XBP1 promotes triple-negative breast cancer by controlling the HIF1α pathway

Abstract

Cancer cells induce a set of adaptive response pathways to survive in the face of stressors due to inadequate vascularization. One such adaptive pathway is the unfolded protein (UPR) or endoplasmic reticulum (ER) stress response mediated in part by the ER-localized transmembrane sensor IRE1 (ref. 2) and its substrate XBP1 (ref. 3). Previous studies report UPR activation in various human tumours, but the role of XBP1 in cancer progression in mammary epithelial cells is largely unknown. Triple-negative breast cancer (TNBC)--a form of breast cancer in which tumour cells do not express the genes for oestrogen receptor, progesterone receptor and HER2 (also called ERBB2 or NEU)--is a highly aggressive malignancy with limited treatment options. Here we report that XBP1 is activated in TNBC and has a pivotal role in the tumorigenicity and progression of this human breast cancer subtype. In breast cancer cell line models, depletion of XBP1 inhibited tumour growth and tumour relapse and reduced the CD44(high)CD24(low) population. Hypoxia-inducing factor 1α (HIF1α) is known to be hyperactivated in TNBCs. Genome-wide mapping of the XBP1 transcriptional regulatory network revealed that XBP1 drives TNBC tumorigenicity by assembling a transcriptional complex with HIF1α that regulates the expression of HIF1α targets via the recruitment of RNA polymerase II. Analysis of independent cohorts of patients with TNBC revealed a specific XBP1 gene expression signature that was highly correlated with HIF1α and hypoxia-driven signatures and that strongly associated with poor prognosis. Our findings reveal a key function for the XBP1 branch of the UPR in TNBC and indicate that targeting this pathway may offer alternative treatment strategies for this aggressive subtype of breast cancer.

Extended Data Figure 1. Effect of XBP1 silencing on TNBC cells and UPR

a, Activation of UPR in different breast cancer cells. Immunoblot of PERK phosphorylation, IRE1α activation (phos-tag SDS-PAGE), and EIF2α phosphorylation in whole cell lysates, and ATF6α processing (pATF6α) in nuclear extract of basal-like breast cancer cells (1: HCC1937; 2: MDA-MB-231; 3: SUM159; 4: MDA-MB-157; 5: HCC70) and luminal breast cancer cells (6: ZR-75-1; 7: T47D; 8: MCF7). TM: Positive control (whole cell lysates or nuclear extracts from MDA-MB-231 cells treated with 5μg/ml tunicamycin for 6 hours). HSP90 was used as loading control for whole cell lysates, TBP was used as loading control for nuclear extract. b, Transmission electron microscopic analysis of ER in basal-like and luminal breast cancer cell lines. Black arrows indicate the endoplasmic reticulum. All images are at 30,000× magnification. Scale bar represents 1μM. c, Quantification of soft agar colony formation and number of invasive cells in untreated and control shRNA or XBP1 shRNA infected breast cancer cells. Experiments were performed in triplicate and data are shown as mean ± SD. **p<0.01. d, Quantitative RT-PCR analysis of XBP1 expression in MDA-MB-231 cells infected with lentiviruses encoding doxycycline (DOX) inducible shRNAs against XBP1 or scrambled LacZ control, in the presence or absence of doxycycline for 48h. Data are presented relative to β-actin and shown as mean ± SD of technical triplicates. e-f, Knockdown efficiency of total XBP1 (e) and XBP1s (f) in MDA-MB-231 derived xenograft tumor (as in Fig.1d). Data are presented relative to β-actin. n=5. g, Bioluminescent images of orthotopic tumors formed by luciferase expressing MDA-MB-231 cells infected with different lentiviruses. A total of 1.5×10⁶ cells were injected into the fourth mammary glands of nude mice. Bioluminescent images were obtained 1 week later and serially after mice were begun on chow containing doxycycline (Dox) (day 10). Pictures shown are the day 10 images (Before Dox) and day 45 images (After Dox). h, Effect of XBP1 knockdown on ER stress marker BIP expression in MDA-MB-231 derived xenograft tumors. Quantitative RT-PCR analysis of BIP expression in shCtrl or shXBP1 xenograft tumor. Data are presented relative to β-actin. n=5. i, Immunoblot of IRE1α activation (phos-tag SDS-PAGE) and PERK phosphorylation in whole cell lysates; ATF6α processing and ATF4 expression in nuclear extracts of two shCtrl or shXBP1 xenograft tumors. HSP90 was used as loading control for whole cell lysates, TBP was used as loading control for nuclear extract. j-k, Tumor growth of untreated or control shRNA, or XBP1 shRNA treated MDA-MB-436 (j) or HBL-100 cells (k) in nude mice. Data are shown as mean ± SD of biological replicates (n=3). **p<0.01. Tx: Treatment with shRNA. l, Kaplan-Meier tumor free survival curve of mice from Fig. 1f. m, Tumor growth (mean ± SEM) of BCM-2147 tumors as in Fig. 1f (Scr siRNA: n=7; XBP1 siRNA: n=2).

