A).

TNFR1-induced killing can occur through either apoptosis or necroptosis (49, 50). To distinguish between these possibilities, we treated 2838c3 Mgat5-KO or EV control cells with TNF-α and either the pan-caspase (apoptosis) inhibitor Z-VAD-FMK (z-VAD) (51) or the RIPK1 (necroptosis) inhibitor necrostatin-1 (52, 53). Inhibitors were validated using Western blotting to confirm knockdown of CC3 and cleaved caspase-8 (z-VAD) or phosphorylated RIPK1 (necrostatin-1) (Supplemental Figure 10, B and C). Whereas z-VAD marginally reversed the enhanced sensitivity to TNF-α caused by Mgat5 deficiency, necrostatin-1 resulted in a near-complete rescue of the cell death phenotype (Figure 4E). The sensitivity to TNF-α of another Mgat5-KO line, 6694c2, was also reversed by necrostatin-1 (Supplemental Figure 10D).

Stimulation of the TRAIL receptor in cancer cells can also lead to cell death through either the apoptotic or necroptotic pathway (54, 55). We thus repeated the inhibitor experiments with the cell lines that were resistant to TNF-α but sensitive to TRAIL — 6499c4 and 6419c5. In these lines, necrostatin-1 had no effect; instead, the pan-caspase inhibitor z-VAD was able to fully reverse the increased sensitivity of Mgat5-KO cells to TRAIL-induced cell death (Figure 4F and Supplemental Figure 10E). These findings suggest that loss of Mgat5 renders pancreatic tumor cells more susceptible to TNF-α and TRAIL by lowering the threshold for cells to undergo apoptotic and/or necroptotic cell death.

Mgat5 glycans affect sensitivity to TNF-α–mediated cell death in lung and colorectal cancer cells. To determine whether the increased sensitivity of Mgat5-deficient cells to TNF-α– or TRAIL-induced cell death is specific for PDAC or generalizable to other tumor types, we evaluated the effects of Mgat5 KO in 4 non-PDAC cell lines: Lewis lung carcinoma (LLC) cells, MC38 colorectal cancer cells, B16-F10 melanoma cells, and Hep55 HCC cells. We used CRISPR to edit Mgat5 in these cell lines and then used flow cytometry and cell sorting to isolate highly enriched populations of PHA-L– (Mgat5-KO) cells.

Two of the 4 lines tested revealed increased sensitivity to TNF-α–mediated cell death, as observed in our PDAC lines. Similar to our PDAC cell lines, loss of Mgat5 in LLC cells had no effect on in vitro growth at baseline, but significantly increased sensitivity to TNF-α–mediated cell death, with no effect on TRAIL- or FasL-induced cell death. Subcutaneous injection in vivo, however, revealed no tumor growth deficiencies in the Mgat5-KO line (Figure 5A and Supplemental Figure 11A). Loss of Mgat5 in the colorectal cancer line MC38 resulted in a mild growth deficiency in vitro, increased sensitivity to TNF-α–induced cell death, but no effect on tumor growth in vivo (Figure 5B and Supplemental Figure 11B). The increased sensitivity found in the LLC and colorectal cancer lines confirms that the function of Mgat5 in limiting the response of cells to TNF-α is not restricted to PDAC.

Mgat5 glycans protect some non–pancreatic cancer cells against TNF-α–mediated cell death. (A) Histogram of PHA-L binding, in vitro growth, in vitro cell death assays using TNF-α, and subcutaneous tumor growth of Hep55 EV and Mgat5-KO cells in C57BL/6 mice. For in vitro growth assays, statistical analysis done using 2-way ANOVA with n = 3 replicates per data point for this and all further in vitro growth assays. In vivo growth representative of 2 independent experiments. Analysis for TNF-α death assay done using 2-way ANOVA at 400 ng/mL for this and all further TNF-α death assays at the specified concentration, and representative of 2 independent experiments. Analysis for tumor growth using 2-way ANOVA for this and all further tumor growth curves. Data represent mean ± SEM. (B) Histogram of PHA-L binding, in vitro growth, in vitro cell death assays using TNF-α, and subcutaneous tumor growth of LLC EV and Mgat5-KO cells in C57BL/6 mice. Statistics for TNF-α death assay done at 3.2 ng/mL. (C) Histogram of PHA-L binding, in vitro growth, in vitro cell death assays using TNF-α, and subcutaneous tumor growth of MC38 EV and Mgat5-KO cells in C57BL/6 mice. For in vitro growth assay, n = 6 replicates per data point. Statistics for TNF-α death assay done at 3.2 ng/mL. (D) Histogram of PHA-L binding, in vitro growth, in vitro cell death assays using TNF-α, and subcutaneous tumor growth of B16-F10 EV and Mgat5-KO cells in C57BL/6 mice. Statistics for TNF-α death assay done at 80 ng/mL. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001.

