Evolution and clinical impact of co-occurring genetic alterations in advanced-stage EGFR-mutant lung cancers

Abstract

A widespread approach to modern cancer therapy is to identify a single oncogenic driver gene and target its mutant-protein product (for example, EGFR-inhibitor treatment in EGFR-mutant lung cancers). However, genetically driven resistance to targeted therapy limits patient survival. Through genomic analysis of 1,122 EGFR-mutant lung cancer cell-free DNA samples and whole-exome analysis of seven longitudinally collected tumor samples from a patient with EGFR-mutant lung cancer, we identified critical co-occurring oncogenic events present in most advanced-stage EGFR-mutant lung cancers. We defined new pathways limiting EGFR-inhibitor response, including WNT/β-catenin alterations and cell-cycle-gene (CDK4 and CDK6) mutations. Tumor genomic complexity increases with EGFR-inhibitor treatment, and co-occurring alterations in CTNNB1 and PIK3CA exhibit nonredundant functions that cooperatively promote tumor metastasis or limit EGFR-inhibitor response. This study calls for revisiting the prevailing single-gene driver-oncogene view and links clinical outcomes to co-occurring genetic alterations in patients with advanced-stage EGFR-mutant lung cancer.

Figure 1. Co-occurring genomic alterations detectable in cell-free DNA of advanced-stage EGFR-mutant positive compared to EGFR-mutant negative non-small cell lung cancer (NSCLC) patients

(a) Frequency of genomic alterations: non-synonymous somatic variants of predicted functional significance (SNV, see Methods), copy number gains (CNG), insertions or deletions (INDEL), or gene rearrangements (FUSION) in the cancer-related genes listed (Supplementary Table 2), detected by next-generation sequencing of circulating tumor DNA from 1122 advanced-stage EGFR-mutant positive NSCLC patients (a) compared to a cohort of 944 EGFR-mutant negative NSCLC patients (b) (Supplementary Datasets 1 and 2). Co-occurring alterations that occurred in at least 5% of EGFR-mutant positive cases are shown. * Indicates statistically significant differences between the cohorts (q < 0.2). (c) Gene alterations with increased frequency in EGFR-mutant positive compared to EGFR-mutant negative patients (Two-tailed Fisher’s exact test performed to identify statistically significant differences in TP53, CDK6, CTNNB1, and AR, using Benjamini-Hochbeg correction for multiple hypothesis testing (q-values). (d) Lolliplots of gene level alterations in EGFR-mutant positive compared to EGFR-mutant negative samples. The functional significance of somatic variants is indicated based on analysis described in Methods. (e) Differences in pathway level alterations between EGFR-mutant positive and EGFR-mutant negative cases (two-tailed Fisher’s Exact test comparing EGFR-mutant positive to EGFR mutant-negative with Benjamini-Hochbeg correction for multiple hypothesis testing (q-values). See also Supplementary Tables 1–3 and Supplementary Datasets 1 and 2.

Figure 2. Co-occurring genomic alterations detected in cell-free DNA of 440 advanced-stage EGFR-mutant, p.Thr790Met positive compared to 682 advanced-stage EGFR-mutant, p.Thr790Met negative NSCLC patients

(a–b) Frequency of non-synonymous genomic alterations of known or predicted functional significance: somatic variants (SNV), copy number gain (CNG), insertions or deletions (INDEL), or gene rearrangements (FUSION) in cancer-related genes detectable by next-generation sequencing (in at least 5% of p.Thr790Met positive cases) of circulating tumor DNA are indicated in (a) EGFR-mutant, p.Thr790Met (denoted as T790M) positive (n=440) and (b) EGFR-mutant, p.Thr790Met negative (n=682) cohorts. Q-values determined by two-tailed by Fisher’s Exact test with Benjamini-Hochberg correction for multiple hypothesis testing * Indicates statistically significant differences between the cohorts (q < 0.2). (c) Frequency (percentage) of gene level alterations detectable in the cell-free DNA of EGFR-mutant, p.Thr790Met positive compared EGFR-mutant, p.Thr790Met negative patients (q-values determined by two-tailed by Fisher’s Exact test with Benjamini-Hochberg correction for multiple hypothesis testing). (d–e) Lolliplots of gene level alterations in EGFR-mutant,p.Thr790Met positive compared to EGFR-mutant, p.Thr790Met negative samples. Somatic alterations in CTNNB1 (d) and KRAS (e) are indicated. The functional significance of somatic variants is indicated based on analysis described in Methods. (f) Differences in pathway level alterations between EGFR-mutant p.Thr790Met positive and EGFR-mutant p.Thr790Met negative cases determined by two-tailed Fisher’s Exact test with Benjamini-Hochberg correction for multiple hypothesis testing (q-value). See also Supplementary Figure 1, Supplementary Table 4 and Supplementary Dataset 1.

