A comprehensive survey of genomic alterations in gastric cancer reveals systematic patterns of molecular exclusivity and co-occurrence among distinct therapeutic targets

Abstract

Objective: Gastric cancer is a major gastrointestinal malignancy for which targeted therapies are emerging as treatment options. This study sought to identify the most prevalent molecular targets in gastric cancer and to elucidate systematic patterns of exclusivity and co-occurrence among these targets, through comprehensive genomic analysis of a large panel of gastric cancers.

Design: Using high-resolution single nucleotide polymorphism arrays, copy number alterations were profiled in a panel of 233 gastric cancers (193 primary tumours, 40 cell lines) and 98 primary matched gastric non-malignant samples. For selected alterations, their impact on gene expression and clinical outcome were evaluated.

Results: 22 recurrent focal alterations (13 amplifications and nine deletions) were identified. These included both known targets (FGFR2, ERBB2) and also novel genes in gastric cancer (KLF5, GATA6). Receptor tyrosine kinase (RTK)/RAS alterations were found to be frequent in gastric cancer. This study also demonstrates, for the first time, that these alterations occur in a mutually exclusive fashion, with KRAS gene amplifications highlighting a clinically relevant but previously underappreciated gastric cancer subgroup. FGFR2-amplified gastric cancers were also shown to be sensitive to dovitinib, an orally bioavailable FGFR/VEGFR targeting agent, potentially representing a subtype-specific therapy for FGFR2-amplified gastric cancers.

Conclusion: The study demonstrates the existence of five distinct gastric cancer patient subgroups, defined by the signature genomic alterations FGFR2 (9% of tumours), KRAS (9%), EGFR (8%), ERBB2 (7%) and MET (4%). Collectively, these subgroups suggest that at least 37% of gastric cancer patients may be potentially treatable by RTK/RAS directed therapies.

Figure 1

Broad and focal genomic alterations in gastric cancer. (A) Large-scale copy number alterations. The diagram shows a CNA plot where chromosomal regions of the 22 autosomes are represented on the y-axis, and genomic identification of significant targets in cancer (GISTIC) computed false discovery rate (FDR) q-values are on the x-axis. Chromosomal deletions are on the left (blue) and amplifications are on the right (red). Significantly altered regions of broad CNA are highlighted at the sides, as blue and red bars (GISTIC q value <0.25). (B) Focal alterations. Genes localised within the peaks of the focally altered regions are specified. Genes in square brackets are genes that lie immediately adjacent to the alteration peak (eg, MYC). Significantly altered focal events (GISTIC q-value <0.001) are highlighted at the sides and summarised in table 1.

Figure 2

Mutually exclusive and co-amplified genomic alterations. (A) Focal regions exhibiting mutually exclusive patterns of genome amplification. Chromosomal diagrams were created using Circos software. Circular tracks from outside to in: genomic positions by chromosomes (black lines are cytobands, red lines are centromeres); summarised CNA values in gastric tumours, summarised CNA values in normal gastric samples. Blue lines indicate pairs of focal regions (genes) exhibiting significant patterns of mutually exclusive genomic amplification identified by dimension reduction permutation (DRP) analysis (p<0.05; EGFR/KRAS, p=0.05). Genes involved in receptor tyrosine kinase (RTK)/RAS signalling are highlighted in red. (B) Focal regions exhibiting patterns of genomic co-amplification. Orange lines indicate pairs of focal regions (genes) exhibiting significant patterns of genomic co-amplification identified by DRP analysis (p<0.05). Genes involved in RTK/RAS signalling are highlighted in red. Supplementary table S3 (available online only) provides a complete list of significant mutually exclusive and co-alteration relationships for amplifications and deletions.

Figure 3

Genomic alterations of receptor tyrosine kinase (RTK)/RAS signalling components in gastric cancer. (A) Mutually exclusive amplification patterns of RTK/RAS signalling components. In the heat-map, each row represents a different RTK/RAS signalling component. Each column represents an individual tumour exhibiting RTK/RAS amplification (72 tumours). The red colour gradient (top right) highlights the degree of copy number amplification. Black arrows highlight two tumours exhibiting high level amplifications in two RTK/RAS components. (B) Overall frequency of RTK/RAS genomic alterations in gastric cancer. The pie chart displays the different gastric cancer subgroups exhibiting RTK/RAS amplification. Gastric cancers exhibiting at least one RTK/RAS amplification event comprise a collective 37% of the gastric cancer cohort analysed. (C) Kaplan–Meier survival analysis comparing outcomes of patients with tumours exhibiting RTK amplification (either FGFR2, ERBB2, EGFR, or MET) amplification to patients with tumours lacking RTK amplification. Patients with tumours exhibiting focal KRAS amplifications were included in analysis, and fall into the RTK low/no CNA group. Overall survival was used as the outcome metric. (D) Kaplan–Meier survival analysis comparing outcomes of patients with tumours exhibiting KRAS amplification (15 patients) to patients with non-RTK/KRAS-amplified tumours. Overall survival was used as the outcome metric. The inset photo displays a patient tumour (ID 49375233) with KRAS amplification confirmed by fluorescence in-situ hybridisation (FISH) analysis (blue, DAPI nuclear stain; green, KRAS FISH probe; red, centromere 12 probe).

