Genomic analyses of germline and somatic variation in high-grade serous ovarian cancer

Abstract

Background: High-grade serous ovarian cancers (HGSCs) display a high degree of complex genetic alterations. In this study, we identified germline and somatic genetic alterations in HGSC and their association with relapse-free and overall survival. Using a targeted capture of 557 genes involved in DNA damage response and PI3K/AKT/mTOR pathways, we conducted next-generation sequencing of DNA from matched blood and tumor tissue from 71 HGSC participants. In addition, we performed the OncoScan assay on tumor DNA from 61 participants to examine somatic copy number alterations (SCNA).

Results: Approximately one-third of tumors had loss-of-function (LOF) germline (18/71, 25.4%) or somatic (7/71, 9.9%) variants in the DNA homologous recombination repair pathway genes BRCA1, BRCA2, CHEK2, MRE11A, BLM, and PALB2. LOF germline variants also were identified in other Fanconi anemia genes and in MAPK and PI3K/AKT/mTOR pathway genes. Most tumors harbored somatic TP53 variants (65/71, 91.5%). Using the OncoScan assay on tumor DNA from 61 participants, we identified focal homozygous deletions in BRCA1, BRCA2, MAP2K4, PTEN, RB1, SLX4, STK11, CREBBP, and NF1. In total, 38% (27/71) of HGSC patients harbored pathogenic variants in DNA homologous recombination repair genes. For patients with multiple tissues from the primary debulking or from multiple surgeries, the somatic mutations were maintained with few newly acquired point mutations suggesting that tumor evolution was not through somatic mutations. There was a significant association of LOF variants in homologous recombination repair pathway genes and high-amplitude somatic copy number alterations. Using GISTIC analysis, we identified NOTCH3, ZNF536, and PIK3R2 in these regions that were significantly associated with an increase in cancer recurrence and a reduction in overall survival.

Conclusions: From 71 patients with HGCS, we performed targeted germline and tumor sequencing and provided a comprehensive analysis of these 557 genes. We identified germline and somatic genetic alterations including somatic copy number alterations and analyzed their associations with relapse-free and overall survival. This single-site long-term follow-up study provides additional information on genetic alterations related to occurrence and outcome of HGSC. Our findings suggest that targeted treatments based on both variant and SCNA profile potentially could improve relapse-free and overall survival.

Keywords: Germline mutations; High-grade serous ovarian cancer; Homologous recombination repair; Somatic mutations; Somatic copy number alterations.

Fig. 1

Oncoplot of LOF germline mutations and non-silent somatic mutations. Only genes with variants in at least 3% of patients are displayed. OS = overall survival. RFS = relapse-free survival

Fig. 2

Overall frequency of SCNAs in 61 primary HGSC tumors. From Nexus Copy Number v. 10, red indicates regions of loss, blue indicates regions of gain, and dark blue indicates regions of high-copy gain

Fig. 3

Significantly amplified (panel A) or deleted (panel B) regions of genome. GISTIC analysis was performed to identify significant recurrent focal SCNAs in 61 tumor samples. Genomic positions of SCNA regions are oriented vertically. GISTIC q value and G scores are shown at the bottom and top, respectively. The green line marks GISTIC q value of 0.05. Potential candidate or common cancer genes for each SCNA region are included in the parenthesis next to each SCNA region

Fig. 4

Unsupervised hierarchical clustering of 61 primary HGSC samples using Oncoscan data from 37 SCNAs. Changes in copy number for 37 SCNAs with GISTIC residual q value < 0.05 were used to perform unsupervised hierarchical clustering of 61 primary HGSCs samples. Each column represents a tumor sample and rows represent the 37 SCNAs. As shown in the color key, genomic regions of gain are represented in red and regions of loss are represented in blue

Fig. 5

Relapse-free (A) and overall survival analysis (B) of four clusters of patients defined by SCNAs. Kaplan–Meier analysis was used to evaluate the difference in survival for COH patients in the four clusters of the unsupervised hierarchical tree in Fig. 4

Fig. 6

Relapse-free and overall survival related to high-amplitude SCNAs in NOTCH3, ZNF536, and PIK3R2. Compared to patients not carrying high copy number gains in NOTCH3, ZNF536, and PIK3R2, patients from both COH (panels A and B) and TCGA (panels C and D) carrying high copy gains in at least one of the three genes showed significantly worse relapse-free survival (panel A and C) and overall survival (panel B and D), respectively