Figure 3. Therapy-induced evolution of genomic co-alterations detected in cell-free DNA of advanced-stage EGFR-mutant NSCLC patients

cfDNA analysis of 137 samples collected from 97 patients with known clinical history (see also Supplementary Table 5 and Supplementary Dataset 3). (a) Samples were segregated by EGFR TKI treatment; pre-TKI (n=21), at the time of progression to first-line EGFR TKI therapy; PD to 1^st line (n=53), or at the time of progression to 2^nd line anti-cancer therapy (2^nd or 3^rd generation EGFR TKI, or chemotherapy); PD to 2^nd line (n=26). (b) Number of functional alterations detectable based on line of therapy are indicated (mean ± 95% CI). Pre-TKI (3.4, 95% CI: 2.2–4.5), PD to 1^st line (3.8, 95% CI: 3.2–4.4), PD to 2^nd line (5.2, 95% CI: 4.1–6.3). Pre-TKI vs. PD to 1^st line P = 0.8, Pre-TKI vs. PD to 2^nd line P = 0.03, PD to 1^st line vs. PD to 2^nd line P = 0.04, F = 4.3, DF = 97, ANOVA with Tukey correction for multiple comparisons. (c) Changes in gene alteration frequency (percentage) with line of therapy (d) Changes in cancer-related pathway alterations (percentage) with line of therapy. (c and d) Two-way Fisher’s exact test was performed to identify statistically significant differences between pre-TKI and PD to 1^st line, between PD to 1^st line and PD to 2^nd line, and between pre-TKI and PD to 2^nd line with Benjamini-Hochberg correction for multiple hypothesis testing (q-values). See also Supplementary Figures 2–5, Supplementary Tables 5, and Supplementary Dataset 3.

Figure 4. Effect of cfDNA detectable co-occurring genetic alterations on osimertinib clinical response in advanced-stage EGFR-mutant lung cancer patients

(a–b) Genomic alterations detectable in cfDNA from advanced EGFR-mutant NSCLC patients who were subsequently treated with osimertinib and exhibited a radiographic/clinical response (a) (PR by clinician assessment, see methods) versus patients who did not respond (b) (by clinician assessment, see methods). (c) Forrest plot demonstrating effect of cfDNA detectable gene level alterations on PFS with P-values determined by Cox-proportional Hazard Ratio (HR) with 95% CI. (d) Kaplan-Meier curves demonstrating difference in median PFS (logrank test) in patients with cfDNA detectable alterations in CDK4 or CDK6. (e) Pathway level alterations in osimertinib responders vs. non-responders. Q-values determined by two-tailed Fisher’s Exact test with Benjamini-Hochberg correction for multiple hypothesis testing. (f–g) Forrest plot and Kaplan-Meier curves assessing the effects of indicated cfDNA detectable pathway alterations on PFS with P-values determined by Cox-proportional Hazard Ratio (HR) with 95% CI. See also Supplementary Figures 4 and 5, Supplementary Table 6 and Supplementary Dataset 4.

Figure 5. Longitudinal genomic analysis of tumor and cell-free DNA in a patient with EGFR-mutant lung cancer from diagnosis to death

(a) Heatmap depicting the clonal status of non-synonymous somatic mutations including SNVs, dinucleotides and indels from each sequenced region of the patient’s disease as determined by subclonal copy number corrected cancer cell fraction and PyClone cross sample clustering. Somatic alterations were detected by whole-exome sequencing of the tumor DNA of the patient at initial presentation and surgical resection of EGFR-mutant lung cancer (R1), at the time of development of metastatic disease (R2), upon progression to first line treatment with erlotinib (R3), and at autopsy after treatment with the 2^nd line EGFR TKI rociletinib followed by PD and death (R4-R7). (see Methods for description of analysis). (b) Phylogenetic tree illustrating the evolutionary history of the patient’s disease at the level of subclonal clusters of mutations. These subclonal clusters are inferred, using PyClone, from the samples taken from the primary and different metastases at multiple time-points. The mutations were clustered based on their prevalence (subclonal copy number corrected cancer cell fraction) in the sequenced cancer cell populations across all samples, this clustering is then used to infer the founding clone (at the bottom of the tree) and subclonal clusters. (c) Pictorial representation of primary tumor and metastatic sites analyzed by whole exome sequencing. (d) cfDNA detectable in plasma from patient at indicated time points as determined by CAPP-Seq analysis. See also Supplementary Figs. 6–8, and Supplementary Datasets 5 and 6.

