A gene expression signature that predicts the therapeutic response of the basal-like breast cancer to neoadjuvant chemotherapy

Abstract

Several gene expression profiles have been reported to predict breast cancer response to neoadjuvant chemotherapy. These studies often consider breast cancer as a homogeneous entity, although higher rates of pathologic complete response (pCR) are known to occur within the basal-like subclass. We postulated that profiles with higher predictive accuracy could be derived from a subset analysis of basal-like tumors in isolation. Using a previously described "intrinsic" signature to differentiate breast tumor subclasses, we identified 50 basal-like tumors from two independent clinical trials associated with gene expression profile data. 24 tumor data sets were derived from a 119-patient neoadjuvant trial at our institution and an additional 26 tumor data sets were identified from a published data set (Hess et al. J Clin Oncol 24:4236-4244, 2006). The combined 50 basal-like tumors were partitioned to form a 37 sample training set with 13 sequestered for validation. Clinical surveillance occurred for a mean of 26 months. We identified a 23-gene profile which predicted pCR in basal-like breast cancers with 92% predictive accuracy in the sequestered validation data set. Furthermore, distinct cluster of patients with high rates of cancer recurrence was observed based on cluster analysis with the 23-gene signature. Disease-free survival analysis of these three clusters revealed significantly reduced survival in the patients of this high recurrence cluster. We identified a 23-gene signature which predicts response of basal-like breast cancer to neoadjuvant chemotherapy as well as disease-free survival. This signature is independent of tissue collection method and chemotherapeutic regimen.

Fig. 1

Identification of basal-like tumors. Unsupervised hierarchical clustering of samples from WU using the “intrinsic” signature (a) and Hess et al. (b) [4]. The red branch demarcates BL tumors. Blue marks denote positive expression of ER, PR,and HER2. Black marks denote pCR. Probe set numbers differ between the two plots as the result of oligonucleotide platforms. For the analyses, probe sets common to both chips were used. In the right-most branch of (b) (blue), samples had low values and were therefore excluded from the analysis

Fig. 2

Determination of the optimal number of probe sets. The 50 basal-like tumor samples were partitioned in a balanced manner into a 37-sample training group and a 13-sample validation group. A moderated t-statistic ranked the probe sets by their degree of differential expression as related to treatment response. A search using linear discrimination analysis with leave-one-out cross validation found that inclusion of the top 25 probe sets in the discrimination model yielded the optimal and most parsimonious predictive results

Fig. 3

Training and validation heat plots of the 25 probe model. Using linear discrimination analysis, each of the 13 validation samples were compared to the training data and predicted to have had pCR or RD to neoadjuvant therapy. All RD samples were correctly categorized as such, as were five of six pCR samples. Overall accuracy was 92% (95% CI 64–100), with sensitivity of 80% (95% CI 28–99) and specificity of 100% (95% CI 63–100). Hash marks above heat plots mark samples which had pCR to neoadjuvant therapy

Fig. 4

Internal consistency of the expression signature. The expression profiles of the 50 basal-like tumors were clustered using the 23-gene expression signature. The data from Hess et al. are indicated in the recurrence hashes by open boxes; the data from this institution are indicated by closed boxes

Fig. 5

Kaplan–Meier survival analysis. Disease-free survival estimates for the three groups—pCR, RD, and high recurrence—resulting from hierarchical clustering of the 50 basal-like tumors with the 23-gene prediction profile demonstrated a statistically significant difference in survival between the pCR, RD and high recurrence groups (P<0.01). Survival analysis of the pCR and RD groups alone did not achieve statistical significance