We next turned our attention to the HCC line Hep55. Mgat5 expression has prognostic significance in HCC (16), and Mgat5 influences multiple aspects of tumor biology (20, 23, 24, 56, 57). We found that Mgat5 loss in Hep55 cells resulted in a significant growth defect in vitro without any increased sensitivity to the 3 extrinsic cell death ligands. Likewise, Mgat5-deficient Hep55 cells exhibited spontaneous tumor regressions in vivo, following the pattern of initial growth followed by rapid rejection, as seen in the PDAC lines (Figure 5C and Supplemental Figure 11C).

Finally, B16 cells lacking Mgat5 exhibited ligand sensitivity and growth profiles (in vitro and in vivo) that were similar to EV controls (Figure 5D and Supplemental Figure 11D). These results emphasize the heterogeneity of glycosylation in different cell lines and tumor types, with the function of Mgat5 in controlling sensitivity to TNF-α conserved in some non-PDAC cancers and its ability to promote tumor regression present in others.

Loss of Mgat5 sensitizes tumors to immunotherapy. Given the finding that Mgat5-KO tumors were more susceptible to T cell–mediated antitumor activity, we hypothesized that Mgat5 loss might sensitize tumors to T cell–directed immunotherapy. The increased number of PD-1+CD8+ T cells shown to be present in non–T cell–inflamed Mgat5-KO tumors as seen in Supplemental Figure 7B further suggests this may be an effective therapy, although no difference in PD-L1 expression on EV and Mgat5-KO tumor cells after stimulation with IFN-γ was observed in vitro (Supplemental Figure 12A). To test this, we used a non–T cell–inflamed line (6694c2), which is poorly responsive to combination ICB (40). We injected C57BL/6 mice with either 6694c2 EV or Mgat5-KO cells and treated tumor-bearing animals with a combination of PD-1– and CTLA4-blocking antibodies when tumors reached 50–100 mm3 in volume (Figure 6A). Because tumors arise in only approximately 50% of mice injected with Mgat5-KO 6694c2 cells (Table 1), only those animals that developed tumors (i.e., those with the weakest Mgat5-KO phenotype) were used in the experiment. Despite this handicap, the addition of ICB treatment led to a significant decrease in tumor growth (Figure 6B) and improved survival (Figure 6C) of mice bearing Mgat5-KO tumors.

Mgat5 loss augments the antitumor effects immune checkpoint blockade (ICB). (A) Schematic illustrating the ICB experimental design. (B) Growth of 6694c2 EV under isotype control (n = 9), EV treated with ICB (n = 8), Mgat5-KO under isotype control (n = 8), and Mgat5-KO treated with ICB (n = 9). Spaghetti plots showing the growth of individual tumors are presented on the right. Data represent mean ± SEM. Statistical analysis by 2-way ANOVA at day 9. Not shown is significance (****) of EV + isotype ctrl and KO + ICB groups. EV + isotype ctrl and EV + ICB groups are not significantly different (P = 0.4095). (C) Survival of mice from the experiment in B. Statistical analysis by log-rank (Mantel-Cox) test. (D) Microscopic evaluation of immunofluorescent PHA-L binding in 2838c3 WT tumors treated with 1 or 2 weeks of 0 mg/kg, 1 mg/kg, or 4 mg/kg swainsonine. Quantification of immunofluorescent staining for PHA-L using ImageJ. Two mice per condition per week (EV, KO) with with 3–5 HPF per tumor. Statistical analysis done using unpaired, 2-tailed Student’s t test. (E) Growth of 2838c3 WT subcutaneous tumors in mice treated with 0 mg/kg (n = 5), 1 mg/kg (n = 4), or 4 mg/kg (n = 5) of swainsonine administered once daily i.p. for 7 days. Mice with tumors sized 20–60mm3 were enrolled in treatment. Data represent mean ± SEM. Statistical analysis by 2-way ANOVA at day 14. *P < 0.05; **P < 0.01; ****P < 0.0001.

Given the immune effects of genetic loss of Mgat5, we reasoned that pharmacological inhibition of Mgat5 might also have an antitumor effect in vivo. Swainsonine is an inhibitor of Golgi α-mannosidase II, which lies upstream of Mgat5 (58) and can efficiently inhibit the formation of PHA-L+ N-glycans in our system without inflicting cell death in vitro (Supplemental Figure 12, B and C). Although swainsonine showed initial promise as an anticancer agent, a phase II clinical trial failed to show efficacy in renal cell carcinoma (59–62). To determine whether pancreatic cancer is sensitive to pharmacological inhibition of Mgat5, we treated mice bearing T cell–inflamed 2838c3 WT tumors with either swainsonine (1 mg/kg or 4 mg/kg) or vehicle control for 2 weeks. IF of tumors taken after 1 week and 2 weeks of swainsonine treatment verified an effective reduction in PHA-L binding (Figure 6D). Both the 1 mg/kg and 4 mg/kg swainsonine dosages prompted a significant decrease in tumor growth compared with vehicle control–treated tumors (Figure 6E), indicating that pharmacologic inhibition of N-glycosylation can phenocopy disruption of the Mgat5 gene.