Extended Data Figure 2. Effect of XBP1 on tumor relapse and CD44^high/CD24^low cells

a, Tumor growth of MDA-MB-231 cells untreated or treated with paclitaxel (20mg/kg), or paclitaxel + control shRNA, or paclitaxel + XBP1 shRNA in nude mice. TX: treatment with paclitaxel or paclitaxel+ shRNA. Data are shown as mean ± SD of biological replicates (n=5). b, Number of mammospheres per 1,000 cells generated from day 20 xenograft tumors under different treatments as indicated under normoxic or hypoxic condition (0.1% O₂). Data are shown as mean ± SD of biological replicates (n=3). * denotes significantly different from paclitaxel+shCtrl control in each treatment, *p<0.05, **p<0.01. c, Effect of XBP1 knockdown on cell death in hypoxic regions (assessed by CA9 and cleaved caspase3 staining) or accumulation of CD44^high/CD24^low cells (assessed by CD44 staining). Immunohistochemical staining of CA9 and Cleaved Caspase 3 (consecutive sections) showed that cell death was not induced in hypoxic region in XBP1 knockdown tumors. Immunohistochemical staining of CD44 showed significant reduction of CD44 expression in XBP1 knockdown tumors. All tumor sections are from MDA-MB-231 derived xenograft with different treatment as indicated. d, Knockdown efficiency of XBP1 in MCF10A-ER-Src cells. Data are shown as mean ± SD of technical triplicates. e, Left panel: Flow cytometry analysis of CD44 and CD24 expression of TAM treated (36h) MCF10A ER-Src cells infected with control shRNA or XBP1 shRNA encoding lentivirus. Right panel: Percentage of CD44^high/CD24^low cells in TAM (4-OH-tamoxifen) treated MCF10A-ER-Src cells infected with control shRNA or XBP1 shRNA encoding lentivirus. Experiments were performed in triplicate and data are shown as mean ± SD. *p<0.05. f, Number of mammospheres per 1,000 cells generated by TAM treated MCF10A ER-Src cells uninfected, or infected with control shRNA or XBP1 shRNA encoding lentivirus. Experiments were performed in triplicate and data are shown as mean ± SD. g, Cell viability assay (Cell-titer Glo) on CD44^high/CD24^low or CD44^low/CD24^high cells isolated from TAM treated MCF10A-ER-Src cells infected with control shRNA or XBP1 shRNA encoding lentivirus (72h after infection). Data were normalized to the control (cell infected with shCtrl). Experiments were performed in triplicate and data are shown as mean ± SD. h, Cleaved caspase 3 ELISA assays on CD44^high/CD24^low or CD44^low/CD24^high cells isolated from TAM treated MCF10A-ER-Src cells infected with control shRNA or XBP1 shRNA encoding lentivirus (72h after infection). Experiments were performed in triplicate and data are shown as mean ± SD.

