Evaluation of Commercial Circulating Tumor DNA Test in Metastatic Prostate Cancer

Abstract

Purpose: Circulating tumor DNA (ctDNA) sequencing provides a minimally invasive method for tumor molecular stratification. Commercial ctDNA sequencing is increasingly used in the clinic, but its accuracy in metastatic prostate cancer is untested. We compared the commercial Guardant360 ctDNA test against an academic sequencing approach for profiling metastatic prostate cancer.

Patients and methods: Plasma cell-free DNA was collected between September 2016 and April 2018 from 24 patients with clinically progressive metastatic prostate cancer representing a range of clinical scenarios. Each sample was analyzed using Guardant360 and a research panel encompassing 73 prostate cancer genes. Concordance of somatic mutation and copy number calls was evaluated between the two approaches.

Results: Targeted sequencing independently confirmed 94% of somatic mutations identified by Guardant360 at an allele fraction greater than 1%. AR amplifications and mutations were detected with high concordance in 14 patients, with only three discordant subclonal mutations at an allele fraction lower than 0.5%. Many somatic mutations identified by Guardant360 at an allele fraction lower than 1% seemed to represent subclonal passenger events or non-prostate-derived clones. Most of the non-AR gene amplifications reported by Guardant360 represented single copy gains. The research approach detected several clinically relevant DNA repair gene alterations not reported by Guardant360, including four germline truncating BRCA2/ATM mutations, two somatic ATM stop gain mutations, one BRCA2 biallelic deletion, 11 BRCA2 stop gain reversal mutations in a patient treated with olaparib, and a hypermutator phenotype in a patient sample with 42 mutations per megabase.

Conclusion: Guardant360 accurately identifies somatic ctDNA mutations in patients with metastatic prostate cancer, but low allele frequency mutations should be interpreted with caution. Test utility in metastatic prostate cancer is currently limited by the lack of reporting on actionable deletions, rearrangements, and germline mutations.

FIG 1.

Concordance of somatic circulating tumor DNA mutation calls between Guardant360 and the Vancouver panel. Allele fractions of somatic mutations based on the two assays: mutations with allele fraction of (A) 1% or greater and (B) lower than 1%. Known prostate cancer driver mutations are shown in blue; other mutations in red. Bar plot below shows allele fraction in matched WBC samples. Mutations were labeled as subclonal if their allele fraction was less than half the allele fraction expected for truncal mutations (described in Patients and Methods). It is plausible that some mutations labeled as subclonal had a nonprostate origin. (C) Plot showing all mutations (dots) identified by Guardant360 in the cell-free DNA (cfDNA) time points that were also analyzed with the Vancouver panel, grouped by allele fraction. Position along x-axis indicates the highest allele fraction that those mutations reached in other time points analyzed by Guardant360. (D) Bar plot showing the total number of somatic mutations called by the Vancouver panel in 16 cfDNA samples with detectable mutations. Patient 6 displays a hypermutation signature enriched for somatic CG>TG transitions and insertions/deletions, consistent with an underlying mismatch repair defect.

FIG 2.

Genomic changes identified in AR by Guardant360 and the Vancouver panel. (A) Bar plot showing allele fractions of somatic AR hotspot mutations detected by the two assays. AR amplification status is indicated by blue and red tiles in the middle. (B) Structure of two androgen receptor (AR) ligand-binding domain truncating rearrangements identified by the Vancouver panel. The somatic junction sequences detected in cell-free DNA (cfDNA) are shown below. At the top, a diagram of full-length AR protein highlights that exons 4 to 8 code for the ligand-binding domain. DBD, DNA binding domain.

FIG 3.

Homologous recombination repair defects identified by the Vancouver panel. (A) Bar plot showing allele fractions of four germline and four somatic BRCA2 or ATM truncating mutations identified by the Vancouver panel but not reported by Guardant360. Blue and red bars show mutant allele fraction in the cell-free DNA (cfDNA) sample and matched WBC sample, respectively. (B) Scatter plot showing sequencing coverage log ratios (Vancouver panel) for all 69 autosomal genes in cfDNA of patient 12. Horizontal lines indicate expected log ratios for different copy numbers, given his estimated ctDNA fraction of 72%. Green and orange colors indicate copy number gains and losses, respectively. BRCA2 biallelic loss in chromosome 13 (chr13) is indicated with an arrow. (C) Eleven BRCA2 stop gain reversing somatic alterations detected with the Vancouver panel in cfDNA from patient 17 after treatment with poly (ADP-ribose) polymerase inhibitor olaparib. Deletions are shown as orange rectangles, with length (in base pairs [bp]) shown on the left and number of supporting reads on the right. All deletions overlapping the stop gain mutation are multiple of 3 bp in length and therefore remove the stop gain mutation while avoiding frameshift. Stop gain–reversing base substitutions are shown in the embedded table.

FIG 4.

Concordance of gene amplification calls between Guardant360 and the Vancouver panel. (A) Absolute gene copy number (estimated with the Vancouver panel) of AR compared with six other genes. Copy numbers were estimated based on sequencing coverage log ratio and circulating tumor (ctDNA) fraction (described in Patients and Methods) and represent the average gene copy numbers in ctDNA-shedding cancer cells. Circle size represents the estimated ctDNA fraction of a sample. (B) Sequencing coverage log ratios of genes MET, BRAF, CDK6, PIK3CA, MYC, CCND1, and AR, quantified with the Vancouver panel in all 24 cfDNA samples. Bars highlighted in blue indicate that the gene was reported as amplified by Guardant360 in that sample. Numbers above bars indicate the average gene copy numbers in ctDNA-shedding cancer cells that would produce the observed coverage log ratio in the Vancouver panel data, correcting for presence of normal cfDNA (Patients and Methods). Chr, chromosome.