Paradoxical resistance of multiple myeloma to proteasome inhibitors by decreased levels of 19S proteasomal subunits

Abstract

Hallmarks of cancer, including rapid growth and aneuploidy, can result in non-oncogene addiction to the proteostasis network that can be exploited clinically. The defining example is the exquisite sensitivity of multiple myeloma (MM) to 20S proteasome inhibitors, such as carfilzomib. However, MM patients invariably acquire resistance to these drugs. Using a next-generation shRNA platform, we found that proteostasis factors, including chaperones and stress-response regulators, controlled the response to carfilzomib. Paradoxically, 19S proteasome regulator knockdown induced resistance to carfilzomib in MM and non-MM cells. 19S subunit knockdown did not affect the activity of the 20S subunits targeted by carfilzomib nor their inhibition by the drug, suggesting an alternative mechanism, such as the selective accumulation of protective factors. In MM patients, lower 19S levels predicted a diminished response to carfilzomib-based therapies. Together, our findings suggest that an understanding of network rewiring can inform development of new combination therapies to overcome drug resistance.

Trial registration: ClinicalTrials.gov NCT01402284.

Keywords: cancer; carfilzomib; cell biology; human; myeloma; proteasome; proteostasis.

Figure 1.. Screen for genes controlling the sensitivity of multiple myeloma cells to carfilzomib.

(A) Screening strategy. (B) Gene Ontology (GO) categories enriched among the top 50 genes whose depletion results in sensitization carfilzomib and the top 50 genes whose depletion results in desensitization carfilzomib. DOI: http://dx.doi.org/10.7554/eLife.08153.003

Figure 2.. Nodes within the proteostasis network control the response of myeloma cells to carfilzomib.

(A) Volcano plot showing knockdown effects (sensitization or desensitization to carfilzomib) and statistical significance of human genes (orange dots) and quasi-genes generated from negative control shRNAs (grey dots). Drug resistance / sensitization phenotypes were previously defined as ρ (Kampmann et al., 2013); a value of −1 corresponds to a twofold sensitization to the drug. Hit genes belonging to functional categories of interest are color-coded as labeled in the panels. (B) Volcano plot as in A, except showing effect on growth. Growth phenotypes were previously defined as γ (Kampmann et al., 2013); a value of −1 corresponds to a twofold reduction in growth rate. (C) Volcano plot as in A, highlighting the opposing effects of 20S or 19S proteasome knockdown on the sensitivity of cells towards carfilzomib. Note the protective effect is not restricted to the 19S regulator alone, but is shared with the 11S regulator. (D) Volcano plot as in C, except showing effect on growth. DOI: http://dx.doi.org/10.7554/eLife.08153.004

Figure 2—figure supplement 1.. Comparison of growth phenotypes and carfilzomib resistance phenotypes for each targeted gene.

Hit genes belonging to functional categories of interest are color-coded. DOI: http://dx.doi.org/10.7554/eLife.08153.005

Figure 3.. Rapamycin desensitizes cells to carfilzomib.

Dose-response curves of multiple myeloma (MM) cells (A, B) and a leukemia cell line (C) exposed to carfilzomib after a 24 hr pretreatment with 200 nM rapamycin. FC: fold change of EC50. Data points are means of two experimental replicates, error bars denote SD. DOI: http://dx.doi.org/10.7554/eLife.08153.006

Figure 3—figure supplement 1.. Induction of autophagy desensitizes cells to carfilzomib.

(A–C) Dose-response curves of MM cells (A, B) and a leukemia cell line (C) exposed to carfilzomib after a 24 hr pretreatment with 100 mM trehalose. FC: fold change of EC50. Data points are means of four experimental replicates, error bars denote SD. (D) The percent viable cells (compared to untreated) at the calculated EC50 for carfilzomib are interpolated from the dose response curves in (A–C) and Figure 3. p values are derived from a one-tailed Student's t-test for unpaired samples. (E) Measurement of autophagy induction in U-266 cells transduced with a mCherry-EGFP-LC3B autophagic flux reporter and treated with 200 nM rapamycin or 100 mM trehalose for 24 hr. Reduction in GFP signal indicates an increase in autophagic flux. Chloroquine (75 μM, 24hr, co-incubation) was added as a control to show inhibition of autophagic flux. DOI: http://dx.doi.org/10.7554/eLife.08153.007

Figure 4.. Opposing effects of 19S and 20S proteasomal subunit knockdown on carfilzomib sensitivity.