Extended Data Figure 3. Effect of XBP1 on CD44^high/CD24^low cells

a, UPR markers are upregulated in CD44^high/CD24^low cells. Quantitative RT-PCR analysis of UPR markers BIP, CHOP, ERDJ4, HERP and MBTPS1 in CD44^low/CD24^high cells and CD44^high/CD24^low cells sorted from two TNBC patients. Data are shown as mean ± SD of technical triplicates. *p<0.05, **p<0.01. b, XBP1s overespression in CD44^low/CD24^high cells generates mammosphere-forming ability. Number of mammospheres per 1,000 cells generated by sorted CD44^low/CD24^high cells transduced with empty vector or XBP1s expressing retrovirus. Experiments were performed in triplicate and data are shown as mean ± SD. c, CD44^low/CD24^high cells overexpressing XBP1s are more resistant to chemotherapy. MTT assay was performed to measure the dose-response curves of CD44^low/CD24^high cells or CD44^low/CD24^high cells expressing XBP1s treated with doxorubicin. Experiments were performed in triplicate and data are shown as mean ± SD. *p<0.05, **p<0.01. d, 1000 or 100 CD44^low/CD24^high cells sorted from transformed MCF10A ER-Src cells or CD44^low/CD24^high cells overexpressing XBP1s were injected into NOD/SCID/IL2Rγ-/-mice and the incidence of tumors was monitored. e, 10 CD44^low/CD24^high cells sorted from two human patients with TNBC or CD44^low/CD24^high cells overexpressing XBP1s were injected into NOD/SCID/IL2Rγ-/-mice and the incidence of tumors was monitored.

Extended Data Figure 4. HIF1α is a co-regulator of XBP1

a, Identification of XBP1 motif in MDA-MB-231 ChIP-seq dataset. Matrices predicted by the de novo motif-discovery algorithm Seqpos. p<1.08×10^-30. b, Induction of XBP1 splicing by hypoxia. RT-PCR analysis of the ratio of XBP1s to total XBP1 in MDA-MB-231 cells cultured under normoxic condition or hypoxic condition (0.1% O₂) for 24h. Data are shown as mean ± SD of technical triplicates. **p<0.01. c, Induction of XBP1 splicing by glucose deprivation. RT-PCR analysis of the ratio of XBP1s to total XBP1 in MDA-MB-231 cells cultured in normal medium or glucose free medium for 24h or 48h. Data are shown as mean ± SD of technical triplicates. *p<0.05. d, Induction of XBP1 splicing by oxidative stress. RT-PCR analysis of the ratio of XBP1s to total XBP1 in MDA-MB-231 cells untreated or treated with different dose of H₂O₂ for 1h, 4h or 24h. Data are shown as mean ± SD of technical triplicates. e, Western blotting analysis of XBP1s expression in nuclear extract of MDA-MB-231 cells cultured under normoxia or hypoxia (0.1% O₂) and glucose free condition for 16h. Lamin B was used as loading control. f, Venn diagram showing the overlap between XBP1 targets in MDA-MB-231 breast cancer cells cultured under normoxic condition (untreated) or hypoxia and glucose deprivation condition (treated). g, Motif enrichment analysis in the XBP1 binding sites in untreated or stressed (0.1% O₂ and glucose deprivation: HG) MDA-MB-231, Hs578T or T47D cells. The 1kb region surrounding the summit of the XBP1 peak is equally divided into 50 bins. The average HIF1α motif occurrence over top 1000 XBP1 peaks in each bin is plotted. The corresponding p-values of each condition are listed as follows: M231_UN: 7.78×10^-20; M231_HG: <1.08×10^-30; Hs578T_HG: <1.08×10^-30, T47D_HG: 6.14×10^-6. h, FLAG-tagged HIF1α and XBP1s were co-expressed in 293T cells, and the cells were treated in 0.1% O₂ for 16h. Co-IP was performed with M2 anti-FLAG antibody. Western blot was carried out with anti-XBP1s antibody, anti-FLAG antibody or anti-HIF1α antibody. Empty vector was used as control. i, Nuclear extracts from Hs578T cells treated with Tunicamycin (1μg/ml, 6h) in 0.1% O₂ (16h) were subjected to co-IP with anti-HIF1α antibody or rabbit IgG. Western blot was carried out with anti-XBP1s antibody or anti-HIF1α antibody. j, HA-tagged HIF2α and XBP1s were co-expressed in 293T cells, and the cells were treated in 0.1% O₂ for 16h. Co-IP was performed with anti-HA antibody. Western blot was carried out with anti-XBP1s antibody or anti-HA antibody. Empty vector was used as control. k, Localization of XBP1s and HIF1α in MDA-MB-231 cells. Western blotting analysis of XBP1s and HIF1α expression in cytosolic extracts and nuclear extracts of MDA-MB-231 cells cultured under 0.1% O₂ condition for 24h. HSP90 and TBP were used as control. l, XBP1u is not expressed in MDA-MB-231 cells. Western blotting analysis of XBP1u in MDA-MB-231 cells untreated or treated with 1μM or 10μM MG132 for 4h. HSP90 was used as loading control. m, Schematic diagram of full-length and truncated forms of XBP1s protein. n, A GST pull down assay was performed using GST-tagged XBP1s proteins and 293T cell lysates overexpressing HA-tagged HIF1α. Western blotting was performed with an anti-HA antibody. Lower panel: Coomassie blue staining of GST-tagged different truncated forms of XBP1s proteins.

