Dysfunctional KEAP1-NRF2 interaction in non-small-cell lung cancer

Abstract

Background: Nuclear factor erythroid-2 related factor 2 (NRF2) is a redox-sensitive transcription factor that positively regulates the expression of genes encoding antioxidants, xenobiotic detoxification enzymes, and drug efflux pumps, and confers cytoprotection against oxidative stress and xenobiotics in normal cells. Kelch-like ECH-associated protein 1 (KEAP1) negatively regulates NRF2 activity by targeting it to proteasomal degradation. Increased expression of cellular antioxidants and xenobiotic detoxification enzymes has been implicated in resistance of tumor cells against chemotherapeutic drugs.

Methods and findings: Here we report a systematic analysis of the KEAP1 genomic locus in lung cancer patients and cell lines that revealed deletion, insertion, and missense mutations in functionally important domains of KEAP1 and a very high percentage of loss of heterozygosity at 19p13.2, suggesting that biallelic inactivation of KEAP1 in lung cancer is a common event. Sequencing of KEAP1 in 12 cell lines and 54 non-small-cell lung cancer (NSCLC) samples revealed somatic mutations in KEAP1 in a total of six cell lines and ten tumors at a frequency of 50% and 19%, respectively. All the mutations were within highly conserved amino acid residues located in the Kelch or intervening region domain of the KEAP1 protein, suggesting that these mutations would likely abolish KEAP1 repressor activity. Evaluation of loss of heterozygosity at 19p13.2 revealed allelic losses in 61% of the NSCLC cell lines and 41% of the tumor samples. Decreased KEAP1 activity in cancer cells induced greater nuclear accumulation of NRF2, causing enhanced transcriptional induction of antioxidants, xenobiotic metabolism enzymes, and drug efflux pumps.

Conclusions: This is the first study to our knowledge to demonstrate that biallelic inactivation of KEAP1 is a frequent genetic alteration in NSCLC. Loss of KEAP1 function leading to constitutive activation of NRF2-mediated gene expression in cancer suggests that tumor cells manipulate the NRF2 pathway for their survival against chemotherapeutic agents.

Figure 1. Schematic of the Conserved Domain Structure of Human KEAP1 Protein

The protein consists of an N-terminal region (amino acids 1–60), a BTB domain (amino acids 61–179), a central IVR (amino acids 180–314), a double-glycine-rich region comprising six Kelch motifs (amino acids 315–359, 361–410, 412–457, 459–504, 506–551, and 553–598), and a C-terminal domain (amino acids 599–624). The frequency of mutations detected within each domain is indicated below. Amino acid positions of the mutations are listed in Table 1.

Figure 2. Somatic Alterations in KEAP1 in Lung Cancer

(A) LOH at the 19p13.1–13.3 region. A heat map depicts microsatellite-based LOH at 19p13.1–19p13.3 in 181 lung cancer cell lines. Tumor-derived cell lines that were non-informative for this region were not included. Microsatellite markers showing heterozygous typings are depicted in red, markers demonstrating homozygous typing are in green, and non-informative markers in black. Each vertical column represents one cell line. ET, endocrine tumors; NS, no subtype specified; SCC, small cell carcinoma. (B) Sequence analysis of KEAP1 mutations in lung cancer. Part a shows the H838 cell line showing C–A substitution (G–T, plus strand), resulting in a termination codon. Wild-type sequence is from BEAS2B. A wild-type allele was not detected in H838. Part b shows a 18-bp deletion in one allele but not in the other allele in the PF DNA sample from PF-8. Part c shows tumor PT-23, showing A–T substitution in one allele but not in the other allele. Part d shows a 2-bp deletion in the fourth exon of KEAP1 that was detected in one allele of PT-17. Samples showing deletion mutations were confirmed by subcloning and sequencing. (C) LOH at the KEAP1 locus in human primary lung tumors. Summary of LOH patterns of 39 NSCLC tumors. Retained microsatellites are indicated in red, markers demonstrating allelic loss in green, markers showing genomic instability in white, and non-informative markers in black. KEAP-UM1 (CA₁₇) is present upstream of the KEAP1 locus, and KEAP-DM1 (CA₂₁) is present downstream of the KEAP1 locus.

Figure 3. Dysfunctional KEAP1–NRF2 Interaction in NSCLC Tumors

(A) Immunohistochemical analysis of NRF2 in NSCLC tissues. Part a shows a patient (PT-18) with mutation in KEAP1 showing strong nuclear and cytoplasmic staining. Part b shows a patient negative for mutation (PT-28) showing weak cytoplasmic staining. Part c shows a patient negative for mutation (PT-20) showing increased nuclear and cytoplasmic staining in tumor tissue. Part d shows weakly staining normal bronchus from the same patient (PT-20). (B) Total GSH and enzyme activities of NQO1 and total GST in NSCLC and matched normal tissues. Raw data for the heat maps are presented in Table S4. *, samples harboring KEAP1 mutation; §, nmol/mg protein; †, nmol DCPIP reduced/min/mg protein; ‡, nmol of product formed/min/mg protein.

Figure 4. Status of KEAP1 and NRF2 Is Altered in Cancer Cells

(A) Immunoblot showing increased nuclear localization of NRF2 in nuclear extracts (NE) from cancer cells. Cancer cells showed lower levels of KEAP1 (~69 kDa) and higher levels of NRF2 (~110 kDa) in total protein lysates (TP). NIVT and KIVT indicate NRF2 and KEAP1 in vitro transcribed/translated product, respectively. (B and C) Quantification of NRF2 and KEAP1 protein in immunoblots. For band densitometry, bands in nuclear extract blot (B) were normalized to Lamin B1, and those in total protein (C) were normalized to GAPDH. (D) Heat map showing relative expression of KEAP1, NRF2, and NRF2-dependent genes by real-time RT-PCR. Raw data for the heat maps are presented in Table S5.

Figure 5. Comparison of Total GSH Levels, GST, NQO1, and GSR Enzyme Activities between Cancer Cells and Normal Cells

Shown are total GSH levels (A) and enzyme activities for GST (B), NQO1 (C), and GSR (D). Data represent mean ± SD (n = 3). *, p = 0.0016; **, p = 0.039; ***, p = 0.011 relative to normal cells (by t-test).

Figure 6. Mutant KEAP1 Protein Is Unable to Suppress NRF2 Activity

(A) Repression activity of the KEAP1 mutants was monitored by a luciferase reporter assay. Wild-type and mutant KEAP1 cDNA constructs were transfected onto H838 cells stably expressing ARE luciferase reporter. Data represent mean ± SD (n = 3). (B) Silencing of NRF2 by siRNA in A549 cells downregulated the expression of NRF2-dependent genes. A nonspecific siRNA (NS siRNA) was used as control. (C) Inhibition of KEAP1 expression by siRNA in BEAS2B cells upregulated the expression of NRF2-dependent genes.

Figure 7. Increased NRF2 Activity Confers Chemoresistance

BEAS2B cells and cancer cells were exposed to etoposide (A) or carboplatin (B) for 72 h, and viable cells were determined by MTT assay. BEAS2B cells displayed enhanced sensitivity whereas cancer cells with dysfunctional KEAP1 activity demonstrated reduced chemosensitivity to etoposide and carboplatin treatment. Data are presented as percentage of viable cells relative to the vehicle-treated control. Data are the mean of eight independent replicates, combined to generate the mean ± SD for each concentration.