Figure 4

FGFR2 gene amplification and messenger RNA expression in gastric cancer. (A) Heat-map showing the FGFR2 gene amplification region in individual gastric cancer samples (20 tumours). Each row indicates one gastric cancer sample with the amplified region in red. Intensity of the red bar indicates the level of copy number amplification. Genes located in this region are shown at the bottom. The intersection of these amplified regions covers only the FGFR2 gene (red box, gene outlined at bottom). (B) FGFR2 genomic amplification confirmed by fluorescence in-situ hybridisation (FISH). The photo displays a patient tumour (ID 21080055) with FGFR2 amplification and two FGFR2-amplified cell lines KATO-III and SNU16 confirmed by FISH analysis. Green signals indicate the FGFR2 FISH probe, red signals probes to centremore 10. (C) FGFR2 gene expression in clinical specimens. FGFR2 gene expression was compared across three categories, each represented by a box-plot: non-malignant gastric tissues (normal) (n=100); tumours exhibiting no/low FGFR2 CNA (n=139); and tumours exhibiting high FGFR2 CNA (n=17). mRNA comparisons were based on 156 gastric cancers in which gene expression data were available, representing a subset of the 193 gastric cancers analysed by single nucleotide polymorphism arrays. FGFR2 gene expression was inferred from Affymetrix microarrays (FGFR2 probe 211401_s_at). FGFR2 mRNA levels are significantly higher in samples with FGFR2 high CNA compared with the other two categories (p=6.7e-9, Kruskal–Wallis test). Tumours exhibiting FGFR2 amplification exhibit significantly increased FGFR2 gene expression compared with tumours exhibiting no/low FGFR2 CNA or non-malignant samples (p=1.9e-5 and 1.7e-7, Wilcoxon test). (D) Kaplan–Meier survival analysis comparing patients with tumours exhibiting high FGFR2 gene expression, defined as twofold higher than the average FGFR2 gene expression level in normal samples (72 tumours), with patients with tumours exhibiting low FGFR2 gene expression (total 398 patients, the 156 patients analysed in figure 4C are a subset of these 398 patients). Overall survival was used as the outcome metric.

Figure 5

Sensitivity of FGFR2-amplified gastric cancer cell lines to dovitinib. (A) (Top) FGFR2 reverse transcription PCR analysis of gastric cancer cell lines. Glyceraldehyde-3-phosphate dehydrogenase (GAPDH) was used as a loading control. (Bottom) FGFR2 protein expression in lines. β-actin was used as a loading control. Cell lines KATOIII and SNU16 are observed to express elevated levels of FGFR2 mRNA and protein. (B) Cell proliferation effects of dovitinib treatment. Dovitinib GI50 values for FGFR2-amplified and non-amplified cell lines. GI50, drug concentration required to cause 50% growth inhibition. GI50 values were calculated after 48 h dovitinib treatment. *p<0.05 compared with non-amplified lines. Results are a mean of three independent experiments. (C) Molecular effects of dovitinib treatment. Cells treated with dovitinib at 50 nM, 100 nM and 500 nM concentrations for 1 h. Lysates were immunoprecipitated with FGFR2 anitbody MAB6841, and probed with 4G10 (phosphotyrosine detection) or MAB6841 for total FGFR2. Other antibodies included total and phospho-ERK, and total and phospho-AKT. Experiments were repeated a minimum of three independent times. (D) Dovitinib inhibits soft agar colony formation. FGFR2-amplified cells were treated with dovitinib at the GI50 concentration for each cell line (KATO-III 0.12 μM; SNU-16 0.17 μM) for 48 h, and soft-agar colony formation monitored over the subsequent 3–4 weeks. Data for KATO-III cells are provided, including representative colony plates. Similar results were observed for SNU16 (see supplementary figure S9, available online only). (E) Dovitinib induces caspase-3 activation. FGFR2-amplified cells were treated with increasing dovitinib concentrations, and apoptosis levels measured after 24 h using Caspase-Glo 3/7 assays. The y-axis represents the percentage of activation normalised against untreated controls. The results are a mean of triplicates ±SD. Experiments were repeated three independent times. (F) Dovitinib inhibits tumour growth in a human primary gastric cancer xenograft model bearing FGFR2 gene amplification. The mean tumour size of the vehicle-treated mice reached 1163 mm³ at day 25 post-treatment. Treatment with the positive control drug 5-FU at 20 mg/kg (qd × 5/week ×2 weeks, intraperitoneally) produced a mean tumour size of 518 mm³ (total growth inhibition 63%, p=0.08) at the same time. Treatment with dovitinib at 30 mg/kg and 50 mg/kg (qd ×25 days, by mouth) significantly inhibited tumour growth compared with vehicle-treated animals, with a mean tumour size of 194 and 53 mm³, respectively (p=0.006 and 0.002, respectively, at day 25 post-treatment).