BET inhibition in advanced cutaneous T cell lymphoma is synergistically potentiated by BCL2 inhibition or HDAC inhibition

Abstract

While several systemic therapies are approved for cutaneous T cell lymphoma (CTCL), a non-Hodgkin lymphoma of skin-homing T cells that may involve lymph nodes and peripheral blood in advanced stages, relapses are common. Mutational analysis of CTCL cells has revealed frequent amplification of the MYC oncogene, and bromodomain and extraterminal (BET) protein inhibitors have been shown to repress MYC expression in various malignancies. Towards a potential novel therapy, we thus sought to examine the effect of BET inhibition on CTCL cells in vitro. Each of the four tested BET inhibitors (JQ1, ABBV-075, I-BET762, CPI-0610) consistently induced dose-dependent decreases in viability of isolated patient-derived CTCL cells and established CTCL cell lines (MyLa, Sez4, HH, Hut78). This effect was synergistically potentiated by combination of BET inhibition with BCL2 inhibition (e.g. venetoclax) or histone deacetylase (HDAC) inhibition (e.g. vorinostat or romidepsin). There was also a marked increase in caspase 3/7 activation when JQ1 was combined with either vorinostat or romidepsin, confirming that the observed synergies are due in major part to induction of apoptosis. Furthermore, MYC and BCL2 expression were each synergistically repressed when CTCL cells were treated with JQ1 plus HDAC inhibitors, suggesting cooperative activities at the level of epigenetic regulation. Taken together, these data indicate that targeting BET proteins in CTCL represents a promising novel therapeutic strategy that may be substantially potentiated by combination with BCL2 or HDAC inhibition.

Keywords: BET inhibition; CTCL; HDAC inhibition; apoptosis.

Figure 1. The BET inhibitor JQ1 substantially decreases the viability of patient-derived CTCL cells and CTCL cell lines

All samples were incubated with JQ1 for 72 hours and dose-response curves were generated, from which IC₅₀ and hill slopes were calculated. (A) IC₅₀ of patient-derived samples in increasing order. The median and mean IC₅₀s were 4.29 µM and 6.05 µM, respectively. Mycosis fungoides (MF) patients are in blue and Sézary syndrome (SS) patients are in red. (B) Comparison of IC₅₀ with CTCL subtype at the time of diagnosis as either MF or SS. (C) Comparison of IC₅₀ with CTCL B stage based on ISCL classification. (D) Representative dose-response curves for patient-derived samples. (E) Dose-response curves for cell lines. (F) Comparison of IC₅₀ with MYC amplification status in patient-derived samples. (G) Comparison of IC₅₀ with MYC amplification status in cell lines. ns, p > 0.05; pt, patient; ^*p < 0.05.

Figure 2. BET inhibitors in clinical development (ABBV-075, I-BET762, CPI-0610) are variably effective in limiting CTCL cell viability

(A) Representative dose-response curves of CTCL cells derived from patient 11 to different BET inhibitors. (B) Comparison of average IC₅₀s of BET inhibitors from patient-derived samples. ABBV-075 and JQ1 were tested against eight patient-derived samples; I-BET-762 and CPI-0610 were tested against five patient-derived samples. Patient codes and individual IC₅₀s are provided in Supplementary Table 1. ^*p < 0.05; ^**p < 0.01.

Figure 3. BCL2 inhibitors or HDAC inhibitors synergistically potentiate BET inhibition against patient-derived CTCL cells

(A) The combination index (CI) at 10% viability was calculated for nine patient-derived samples (listed in Supplementary Table 2) exposed to JQ1 combined with venetoclax, vorinostat, or romidepsin, using the Chou-Talalay method. Strong synergy is defined as CI < 0.3, moderate synergy is CI < 0.7, and weak synergy is CI < 0.9 (adapted from Chou). (B) Calculated CI at 10% viability for six patient-derived samples exposed to ABBV-075 combined with venetoclax, vorinostat, or romidepsin. Synergy was note in all patient-derived samples. (C) Representative viability curves for BET inhibitors (JQ1 or ABBV-075) and their combinations with venetoclax, vorinostat, or romidepsin (patient 10).

Figure 4. Effects of BET inhibition and its potentiation by HDAC inhibition are mediated in part by induction of apoptosis by caspase 3/7

Average caspase 3/7 activity at 24 hours, shown as fold change from the control, for four patient-derived samples (patient 4, 9, 11, and 12) incubated with (A) JQ1 and vorinostat, (B) JQ1 and romidepsin, and (C) JQ1 and venetoclax. Caspase 3/7 activity over 48 hours shown for patient 9 following incubation with (D) JQ1 and vorinostat, (E) JQ1 and romidepsin and (F) JQ1 and venetoclax. ^*p < 0.05; ^**p < 0.01; ^***p < 0.001. For (D–F), +indicates p-value against JQ1 and ^*indicates p-value against vorinostat, romidepsin or venetoclax.

Figure 5. Combination of BET inhibition and HDAC inhibition markedly represses MYC and BCL2 expression in CTCL cells

Seven patient-derived samples (listed in Supplementary Table 3) were incubated with the indicated agents or vehicle control for 24 hours and changes in gene expression evaluated by qRT-PCR. Change in gene expression as represented by fold change from untreated for (A) JQ1 and vorinostat, (B) JQ1 and romidepsin, and (C) JQ1 and venetoclax. There was a striking decrease in MYC and BCL2 expression when JQ1 was combined with either vorinostat or romidepsin. ^*p < 0.05; ^**p < 0.01; ^***p < 0.001; ^****p < 0.0001.