Ectopic lymphoid structures function as microniches for tumor progenitor cells in hepatocellular carcinoma

Abstract

Ectopic lymphoid-like structures (ELSs) are often observed in cancer, yet their function is obscure. Although ELSs signify good prognosis in certain malignancies, we found that hepatic ELSs indicated poor prognosis for hepatocellular carcinoma (HCC). We studied an HCC mouse model that displayed abundant ELSs and found that they constituted immunopathological microniches wherein malignant hepatocyte progenitor cells appeared and thrived in a complex cellular and cytokine milieu until gaining self-sufficiency. The egress of progenitor cells and tumor formation were associated with the autocrine production of cytokines previously provided by the niche. ELSs developed via cooperation between the innate immune system and adaptive immune system, an event facilitated by activation of the transcription factor NF-κB and abolished by depletion of T cells. Such aberrant immunological foci might represent new targets for cancer therapy.

Figure 1. Hepatic ELSs signify a poor prognosis in human HCC and are associated with NF-κB activation

(a) Upper panel, histological ELS score: For each human sample (n=82) the percentage of portal areas with ELS features (green) and the type of ELS was evaluated histologically (black and grey colors indicate presence and absence of histological ELS, respectively; Agg= Aggregate, Fol=Follicle, GC=Germinal Center). Gaps indicate lack of H&E-stained slides. Lower panel, ELS gene signature: Heatmap for expression of each of the 12 genes composing the ELS gene signature. Presence of high ELS gene signature is shown in the black color bar above the gene expression heatmap. Presence of high ELS gene signature was determined by coherent overexpression of the signature genes with statistical significance (prediction confidence p<0.05), as described in the Methods (black – present, grey – absent; upper horizontal bar). Cases in upper and lower panels are ordered according to ELS gene signature. (b,c) Kaplan Meier curves for survival (b) or late recurrence (c) after resection of HCC, in patients with high (red) and low (blue) ELS gene signatures in the liver parenchyma [n=82 patients (15 high score, 67 low score); *p=0.01 and 0.03 for (b) and (c), respectively, Log-rank test]. (d,e) Hazard ratios of the ELS gene signature for overall survival (d) and late recurrence (e) in multivariable Cox regression modeling adjusted for 186-gene prognostic HCC risk and American Association for Study of Liver Diseases (AASLD) prognostic stage. Bars - 95% confidence interval. (f) Heatmap for NF-κB signature enrichment in the same cohort of human patients as in (a). NF-κB signature enrichment was determined by modulation of 3 experimentally defined sets in HeLa cells, primary human fibroblasts and keratinocytes (see Methods for details). In all 3 panels, samples are ordered according to the extent of ELS signature induction from left to right (same order as in a).

Figure 2. Persistent liver IKK activation induces ectopic lymphoid structures

(a) Immunoblot analysis for Flag-tagged IKKβ(EE) in tissues of Alb-cre control and IKKβ(EE)^Hep mice. Tubulin - loading control (shown two representative mice per group). (b,c) Quantification of ELS number and size in IKKβ(EE)^Hep livers. Control Alb-cre mice do not develop follicles (n=10,8,6,5 for control, 4,7 and 14 months old IKKβ(EE)^Hep mice, respectively; *p=0.0002, **p=0.00001, two-tailed Students t-test, red line signifies mean). (d) Representative H&E and immunostained sections of IKKβ(EE)^Hep mouse and human livers from patients with chronic hepatitis showing presence of immune follicles (scale bars 50 µm, FDCs, follicular dendritic cells, HEVs, high endothelial venules). (e) Cells from microscopically isolated ELSs from IKKβ(EE)^Hep mice livers were analyzed by flow cytometry for markers indicative of the shown cell types (red line signifies mean, results are representative of ELSs isolated from at least 6 IKKβ(EE)^Hep mice). Data are representative of three independent experiments in (a) and (d) and of one experiment in (e).