Extended Data Figure 5. XBP1 and HIF1α co-occupy HIF1α targets

a, Track view of XBP1 ChIP-seq density profile (two biological replicates) on HIF1α target genes. b, XBP1 and HIF1α co-bind to DDIT4, VEGFA, and PDK1 promoters under hypoxic conditions. A ChIP assay was performed using anti-XBP1 or anti-HIF1α antibody to detect enriched fragments. GST antibody was used as mock ChIP control. c, XBP1 and HIF1α co-bind to JMJD1A and JMJD2C promoters under hypoxic conditions. Upper panel: Schematic diagram of the primer locations across the JMJD2C or JMJD1A promoter. Grey boxes indicate exon. A ChIP assay was performed using anti-XBP1 polyclonal antibody or anti-HIF1α polyclonal antibody to detect enriched fragments. Fold enrichment is the relative abundance of DNA fragments at the amplified region over a control amplified region. GST antibody was used as mock ChIP control. d, XBP1s and HIF1α co-occupy JMJD1A, DDIT4, NDRG1, PDK1 and VEGFA promoters. A ChIP-re-ChIP assay was performed using the anti-XBP1s antibody first (X). The eluants were then subjected to a second ChIP assay using an anti-HIF1α antibody (XH) or a control IgG antibody (XC). All ChIP Data (b-d) are shown as mean ± SD of technical triplicates. Results show a representative of two independent experiments. *p<0.05; **p<0.01. e, HIF1α, but not XBP1s, binds to a probe in Twist promoter in 293T cells. DNA pull down assay was used to analyze the binding of XBP1s or HIF1α on a probe in Twist promoter. The nuclear extracts of 293T cells overexpressing XBP1s or Flag-HIF1α was incubated with the wild-type probe and immunoblot analysis was performed with anti-XBP1s or anti-Flag antibody. f, XBP1s binds to Twist promoter in MDA-MB-231 cells under 0.1% O₂. The nuclear extract of MDA-MB-231 cells cultured under 0.1% O₂ for 24h was incubated with the wild-type or mutant probe (HIF1α consensus sequence was mutated) and immunoblot analysis was performed with anti-XBP1s or anti-HIF1α antibody. The lower panel shows the sequence of the probes used. g, 3xHRE reporter was co-transfected with XBP1s expression plasmid or empty vector into MDA-MB-231 cells and luciferase activity measured. Experiments were performed in triplicate and data are shown as mean ± SD. **p<0.01. h, RT-PCR analysis of XBP1 expression as in (g). Data are shown as mean ± SD of technical triplicates.

Extended Data Figure 6. XBP1 regulates HIF1α targets

a, Plot from GSEA showing enrichment of the HIF1α mediated hypoxia response pathway in XBP1-upregulated genes. b, Quantitative RT-PCR analysis of VEGFA, PDK1, GLUT1, and DDIT4 expression after knockdown of XBP1 in MDA-MB-231 under both normoxic or hypoxic conditions. c, Quantitative RT-PCR analysis of VEGFA, PDK1, GLUT1, MCT4, JMJD1A and XBP1 expression after knockdown of XBP1 in Hs578T cells treated with 0.1% O₂ for 24h. Results are presented relative to β-actin expression. Experiments were performed in triplicate and data are shown as mean ± SD. *p<0.05, **p<0.01. d, Plot from GSEA showing no enrichment of the HIF1α mediated hypoxia response pathway in XBP1-regulated genes in T47D cells (p=0.1684). e-k, Cooperative binding of XBP1 and HIF1α on common targets. e, Immunoblotting analysis of control MDA-MB-231 cell lysates and XBP1 knockdown lysates (treated with 0.1% O₂ for 24h) were performed using anti-HIF1α or anti-HSP90 antibody. f-g, Chromatin extracts from control MDA-MB-231 cells or XBP1 knockdown MDA-MB-231 cells (treated with 0.1% O₂ for 24h) were subjected to ChIP using anti-XBP1s antibody (f), or anti-RNA polymerase II antibody (g). The primers used to detect ChIP-enriched DNA were the peak pair of primers in JMJD1A, DDIT4, NDRG1, PDK1 and VEGFA promoters (Supplementary Table 3). Primers in the β-actin region were used as control. h-i, Chromatin extracts from control MDA-MB-231 cells or HIF1α knockdown MDA-MB-231 cells (treated with 0.1% O₂ for 24h) were subjected to ChIP using anti-HIF1α antibody (h), or anti-RNA polymerase II antibody (i). j-k, Chromatin extracts from control MDA-MB-231 cells or XBP1 knockdown MDA-MB-231 cells (treated with 1% O₂ for 24h) were subjected to ChIP using anti-HIF1α antibody (j), and anti-XBP1s antibody (k). All ChIP Data (f-k) are shown as mean ± SD of technical triplicates. Results show a representative of two independent experiments. *p<0.05; **p<0.01. l, Quantitative RT-PCR analysis of VEGFA, PDK1, GLUT1, and JMJD1A after knockdown of XBP1 in MDA-MB-231 cells treated with 1% O₂ for 24h. Results are presented relative to β-actin expression. Data are shown as mean ± SD of technical triplicates. *p<0.05, **p<0.01.

