Time series analysis of neoadjuvant chemotherapy and bevacizumab-treated breast carcinomas reveals a systemic shift in genomic aberrations

Abstract

Background: Chemotherapeutic agents such as anthracyclines and taxanes are commonly used in the neoadjuvant setting. Bevacizumab is an antibody which binds to vascular endothelial growth factor A (VEGFA) and inhibits its receptor interaction, thus obstructing the formation of new blood vessels.

Methods: A phase II randomized clinical trial of 123 patients with Her2-negative breast cancer was conducted, with patients treated with neoadjuvant chemotherapy (fluorouracil (5FU)/epirubicin/cyclophosphamide (FEC) and taxane), with or without bevacizumab. Serial biopsies were obtained at time of diagnosis, after 12 weeks of treatment with FEC ± bevacizumab, and after 25 weeks of treatment with taxane ± bevacizumab. A time course study was designed to investigate the genomic landscape at the three time points when tumor DNA alterations, tumor percentage, genomic instability, and tumor clonality were assessed. Substantial differences were observed with some tumors changing mainly between diagnosis and at 12 weeks, others between 12 and 25 weeks, and still others changing in both time periods.

Results: In both treatment arms, good responders (GR) and non-responders (NR) displayed significant difference in genomic instability index (GII) at time of diagnosis. In the combination arm, copy number alterations at 25 loci at the time of diagnosis were significantly different between the GR and NR. An inverse aberration pattern was also observed between the two extreme response groups at 6p22-p12 for patients in the combination arm. Signs of subclonal reduction were observed, with some aberrations disappearing and others being retained during treatment. Increase in subclonal amplification was observed at 6p21.1, a locus which contains the VEGFA gene for the protein which are targeted by the study drug bevacizumab. Of the 13 pre-treatment samples that had a gain at VEGFA, 12 were responders. Significant decrease of frequency of subclones carrying gains at 17q21.32-q22 was observed at 12 weeks, with the peak occurring at TMEM100, an ALK1 receptor signaling-dependent gene essential for vasculogenesis. This implies that cells bearing amplifications of VEGFA and TMEM100 are particularly sensitive to this treatment regime.

Conclusions: Taken together, these results suggest that heterogeneity and subclonal architecture influence the response to targeted treatment in combination with chemotherapy, with possible implications for clinical decision-making and monitoring of treatment efficacy.

Trial registration: NCT00773695 . Registered 15 October 2008.

Keywords: Angiogenesis; Breast cancer; Chemotherapy; Clonal and subclonal aberrations; Targeted treatment; Tumor heterogeneity.

Fig. 1

Degree of copy number aberrations between different response groups within each treatment arm. a Difference in genomic instability index (GII, y-axis) between patients obtaining pCR and non-pCR (x-axis). No significant difference was observed in either treatment arm (Student’s t test). b Significant difference in tumors’ GII between patients with good response (GR), intermediate response (IR), and no response (NR) (ANOVA test p value < 0.05) within both treatment arms

Fig. 2

Genomic instability index (GII) as a function of proliferation score for with good response (GR, green), intermediate response (IR, light blue), and no response (NR, red) tumors for both treatment arms. Significant correlation was observed (Pearson correlation = 0.52, p value < 0.01)

Fig. 3

Mean genomic instability index (GII) versus tumor percentage (deduced from ASCAT) before, during, and after treatment, stratified on treatment arms. The top row shows that patients with good response (GR) independent of treatment arms have a higher mean GII, but similar average tumor percentage (bars indicating standard error), than patients with no response (NR) tumors (lower row) before any treatment (blue). After 12 weeks of treatment (pink), the mean GII and tumor percentage drastically gets reduced in the GR tumors (top row), and at the time of surgery (green), more or less all sign of tumor is lost in both treatment arms. Patients not responding to the combination therapy (bottom left plot) show a reduction in mean GII and tumor percentage after 12 weeks of treatment (pink), which halts until time of surgery (green). The bottom right plot reveals that the shift in mean GII and tumor percentage between the three time points is very low for NR tumors in the chemotherapy arm

Fig. 4

Frequency plots of genome-wide copy number aberrations (CNAs) in tumors at the time of diagnosis (a), after 12 weeks of treatment (b), and at the time of surgery (c) from patients in the combination arm. The y-axis indicates frequency (%) of tumors with gains (red) and deletions (green) sorted by genomic positions (x-axis) across all chromosomes (annotated at top of the plots). a Untreated tumors from good response (GR) tumors (n = 19, top plot) show a higher frequency of alterations genome wide, in comparison with no response (NR) (n = 10, bottom plot). Loci significantly associated to different responses are marked with asterisk. b, c Aberrations disappear during treatment for patients responding (top) to the therapy, while for the NR (bottom), several copy number changes are kept

Fig. 5

Frequency plots of genome-wide copy number aberrations (CNAs) in tumors at the time of diagnosis (a), after 12 weeks of treatment (b), and at the time of surgery (c) for patients treated with chemotherapy alone. The y-axis indicates frequency (%) of tumors with gains (red) and deletions (green) sorted by genomic positions (x-axis) across all chromosomes (annotated at top of the plots). Higher frequency of copy number changes is observed in untreated good response (GR) tumors (a, top) compared to no response (NR) tumors (a, bottom). During treatment (weeks 12 and 25), the GR tumors shrink and CNA frequency profiles lose their aberrations (b, c, top). Tumors not responding to treatment keep their aberrations during treatment (bottom)

Fig. 6

Number of patients showing an increase (green) or a decrease (red) in the subclonality of copy number gains genome wide between diagnosis and 12 weeks after treatment for responders (a) and non-responders (b). Significantly more patients showed an increase in the clonality of VEGFA gains and a decrease in the clonality of TMEM100 gains (arrows) across the whole cohort