Figure 6. Functional analysis of CTNNB1 and PIK3CA co-mutations detected in EGFR-mutant lung adenocarcinoma

(a) IHC staining for nuclear β-Catenin or serine-473-phosphorylated AKT (Mean ± S.E.M. images representative of 3 images per panel, scale bar = 50 microns). (b) Immunoblot analysis of HCC827 cells infected with empty vector (E.V.) or constructs that overexpress β-Catenin p.Ser37Phe, PIK3CA p.Gly106Val, or both proteins. Cells were treated with 100 nM erlotinib (E) or rociletinib (R) or vehicle control (veh), and immunoblot analysis performed on cellular extracts. Relative proportions of cleaved-PARP to total PARP and p-AKT to total AKT are indicated. Images are representative of immunoblots from 3 independent cell culture experiments (c) Cellular viability assay (Methods) of HCC827 NSCLC cells engineered to overexpress β-Catenin p.Ser37Phe and/or PIK3CA p.Gly106Val. Relative cell viability compared to DMSO-treated control is indicated. Images are representative of 3 independent cell culture experiments. Cellular growth (d), invasion (e) and migration (f) assays (Methods) comparing HCC827 cells engineered to express the indicated proteins (mean ± S.E.M. from 3 independent cell culture experiments, P-Values determined by ANOVA with Bonferroni’s correction). (d) F = 4.844, DF = 8. (e), F = 5.095, DF = 8. (f), F = 9.633, DF = 8. (g) Quantitative-PCR (Q-PCR) of β-Catenin target genes (mean ± S.E.M from 2 independent experiments). P-Values compared to PIK3CA p.Gly106Val control, ANOVA with Bonferroni’s correction (MYC: F= 6.5, DF = 3; CCND1: F = 107, DF = 3; LEF1: F = 9.5, DF = 3; HOXB9: F = 23.3, DF = 3).

Figure 7. Clonality analysis of co-occurring genetic alterations detectable in the cfDNA of advanced-stage NSCLC patients

The distribution of clonal and subclonal alterations were determined in (a) EGFR-mutant positive (n=1122) vs. EGFR-mutant negative (n=944) NSCLC, and (b) EGFR-mutant p.Thr790Met (T790M) positive (n=440) vs. EGFR-mutant p.Thr790Met (T790M) mutant negative (n=682) NSCLC. Red line indicates division between clonal (≥ 0.2 MAF/Maximum MAF) and subclonal (< 0.2 MAF/Maximum MAF) as defined in the text and Supplementary Fig. 10. P-values determined by two-tailed Fisher’s Exact test. See also Supplementary Fig. 10 and Supplementary Datasets 1 and 2.

Figure 8. Evolution of the understanding of the genetic pathogenesis of oncogene-positive (here, EGFR-mutant) lung cancer

(a) Traditional view of lung cancer based on histopathological analysis. Lung adenocarcinoma, scale bar = 50 microns. (b) Current molecular classification of NSCLC based on single-gene driver oncogene status, depicting the current view of mutually-exclusive driver oncogenes, as shown in the pie chart with frequency of each driver alteration in lung adenocarcinoma. (c) The proposed new model of EGFR-mutant NSCLC pathogenesis arising from our findings: a re-classification of advanced-stage EGFR-mutant NSCLC based on the co-occurring genetic alterations that our dataset revealed (shown here at the pathway level). We propose that advanced-stage EGFR-mutant NSCLCs contain co-occurring genetic alterations that function collaboratively as co-drivers of tumor progression and drug resistance. We now need to identify and co-target these co-occurring functional genetic alterations beyond mutant EGFR itself in patients, early and dynamically during treatment, in order to improve patient survival. The finding of extensive co-occurring alterations within advanced-stage EGFR-mutant NSCLC at scale now paves the way for studying the biological and clinical impacts of genetic interactions that are created by the co-alterations present in these EGFR-mutant NSCLCs.