Tracking the origins and drivers of subclonal metastatic expansion in prostate cancer

Abstract

Tumour heterogeneity in primary prostate cancer is a well-established phenomenon. However, how the subclonal diversity of tumours changes during metastasis and progression to lethality is poorly understood. Here we reveal the precise direction of metastatic spread across four lethal prostate cancer patients using whole-genome and ultra-deep targeted sequencing of longitudinally collected primary and metastatic tumours. We find one case of metastatic spread to the surgical bed causing local recurrence, and another case of cross-metastatic site seeding combining with dynamic remoulding of subclonal mixtures in response to therapy. By ultra-deep sequencing end-stage blood, we detect both metastatic and primary tumour clones, even years after removal of the prostate. Analysis of mutations associated with metastasis reveals an enrichment of TP53 mutations, and additional sequencing of metastases from 19 patients demonstrates that acquisition of TP53 mutations is linked with the expansion of subclones with metastatic potential which we can detect in the blood.

Figure 1. Diagrams of patient sampling and patterns of metastasis for four patients.

In each of the panels, the diagram to the left depicts the timing and direction of metastatic spread for patients 299 (a), 498 (b), 177 (c), 001 (d). For patients 299 (a) and 498 (b), the multiple regions of the primary tumour that were sampled are indicated in the 3D models of the prostate reconstructed from prostate cross-sections. In the centre of each panel is an evolutionary tree depicting the distinct clones identified during the evolution of the tumour. The branch length is approximately proportional to the number of structural variations and SNVs. The matrix plots at the right of each panel represent the percentage of each clone in a given sample. The plot below this represents the disease progression for each patient measured by levels of prostate-specific antigen (PSA) along with an indication of when tumour or blood specimens were sampled and information on treatment phases.

Figure 2. Evolution of mutational signatures and driver mutations.

The trees in this diagram depict the genomic evolution of the tumours for patient (a) 299, (b) 498, (c) 177 and (d) 001. The branch lengths are approximately proportional to the number of structural variations and single-nuclotide variations. Dashed branches occur when the number of mutations could not be estimated (no WGS performed on the clone depicted in the branch). Branches are colour coded—black representing trunk (clonal) mutations, green representing the branch leading to the bulk primary tumour and red representing the branches leading to metastasis. The mutational signatures detected across the mutations in each branch are indicated via the pie charts. Signatures 1A (purple), 5 (aqua), 8 (cream), 6 (green, MSI), 20 (orange, MSI), 26 (yellow, MSI), 2 (blue, APOBEC), 3 (pink, BRCA). Chromoplexy chains are indicated via circles and crosses and mutations in known cancer drivers are listed.

Figure 3. Mutations in known cancer drivers.

The matrix indicates mutations identified in known cancer drivers for the primary tumours from four patients (left) and the metastases for seven patients (right).

Figure 4. TP53 mutations identified via TAm-Seq.

(a) Pie charts representing the number of patients with detected TP53 mutations across the metastatic and localized cohorts. (b) A schematic indicating the presence of TP53 mutations and their allele frequency for all patients in the metastatic cohort that had matched primary and metastatic samples. Surg bed, surgical bed.