Extended Data Figure 7. Overexpression of constitutively activated HIF1α rescues XBP1 knockdown phenotype

a, Immunoblotting analysis of cell lysates of MDA-MB-231 cells infected with retrovirus encoding control vector or HA-HIF1α dPA was performed using anti-HA or anti-actin antibody. b, XBP1 splicing is not affected by HIF1α or HIF2α activation. RT-PCR analysis of the ratio of XBP1s to total XBP1 in MDA-MB-231 cells expressing control vector, HA-HIF1α dPA or HA-HIF2α dPA. Expression of HA-HIF1α dPA is shown in (a) and expression of HIF2α is shown in the right panel. c, XBP1 splicing is not affected by HIF1α or HIF2α depletion. RT-PCR analysis of the ratio of XBP1s to total XBP1 in MDA-MB-231 cells infected with control, shHIF1α or shHIF2α lentivirus. Knockdown efficiency of HIF1α or HIF2α is shown in the middle and right panels. d-e, Expression of constitutively activated HIF1α doesn't affect XBP1 expression (d), but restores HIF1α targets expression (e). RT-PCR analysis of XBP1 total (d), XBP1s (d) and VEGFA, PDK1, DDIT4 (e) in control shRNA (shCtrl), XBP1 shRNA (shXBP1), or XBP1 shRNA plus constitutively activated HIF1α (shXBP1+HIF1α dPA) infected MDA-MB-231 cells. Data (b-e) are shown as mean ± SD of technical triplicates. *p<0.05, **p<0.01. f, Quantification of soft agar colony formation in control shRNA (shCtrl), XBP1 shRNA (shXBP1), or XBP1 shRNA plus constitutively activated HIF1α (shXBP1+HIF1α dPA) infected MDA-MB-231, MDA-MB-468, or MDA-MB-157 cells. Experiments were performed in triplicate and data are shown as mean ± SD. **p<0.01. g, Quantification of mammosphere formation in control shRNA (shCtrl), XBP1 shRNA (shXBP1), or XBP1 shRNA plus constitutively activated HIF1α (shXBP1+HIF1α dPA) infected MDA-MB-231 cells. Experiments were performed in triplicate and data are shown as mean ± SD. **p<0.01. h, CD31 immunostaining of tumors formed by MDA-MB-231 cells infected with control shRNA (shCtrl), XBP1 shRNA (shXBP1) or XBP1 shRNA plus constitutively activated HIF1α (shXBP1+HIF1αdPA). i, Silencing of HIF1α inhibits the XBP1s-sustained mammosphere forming ability. Quantification of mammosphere formation in MCF10A cells expressing control vector, XBP1s, XBP1s plus control shRNA or XBP1s plus HIF1α shRNA. Experiments were performed in triplicate and data are shown as mean ± SD. **p<0.01.

Extended Data Figure 8. Schema depicting the interaction of XBP1 and HIF1α in TNBC

XBP1 and HIF1α cooperatively regulate HIF1α targets in TNBC. In the setting of a tumor microenvironment, hypoxia further induces XBP1 activation, active XBP1s in turn interacts with HIF1α to stimulate and augment the transactivation of HIF1 target genes that promote cancer progression.