Figure 3. Persistent activation of IKK in hepatocytes induces aggressive HCC

(a,b) Tumor number (≥0.5 cm) and volume in livers of 20-month-old Alb-cre control and IKKβ(EE)^Hep mice (n=13,11 for control and IKKβ(EE)^Hep, respectively; *p≤0.0002, two-tailed Students t-test, red line signifies mean). (c) Representative livers and H&E stained sections from 20-month-old Alb-cre and IKKβ(EE)^Hep mice. Arrows indicate tumors (scale bar- 200 µm). (d) Representative H&E stains of HCCs from 20-month old IKKβ(EE)^Hep mice. WD-HCC= well-differentiated HCC, CCC= cholangiocellular carcinoma (scale bar- 100 µm). (e) Heat map representation of relative mRNA expression of a 16-gene HCC proliferation and differentiation signature in wild-type (WT) liver parenchyma or HCCs derived from the indicated mice (for further details see Methods). Clusters were determined by an unsupervised algorithm and designated A, B, the latter further subdivided into B1 and B2. Note that DEN induced HCCs from WT mice are more similar to WT liver parenchyma than IKKβ(EE)^Hep, most of which fall into cluster B together with the aggressive HCCs of Myc-TP53^−/− mice. Statistical analyses of tumor types in the different clusters: DEN WD-HCCs vs. all IKK HCCs (cluster A vs. B) p=6.0E-05; DEN WD vs. IKK DEN tumors (both WD and HCC-CCC tumors) (A vs. B) p=0.001; DEN WD-HCCs vs. IKK spontaneous (spon) HCCs (both WD-HCCs and HCC-CCC tumors) (A vs. B) p=0.04; DEN WD-HCCs -IKK HCC-CCC (A vs. B) p=0.006; IKK WD-HCCs vs. IKK HCC-CCC (B1 vs. B2) p=0.007. n=4,7,8,8,3 for WT, DEN treated Alb-cre, DEN treated IKKβ(EE)^Hep, untreated IKKβ(EE)^Hep and Myc-TP53^−/− mice, respectively; All p values were determined by two tailed chi-square test. Data are representative of two independent experiments in (a) and (b) and of one experiment in (e).

Figure 4. HCC progenitors appear in ELSs and progressively egress out

(a) Representative co-immunofluoresence stains for GFP (green) expressed from the hepatocyte specific IKKβ(EE) transgene and the epithelial marker E-cadherin (red) depicting the epithelial origin of HCC progenitors. Hoechst 33342 (blue) marks the nuclei (scale bars 100 µm). (b) Representative immunostains for indicated HCC progenitor markers in ELSs of IKKβ(EE)^Hep mice (scale bars 50 µm). (c) Representative H&E stained sections of IKKβ(EE)^Hep livers depicting ELS to HCC progression (arrow points to small ELS; scale bars 50 µm). (d) Representative 3-dimensional (3D) reconstruction of an ELS from a 6 month old DEN-treated IKKβ(EE)^Hep mouse. Left upper panel: double color immunostaining for CD44v6 (brown) and B220 (red). Right upper panel: color conversion of the left panel (brown to green, red to purple). Lower panels: Two different rotations of a 3D reconstruction. Note green CD44v6⁺ progenitor cells egressing out of the ELS at multiple points (scale bars 100 µm). α, β and γ show the same region in all panels. See also Supplementary video 1. (e) Representative immunostains of two different livers (#1 and #2) from 14 month old untreated IKKβ(EE)^Hep mice and 6 month old DEN treated IKKβ(EE)^Hep mice for the pericentral marker glutamine synthetase (GS). Red and blue arrows indicate periportal and pericentral ELSs, respectively. Brown staining highlights pericentral zones (scale bars 100 µm). (f) Representative confocal microscopy images of ELS-containing liver sections from a human patient for the HCC progenitor markers HSP70 (green) and Sox9 (purple) and for the bile duct marker CK19 (red). DAPI (blue) marks the nuclei. Arrow points to a group of HCC progenitors (scale bars 100 µm, arrow points to progenitor cell). Data are representative of three independent experiments in (a) and (b), and of one experiment in (d), (e) and (f).

Figure 5. Adaptive immune cells are required for ELS-dependent HCC promotion

(a,b) Tumor numbers (≥3 mm and ≥5 mm, respectively) and volume (c) in livers of 6 month old DEN-treated Alb-cre control, Rag1^−/− , IKKβ(EE)^Hep and IKKβ(EE)^Hep -Rag1^−/− (IKK-Rag) mice (n=11,10,12,12 for control, Rag1^−/−, IKKβ(EE)^Hep and IKK-Rag, respectively; *p≤0.006, two-tailed Students t-test; red line signifies mean). (d) Representative images of livers from 6-month-old DEN-treated mice. Arrows indicate tumors. (e,f) Tumor quantification by classification to well differentiated HCC (WD-HCC) or mixed cholangio-hepatocellular carcinoma (HCC-CCC). n=11 for each group; *p≤0.00004, two-tailed Students t-test; red line signifies mean. (g) Representative immunostains for the HCC progenitor markers A6, CD44v6, CK19 and Sox9 in 6 month old DEN-treated livers. HCC progenitors in IKKβ(EE)^Hep liver are within ELSs, whereas the rare ones occasionally seen in IKKβ(EE)^Hep -Rag1^−/− mice are in the parenchyma (scale bars- 50 µm). Data are representative of one experiment, n=8.

