Prognostic and predictive value of circulating tumor DNA during neoadjuvant chemotherapy for triple negative breast cancer

Abstract

Response to neoadjuvant chemotherapy (NAC) in triple negative breast cancer (TNBC) is highly prognostic and determines whether adjuvant chemotherapy is needed if residual tumor is found at surgery. To evaluate the predictive and prognostic values of circulating tumor DNA (ctDNA) in this setting, we analyzed tumor and serial bloods from 26 TNBC patients collected prior, during, and after NAC. Individual digital droplet PCR assays were developed for 121 variants (average 5/patient) identified from tumor sequencing, enabling ctDNA detection in 96% of patients at baseline. Mutant allele frequency at baseline was associated with clinical characteristics. Levels drastically fell after one cycle of NAC, especially in patients whose tumors would go on to have a pathological complete response (pCR), but then rose significantly before surgery in patients with significant residual tumor at surgery (p = 0.0001). The detection of ctDNA early during treatment and also late at the end of NAC before surgery was strongly predictive of residual tumor at surgery, but its absence was less predictive of pCR, especially when only TP53 variants are considered. ctDNA detection at the end of neoadjuvant chemotherapy indicated significantly worse relapse-free survival (HR = 0.29 (95% CI 0.08-0.98), p = 0.046), and overall survival (HR = 0.27 95% CI 0.075-0.96), p = 0.043). Hence, individualized multi-variant ctDNA testing during and after NAC prior to surgery has prognostic and predictive value in early TNBC patients.

Figure 1

Neoadjuvant chemotherapy (NAC) and biobanking schedule of the Q-CROC-03 study. An illustration of the schedule of various chemotherapy regimens with the biobanking collection schedule superimposed. Tissue sample collection occurred before the start of NAC at the time of diagnosis (B1), and then either after NAC (B2) and/or at surgery (S3) in the case of non-pCR patients. Up to 5 blood samples were collected: 1 before the start of NAC at baseline (T0), 1 after the 1st cycle of the 1st drug regimen (T1), 1 at mid-treatment or at the switch between the 2 drugs regimen (T2), 1 after the 1st cycle of the 2nd drug regimen (T3), 1 at the end of NAC (T4) before surgery). The different NAC drug regimens were AC + Tax [4 cycles of Doxorubicin (or Epirubicin) with Cyclophosphamide followed by 12 cycles of weekly Paclitaxel, or 3 cycles of 5-Fluorouracil/Epirubicin/Cyclophosphamide followed by 12 cycles of weekly Paclitaxel (or 3 cycles of Docetaxel)]; Tax + AC (12 cycles of weekly Paclitaxel followed by 4 cycles of Doxorubicin (or Epirubicin) with Cyclophosphamide, or 3 cycles of 5-Fluorouracil/Epirubicin/Cyclophosphamide); Tax only (12 cycles of weekly Paclitaxel); or ACTax (3 or 4 cycles of Doxorubicin with Cyclophosphamide + Docetaxel, or 4 cycles of Carboplatin/Paclitaxel).

Figure 2

Detection of Single Nucleotide Variants (SNVs) at baseline (T0). For each patient, the total height of the bar represents total number of variants tested. Shaded (black) area represents the number of detected variants at T0.

Figure 3

Detection of SNVs after 1st cycle of NAC (T1) and at the end of NAC (T4). Total height of bars represents total number of tested variants for each patient. Shaded area of each bar represents the number of detected variants at T1 (A) and at T4 (B) in pCR and non-pCR (RCB > 0) patients. X-axis labels refer to the patient identifier (ID), ® refers to patients with breast cancer relapse.

Figure 4

Change in average Mutated Allele Frequencies (MAF) at different time points. Average and SEM of MAFs at each time point for all variants tested (A) and for the 87 variants detected at baseline time point T0 (B). Average MAFs for all variants tested in patients with pCR (C) and non pCR (D). Only tested variants are considered at each time point and non-detectable values are assigned a “0” value.

Figure 5

Survival Analysis based on ctDNA detection at T1 and T4 time points. Kaplan–Meier curves of relapse-free survival (RFS) (A, C) and overall survival (OS) (B, D) comparing patients for whom we can detect at least 1 SNV at the indicated time point versus the ones for whom we can’t detect any at the same time point. (A, B) represent RFS and OS at T1, respectively; (C, D) represent RFS and OS at T4, respectively. In these analyses, we only considered the 80 variants detected at baseline in 23 patients. p value is calculated from a log-rank.