Extended Data Figure 9. Correlation of XBP1 with HIF1α in patients with TNBC

a-b, Expression of XBP1 signature is highly correlated with two public available hypoxia-driven signatures in TNBC patients (a), but not in ER+ breast cancer patients (b). The scatter-plot of XBP1 and two publicly available HIF1α signature (Left panel: HIF1α pathway; Right panel: Hypoxia via HIF1α pathway) across different tumors were drawn for TNBC (a) and ER+ breast cancer patients (b), respectively. The corresponding Pearson's correlation coefficient (r) between XBP1 and HIF1α signature was shown. c-d, Kaplan-Meier graphs demonstrating no significant association of the expression of the XBP1 signature (red line) (c) or HIF signature (d) with relapse free survival in estrogen receptor positive breast cancer patients. The log-rank test P values are shown.

Extended Data Figure 10. Role of XBP1 in luminal breast cancer

a, XBP1 splicing is induced by hypoxia and glucose deprivation in luminal cancer cells. RT-PCR of XBP1 splicing in T47D and SKBR3 cells under different treatments for 24h. XBP1u: unspliced XBP1, XBP1s: spliced XBP1. Hypoxia: 0.1% O₂. b. Left panel: Quantification of soft agar colony formation in untreated and control shRNA or XBP1 shRNA infected breast cancer cells. Experiments were performed in triplicate and data are shown as mean ± SD. **p<0.01. Right panel: effect of XBP1 depletion on soft agar colony formation in luminal vs basal cell lines. Percentages of soft agar colonies formed from cells infected with XBP1 shRNA lentivirus relative to the same cell line infected with shCtrl lentivirus (set as 100%) are presented. 5 cell lines in each group (as in left panel) and data are shown as mean ± SD. c, Tumor growth (mean ± SD) of ZR-75-1 cells treated with control shRNA (n=4), paclitaxel (20mg/kg) + control shRNA (n=4), XBP1 shRNA (n=4) or paclitaxel + XBP1 shRNA (n=3) in nude mice. TX: treatment with shRNA or paclitaxel+ shRNA. *denotes shXBP1 treated tumors significantly different from shCtrl treated tumors. p<0.05. d, Number of mammospheres per 1,000 cells generated by control shRNA or XBP1 shRNA encoding lentivirus infected T47D or SKBR3 breast cancer cell lines cultured under normoxia or hypoxia and glucose deprivation conditions (treated). Experiments were performed in triplicate and data are shown as mean ± SD. e. Venn diagram showing the overlap between XBP1 targets in MDA-MB-231, Hs578T cells and T47D cells cultured under hypoxia and glucose deprivation conditions. f. XBP1s overexpression is not capable of converting a luminal phenotype to basal phenotype. RT-PCR analysis of luminal markers (CK8, CK18, CK19 and E-cadherin) and basal markers (CK5, CK14, p63, Fibronectin and Vimentin) expression in luminal breast cancer cells (MCF7 or T47D) infected with lentivirus encoding empty vector or XBP1s. Data are shown as mean ± SD of technical triplicates.

Figure 1. XBP1 silencing blocks TNBC cell growth and invasiveness

a-b, RT-PCR analysis of XBP1 splicing in luminal and basal-like cell lines (a) or primary tissues from 6 TNBC patients and 5 ER/PR+ patients (b). XBP1u: unspliced XBP1, XBP1s: spliced XBP1. β-actin was used as loading control. c, Representative bioluminescent images of orthotopic tumors formed by MDA-MB-231 cells as in (Extended Data 1d). Bioluminescent images were obtained 5 days after transplantation and serially after mice were begun on chow containing doxycycline (day 19) for 8 weeks. Pictures shown are the day19 image (Before Dox) and day 64 image (After Dox). d, Quantification of imaging studies as in (c). Data are shown as mean ± SD of biological replicates (n=8). *p<0.05, **p<0.01. e. H&E, Ki67, cleaved Caspase 3 or CD31 immunostaining of tumors or lungs 8 weeks after mice were fed chow containing doxycycline. Black arrows indicate metastatic nodules. f, Tumor incidence in mice transplanted with BCM-2147 tumor cells (10 weeks post-transplantation). Statistical significance was determined by Barnard's test^, .

