Molecular subtype and tumor characteristics of breast cancer metastases as assessed by gene expression significantly influence patient post-relapse survival

Abstract

Background: We and others have recently shown that tumor characteristics are altered throughout tumor progression. These findings emphasize the need for re-examination of tumor characteristics at relapse and have led to recommendations from ESMO and the Swedish Breast Cancer group. Here, we aim to determine whether tumor characteristics and molecular subtypes in breast cancer metastases confer clinically relevant prognostic information for patients.

Patients and methods: The translational aspect of the Swedish multicenter randomized trial called TEX included 111 patients with at least one biopsy from a morphologically confirmed locoregional or distant breast cancer metastasis diagnosed from December 2002 until June 2007. All patients had detailed clinical information, complete follow-up, and metastasis gene expression information (Affymetrix array GPL10379). We assessed the previously published gene expression modules describing biological processes [proliferation, apoptosis, human epidermal receptor 2 (HER2) and estrogen (ER) signaling, tumor invasion, immune response, and angiogenesis] and pathways (Ras, MAPK, PTEN, AKT-MTOR, PI3KCA, IGF1, Src, Myc, E2F3, and β-catenin) and the intrinsic subtypes (PAM50). Furthermore, by contrasting genes expressed in the metastases in relation to survival, we derived a poor metastasis survival signature.

Results: A significant reduction in post-relapse breast cancer-specific survival was associated with low-ER receptor signaling and apoptosis gene module scores, and high AKT-MTOR, Ras, and β-catenin module scores. Similarly, intrinsic subtyping of the metastases provided statistically significant post-relapse survival information with the worst survival outcome in the basal-like [hazard ratio (HR) 3.7; 95% confidence interval (CI) 1.3-10.9] and HER2-enriched (HR 4.4; 95% CI 1.5-12.8) subtypes compared with the luminal A subtype. Overall, 25% of the metastases were basal-like, 32% HER2-enriched, 10% luminal A, 28% luminal B, and 5% normal-like.

Conclusions: We show that tumor characteristics and molecular subtypes of breast cancer metastases significantly influence post-relapse patient survival, emphasizing that molecular investigations at relapse provide prognostic and clinically relevant information. CLINICALTRIALS.GOV: This is the translational part of the Swedish multicenter and randomized trial TEX, clinicaltrials.gov identifier nct01433614 (http://www.clinicaltrials.gov/ct2/show/nct01433614).

Trial registration: ClinicalTrials.gov NCT01433614.

Keywords: TEX randomized trial; biopsy at relapse; breast cancer metastases; gene expression; gene modules; metastasis characteristics.

Figure 1.

Hierarchical clustering of gene expression profiles of breast cancer metastases based on module genes reflecting seven biological processes (A) Positively correlated module genes were selected for visual representation of 120 breast cancer metastatic samples. Arrows indicate patients with multiple metastases. AURKA, proliferation; CASP3, apoptosis; ERBB2, HER2 signaling; ESR1, estrogen signaling; PLAU, tumor invasion/metastasis; STAT1, immune response; VEGF, angiogenesis. (B) Zoom-in of CASP3 and VEGF modules.

Figure 2.

Long- and short-term breast cancer-specific post-relapse survival in relation to gene module groups (A) ESR1 module tertiles long-term (5 years) and short-term (1.5 years) breast cancer-specific survival, respectively. (B) CASP3 module tertiles long- and short-term post-relapse survival, respectively. A P value is based on the log-ranked test, and numbers at risk are shown underneath each graph.

Figure 3.

The PAM50 intrinsic subtypes in relation to long- and short-term post-relapse breast cancer-specific survival. (A) The PAM50 intrinsic subtypes in relation to long-term (5 years) breast cancer-specific survival. (B) The PAM50 intrinsic subtypes in relation to short-term (1.5 years) breast cancer-specific survival. A P value is based on log-ranked test, and numbers at risk are shown underneath each graph.