Development of a personalized therapeutic strategy for ERBB-gene-mutated cancers

Abstract

Background: The application of genomic technologies to patient tumor samples identified groups of signaling pathways which acquire activating mutations. Some cancers are dependent on these mutations and the aberrant proteins resulting from these mutations can be targeted by novel drugs which can eradicate the cancer.

Methods: We used www.cbioportal.org to determine the frequency of ERBB mutations in solid tumors. We then determined the sensitivity of a panel of cell lines to clinically available PI3K inhibitors. Using proliferation and apoptosis assays as well as functional interrogation with reverse phase protein arrays we demonstrated the impact of targeting ERBB-mutant cancers with the combination of a PI3K inhibitor and the pan-HER family inhibitor afatinib.

Results: In over 14,000 patients we found that 12% of their tumors have an ERBB family gene mutation (EGFR, ERBB2, ERBB3 and ERBB4). In cancers not commonly associated with HER family protein overexpression, such as ovarian, endometrial, melanoma and head and neck cancers (n = 2116), we found that ERBB family mutations are enriched, occurring at rates from 14% to 34% and commonly co-occur with PIK3CA mutations. Importantly, we demonstrate that ERBB family mutant cancers are sensitive to treatment with PI3K inhibitors. Finally we show that the combination of afatinib and copanlisib represents a novel therapeutic strategy for patients whose cancers harbor both ERBB family and PIK3CA mutation.

Conclusions: We demonstrate that ERBB family mutations are common in cancers not associated with overexpression or amplification of HER family proteins. These ERBB family mutant cancers are sensitive to treatment with PI3K inhibitors, and when combined with pan-HER inhibitors have synergistic antiproliferative effects.

Keywords: Afatinib; ERBB mutant cancers; PIK3CA mutant cancers; copanlisib; personalized therapy.

Figure 1.

Frequency of somatic ERBB family mutations in (a) all 81 datasets available on www.cbioprtal.org (n = 14,539 cancers) or (b) in datasets where ERBB family mutations are enriched, including esophageal, ovarian, endometrial, melanoma, stomach, head and neck, bladder and colorectal cancers. Mut, mutated (somatic); WT, wild type. ERBB family/PIK3CA WT, blue; ERBB family WT/PIK3CA Mut, red; ERBB family Mut/PIK3CA WT, green; ERBB family/PIK3CA Mut, purple.

Figure 2.

Comparison of IC₅₀ values for copanlisib in green (n = 61), pictilisib in blue (n = 23) and gedatolisib in red (n = 17) when assessed relative to the ERBB family or PIK3CA mutational status of each cell line. Displayed p values were calculated using Student’s t test and were deemed significant if p < 0.05. Mut, mutation; WT, wild type.

Figure 3.

Efficacy of afatinib (blue), copanlisib (red) and a combination of afatinib and copanlisib (green) in a panel of cell lines which are (a) wild type (WT) for both PIK3CA and ERBB family genes, (b) PIK3CA Mut/ERBB family WT, (c) ERBB family Mut/PIK3CA WT and (d) ERBB family/PIK3CA Mut. Error bars are representative of standard deviations across triplicate experiments. The ratio of afatinib to copanlisib in this assay is fixed at either 16:1 or 4:1 depending on the cell line. ED, effective dose; Mut, mutation; WT, wild type.

Figure 4.

The impact of (a) copanlisib, (b) afatinib or (c) copanlisib and afatinib on expression and phosphorylation of proteins in the PI3K/AKT or MAPK/ERK signaling pathways relative to vehicle treated controls as measured by reverse phase protein array analysis. ‘•’ represents the ERBB/PIK3CA wild type (WT) cell line (KLE), ‘’ the PIK3CA mutation (Mut)/ERBB family WT cell line (HT29), ‘□’ the ERBB family Mut/PIK3CA WT cell line (C2BBE1) and ‘’ the ERBB family/PIK3CA Mut cell line (H1975). Error bars are representative of standard deviations across triplicate independent experiments. Fold changes of ⩾1.2 and with a p value of <0.05 as calculated by Student’s t test are classified as significant by the use of an asterisk of a similar color to the relevant cell line.

Figure 5.

The impact of vehicle, copanlisib, afatinib or a combination of copanlisib (Cop, C) and afatinib (Afat, A) on apoptosis induction in (a) the ERBB/PIK3CA wild type (WT) cell line (KLE), (b) the PIK3CA mutation (Mut)/ERBB family WT cell line (HT29), (c) the ERBB family Mut/PIK3CA WT cell line (C2BBE1) and (d) the ERBB family/PIK3CA Mut cell line (H1975) as determined using fluorescence-activated cell sorting (FACS) analysis of propidium iodide/annexin V stained cells. Red bars represent apoptotic cells and green bars represent necrotic cells. Error bars are representative of standard deviations across triplicate independent experiments.

Figure 6.

The impact of the combination of copanlisib and afatinib on expression and phosphorylation of proteins in the apoptotic signaling pathway relative to vehicle-treated controls as measured by reverse phase protein array analysis. ‘•’ represents the ERBB/PIK3CA wild type (WT) cell line (KLE), ‘’ the PIK3CA mutation (Mut)/ERBB family WT cell line (HT29), ‘□’ the ERBB-family Mut/PIK3CA WT cell line (C2BBE1) and ‘’ the ERBB family/PIK3CA Mut cell line (H1975). Error bars are representative of standard deviations across triplicate independent experiments. Changes of ⩾±20% and with a p value of <0.05 as calculated by Student’s t test are classified as significant.