Figure 2. XBP1 is required for tumor relapse and CD44^high/CD24^lowcells

a, Tumor growth of MDA-MB-231 cells untreated or treated with doxorubicin (Dox), or Dox + control shRNA, or Dox + XBP1 shRNA in athymic nude mice. Data are shown as mean ± SD of biological replicates (n=5). TX: treatment. b, Number of mammospheres per 1,000 cells generated from day 20 xenograft tumors under different treatments as indicated. Data are shown as mean ± SD of biological replicates (n=3). c, RT-PCR analysis of XBP1 splicing in TAM (tamoxifen) treated CD44^low/CD24^high and CD44^high/CD24^low cells. d, The indicated number of TAM-treated MCF10A-ER-Src cells infected with control shRNA or XBP1 shRNA were injected into NOD/SCID/IL2Rγ -/- mice and the tumor incidence reported at 12 weeks post-transplantation. e, RT-PCR analysis of XBP1 splicing in CD44^low/CD24^high and CD44^high/CD24^low cells purified from a TNBC patient. f, Number of mammospheres per 1,000 cells generated from untreated and control shRNA or XBP1 shRNA encoding lentivirus infected primary tissue samples from five patients with TNBC. Data are shown as mean ± SD of technical triplicates.

Figure 3. HIF1α is a co-regulator of XBP1

a, Motif enrichment analysis in the XBP1 binding sites in untreated or stressed (0.1% O₂ and glucose deprivation: HG) MDA-MB-231 or Hs578T cells. The 1kb region surrounding the summit of the XBP1 peak is equally divided into 50 bins. The average HIF1α motif occurrence over top 1000 XBP1 peaks in each bin is plotted. The corresponding p-values of each condition: M231_UN: 7.78×10^-20; M231_HG: <1.08×10^-30; Hs578T_HG: <1.08×10^-30. b, Nuclear extracts from MDA-MB-231 cells (treated with 0.1% O₂ for 10h first and then with 1μg/ml tunicamycin for another 6 hours in 0.1% O₂) were subjected to co-IP with anti-HIF1α antibody or rabbit IgG. c, Schematic of the luciferase reporter constructs. 3xHRE reporter was co-transfected with doxycycline (DOX) inducible constructs encoding control or two XBP1 shRNAs into MDA-MB-231 cells. Cells were treated in 0.1% O₂ for 24h and luciferase activity assayed. Experiments were performed in triplicate and data are shown as mean ± SD. d, Gene expression microarray heatmap showing that genes involved in the HIF1α mediated hypoxia response were differentially expressed after XBP1 knockdown. e, RT-PCR analysis of HIF1α target genes expression after knockdown of XBP1 in MDA-MB-231 derived xenograft tumors in NOD/SCID/IL2γ-/- mice. Results are presented relative to β-actin expression. n=5. f, Plot showing the genome-wide association between the strength of XBP1 binding and the occurrence of the HIF1α motif. The signal of XBP1 ChIP-seq peaks is shown as a heatmap using red (the strongest signal) and white (the weakest signal) color scheme. Each row shows ±300 bp centered on the XBP1 ChIP-seq peak summits. Rows are ranked by XBP1 occupancy. The horizontal blue lines denote the presence of the HIF1α motif. g-h, Chromatin extracts from control, XBP1 knockdown (g) or HIF1α knockdown (h) MDA-MB-231 cells (treated with 0.1% O₂ for 24h) were subjected to ChIP using anti-HIF1α (g) or anti-XBP1 antibodies (h). Data are shown as mean ± SD of technical triplicates. Results show a representative of two independent experiments. i. Growth curve of tumors formed by MDA-MB-231 cells infected with inducible control shRNA (shCtrl), XBP1 shRNA (shXBP1) or XBP1 shRNA plus constitutively activated HIF1α (shXBP1+HIF1α dPA). Mice were fed with doxycycline chow from day 7. Data are shown as mean ± SD of biological replicates (n=5). *p<0.05, **p<0.01.

Figure 4. XBP1 genetic signature is associated with human TNBC prognosis

a, Heatmap showing the expression profile of genes bound by XBP1 and differentially expressed after XBP1 knockdown. b,c, Kaplan-Meier graphs demonstrating a significant association between elevated expression of the XBP1 signature (red line) and shorter relapse free survival in two cohorts of patients with TNBC (b, and c). d, Kaplan-Meier graphs showing significant association of elevated HIF1α gene signature expression (red line) with shorter relapse free survival in a cohort of 383 TNBC patients. The log-rank test P values are shown.