Figure 6. Anti-Thy1.2 immuno-ablative treatment during ELS development attenuates liver tumorigenesis

(a) Representative images of immunostaining for CD3 in livers from control or anti-Thy1.2 injected 6 months old DEN-treated IKKβ(EE)^Hep mice (n=6, scale bars upper 200 µm, lower 50 µm). (b) Mice were treated with control or anti Thy1.2 antibody. Representative sections from the entire liver were assessed for the total number of ELSs and presence of ELSs of various sizes as indicated (n=6,5 for control or anti-Thy1.2, respectively; *p≤0.04, **p≤0.003, red line signifies mean) (c) Representative images of livers from control or anti-Thy1.2 injected 6-months-old DEN-treated IKKβ(EE)^Hep mice. n=6,10 for control and anti-Thy1.2, respectively; arrows indicate tumors. (d,e) Tumor number (≥3 mm) (d) and volume (e) in livers of control or anti-Thy1.2 injected 6-month-old DEN-treated IKKβ(EE)^Hep mice (n=6,10 for control and anti-Thy1.2, respectively; *p≤0.04, two-tailed Students t-test, red line signifies mean). Data are representative of one experiment.

Figure 7. ELS microniches provide a rich cytokine milieu

(a) mRNA qPCR analysis of liver parenchyma and HCCs from IKKβ(EE)^Hep or DEN-treated IKKβ(EE)^Hep mice (M=months of age), as well as in liver parenchyma of 3 month old IKKβ(EE)^Hep mice without DEN treatment. Each data point reflects the median expression, normalized to the mean expression of the same gene in control livers derived from the equivalent Alb-cre control mice (for further details see Supplementary Tables 3, 4 & 5). (b) Heat map (upper) and scatter plot (lower) representations of mRNA qPCR analyses of liver tissue from HCV-infected patients (n=43) relative to healthy controls (n=12). Scatter plots depict mRNA amounts of LTβ, CCL17 and CCL20 (for further details see Supplementary Tables 5 & 6; *p<0.0001, two-tailed Students t-test, Log₁₀ scale, cross line signifies mean). (c) Representative immunostaining for LTβ in HCV-infected human liver (scale bars: upper 200 µm; lower 50 µm). (d) Representative LTβ-mRNA in situ hybridization in mouse livers (scale bars 50 µm). (e) Quantification of LTβ expression in malignant hepatocytes. The % of LTβ positive hepatocytes was determined by counting 10 ELSs from each mouse (n=8,5,6,5 for control, 3, 6 and 9 months old mice, respectively; *p=0.0003, **p=0.00006, two-tailed Students t-test, red line signifies mean). (f) Representative serial sections showing LTβ mRNA in-situ hybridization and immunostaining for the progenitor marker A6. Note LTβ staining of immune cells and egressing hepatocytes (black arrows) but not niche residing ones (white arrows, scale bars-100 µm). (g) Representative images of LTβ-mRNA in-situ hybridization in hepatic ELSs of control or anti-Thy1.2 injected 6 month old DEN-treated IKKβ(EE)^Hep mice (scale bars-50 µm). (h) qPCR analysis of LTβ mRNA expression in liver parenchyma of control or anti-Thy1.2 injected 6 month old DEN-treated IKKβ(EE)^Hep mice (n=10,6 respectively; *p=0.003 two-tailed Students t-test, red line signifies mean). Data are representative of one experiment in (a) and (b) and of two independent experiments in (c), (d), (f) and (g).

Figure 8. Blocking LT signaling abolishes microniche egression and tumorigenesis

(a) Heat map representation of mRNA qPCR analysis of liver parenchyma from 33-weeks-old IKKβ(EE)^Hep mice treated with LTβR-Ig for 10 consecutive weeks (23–32 weeks, see Supplementary Fig. 8a). Each data point reflects the median expression, normalized to the mean expression of the same gene in equivalent control murine-IgG1-injected IKKβ(EE)^Hep mice (Log₂ scale; See Supplementary Tables 4 & 5). (b) Tumor number (≥0.5 cm) in livers of 33 week old IKKβ(EE)^Hep mice treated with either control-Ig or LTβR-Ig for the indicated periods (n=12,11,10,11 for control, 3–12w, 13–22w or 23–32w, respectively; *p=0.04, **p=0.0002, two-tailed Students t-test, red line signifies mean). (c,d) Quantification of the percent of ELSs showing egressed progenitor hepatocytes (c) and of the number of egressing hepatocyte clusters per ELS (d) [n=7,11 for control-Ig and LTβR-Ig treated mice, respectively; *p=0.02, and 0.00009 for (c) and (d), respectively; two-tailed Students t-test, red line signifies mean]. (e) Quantification of the CDC47⁺Sox9⁺ double positive cells in ELSs (see below, pink in g, right panels) (n=6; *p=0.02, two-tailed Students t-test, red line signifies mean). (f) Quantification of the GFP⁺ cells inside the ELSs (n=6; *p=0.001, two-tailed Students t-test, red line signifies mean). (g) Representative confocal microscopy images of ELS-containing liver sections from DEN-treated IKKβ(EE)^Hep mice injected for 10 consecutive weeks (23–32 weeks) with control-Ig or LTβR-Ig for GFP, CDC47 and Sox9. Hoechst 33342 marks the nuclei. Arrows indicate CDC47⁺Sox9⁺ double positive cells in pink (scale bars 100 µm). Data are representative of one experiment in (a) and (b) and of two independent experiments in (g).