(A, B) Scatter plots of the frequencies cells expressing different shRNAs targeting a 20S core subunit (A) or a 19S regulator subunit (B) in untreated or carfilzomib-treated cells. The grey dots represent cells expressing negative control shRNAs. Colored bars indicate the quantitative resistance phenotype (ρ) of each shRNA. (C) Heatmap showing the protective or sensitizing effect of knocking down subunits of the 19S or 20S proteasomes, respectively, in multiple cell lines. (D) Dose-response of U266 cells that constitutively expresses an shRNA targeting the PSMD12 subunit of the 19S proteasome, the PSMB5 subunit of the 20S proteasome, or a negative control shRNA. Data points are means of two experimental replicates, error bars denote SD. DOI: http://dx.doi.org/10.7554/eLife.08153.008

Figure 5.. Proteasome activity in U266 cells expressing a negative control shRNA or an shRNA targeting the PSMD12 subunit of the 19S proteasome, and its susceptibility to inhibition by carfilzomib after a 1 hr treatment.

(A) Fluorometric measurement of the chymotrypsin-like protease activity of the 20S proteasome. (B, C) Enzyme-linked immunoabsorbent assay for accessibility of the (B) β5 subunit and the (C) LMP7 subunits of the 20S proteasome. Data points are means of two experimental replicates, error bars denote SD. DOI: http://dx.doi.org/10.7554/eLife.08153.009

Figure 5—figure supplement 1.. Characterization of samples used to measure proteasome activity in Figure 5.

(A) Immunoblot analysis of PSMD12 and PSMB5 levels. Numbers below the blots correspond to the normalized relative amount (compared to total protein in each lane). (B) PSMD12 transcript levels quantified by qPCR and normalized to GAPDH and to the untreated negative control cells. Data points are means of three primer pairs targeting the transcript, error bars denote SD. (C) Dose response to carfilzomib. Data points are means of two experimental replicates, error bars denote SD. DOI: http://dx.doi.org/10.7554/eLife.08153.010

Figure 6.. Depletion of the 19S protease regulator causes the accumulation of specific substrates.

Immunoblot analysis of protein levels in U-266 cells expressing a negative control shRNA or an shRNA targeting 19S subunit PSMD12, untreated or exposed to low (200 nM) or moderate doses (2 μM) of carfilzomib for 4 hr. Numbers below the blots correspond to the normalized relative amount (compared to total protein in each lane). Numbers on the left margin of each panel indicate molecular weights (kDa). DOI: http://dx.doi.org/10.7554/eLife.08153.011

Figure 6—figure supplement 1.. Determination of the global effects of 19S proteasome depletion on the proteome.

(A) Schematic of proteomics experiments in K562 cells expressing a negative control shRNA (N.C.) or an shRNA targeting the PSMD6 subunit of the 19S proteasome, either untreated or treated with bortezomib. (B) Log₂ enrichment of proteins derived from proteome-wide SILAC in cells treated with bortezomib or in cells where the 19S proteasome subunit PSMD6 was knocked down. Overall Pearson correlation between the proteomic changes induced by the two treatments is 0.3. Blue and green lines correspond to the top 50 enriched proteins for each experiment. GO terms enriched within these sets were Protein Degradation (for PSMD6 knockdown, FDR-corrected p < 0.001) and Cell cycle (for bortezomib treatment, FDR-corrected p < 0.13) (C) Increased levels of factors involved in autophagy and the ubiquitin-proteasome system (UPS) specifically by PSMD6 knockdown. PSMD6 KD (bortezomib) refers to the effect of PSMD6 KD in the context of bortezomib treated samples (i.e. log2 ratio of PSMD6 KD + bortezomib over control KD + bortezomib), whereas Bortezomib (PSMD6 KD) refers to the effect of bortezomib treatment in the context of PSMD6 KD cells (i.e. the log2 ratio of PSMD6 KD + bortezomib over PSMD6 KD + DMSO). (D) Fold enrichment of ubiquitylated peptides caused by PSMD6 knockdown. Prominent hits represent the UPS and autophagy as protein degradation pathways. DOI: http://dx.doi.org/10.7554/eLife.08153.012

Figure 7.. 19S proteasomal subunit levels predict the response to carfilzomib-based therapy in patients.

Levels of (A) 19S subunit PSMC2, (B) 20S subunit PSMB2 and (C) aggresomes quantified by flow cytometry in CD138 + bone marrow cells (including plasma cells and MM cells) of patients prior to therapy in clinical trial for carfilzomib-based combination therapy. Values are shown for separately for complete responders and partial responders. DOI: http://dx.doi.org/10.7554/eLife.08153.013

Author response image 1.

DOI: http://dx.doi.org/10.7554/eLife.08153.020