A novel extrachromosomal circular DNA related genes signature for overall survival prediction in patients with ovarian cancer

Abstract

Objective: Ovarian cancer (OV) has a high mortality rate all over the world, and extrachromosomal circular DNA (eccDNA) plays a key role in carcinogenesis. We wish to study more about the molecular structure of eccDNA in the UACC-1598-4 cell line and how its genes are associated with ovarian cancer prognosis.

Methods: We sequenced and annotated the eccDNA by Circle_seq of the OV cell line UACC-1598-4. To acquire the amplified genes of OV on eccDNA, the annotated eccDNA genes were intersected with the overexpression genes of OV in TCGA. Univariate Cox regression was used to find the genes on eccDNA that were linked to OV prognosis. The least absolute shrinkage and selection operator (LASSO) and cox regression models were used to create the OV prognostic model, as well as the receiver operating characteristic curve (ROC) curve and nomogram of the prediction model. By applying the median value of the risk score, the samples were separated into high-risk and low-risk groups, and the differences in immune infiltration between the two groups were examined using ssGSEA.

Results: EccDNA in UACC-1598-4 has a length of 0-2000 bp, and some of them include the whole genes or gene fragments. These eccDNA originated from various parts of chromosomes, especially enriched in repeatmasker, introns, and coding regions. They were annotated with 2188 genes by Circle_seq. Notably, the TCGA database revealed that a total of 198 of these eccDNA genes were overexpressed in OV (p < 0.05). They were mostly enriched in pathways associated with cell adhesion, ECM receptors, and actin cytoskeleton. Univariate Cox analysis showed 13 genes associated with OV prognosis. LASSO and Cox regression analysis were used to create a risk model based on remained 9 genes. In both the training (TCGA database) and validation (International Cancer Genome Consortium, ICGC) cohorts, a 9-gene signature could successfully discriminate high-risk individuals (all p < 0.01). Immune infiltration differed significantly between the high-risk and low-risk groups. The model's area under the ROC curve was 0.67, and a nomograph was created to assist clinician.

Conclusion: EccDNA is found in UACC-1598-4, and part of its genes linked to OV prognosis. Patients with OV may be efficiently evaluated using a prognostic model based on eccDNA genes, including SLC7A1, NTN1, ADORA1, PADI2, SULT2B1, LINC00665, CILP2, EFNA5, TOMM.

Keywords: Immune infiltration; Ovarian cancer; Prognostic model; TCGA; eccDNA.

Fig. 1

Flow chart of data collection and analysis

Fig. 2

Landscape of overall analysis characteristics of eccDNA. A Distribution landscape of eccDNA in chromosome source. B Length distribution of eccDNA shows peaks at 200 -600 bases. C The sites in the genome that give rise to small eccDNA are enriched relative to random expectation in genic sites, The top three are RepeatMasker, ExonPlus, Introns. D The significantly amplified genes on OC were obtained by GEPIA2. E Intersection of eccDNA gene and OV amplified gene

Fig. 3

Protein interaction (PPI) analysis and enrichment of eccDNA related OV amplified genes. A The string database shows 198 protein interactions (PPI). B GO database pathway enrichment analysis results. C KEGG database pathway enrichment analysis results

Fig. 4

Univariate Cox regression analysis of amplified genes in OV associated with prognosis. A Hazard ratio and P-value of constituents involved in Univariate Cox regression and some parameters of the eccDNA signature. The left side of the dotted line represents HR < 1, which is a protective factor, and the right side represents HR > 1, which is a risk factor. B Correlation matrix of hub genes implicated in eccDNA

Fig. 5

Further screen genes by LASSO and correlation study. A LASSO coefficient profiles of the 13 genes in TCGA-OV. Different colors represent different variables (genes). B λ selection diagram. The two dotted lines indicated two particular values of λ. The left side was λmin and the right side was λ1se. The λmin was selected to build the model for accuracy in our study. C Genetic alteration of the 9 genes in the TCGA-OV cohort (cBioPortal). D The prognosis of 9 genes obtained from GEPIA2 database. E Correlation analysis among 9 genes by spearman correlation

Fig. 6

Identification of a risk signature comprising of 9 eccDNA genes in OV. A Distribution of patients in the TCGA cohort based on the median risk score. B The survival status for each patient (low-risk population: on the left side of the dotted line; high-risk population: on the right side of the dotted line). C Kaplan–Meier survival curve between high and low-risk groups. Red lines represent high risk patients, while blue lines represent low risk patients. D The heatmap of the expression profiles of 13 prognostic related genes signature. E Representative diagram of mutation landscape from the high-risk OV cohort. F Representative diagram of mutation landscape from the low-risk OV cohort

Fig. 7

Comparison of immune infiltration and immune checkpoint between high and low-risk group. A The expression levels of 28 immunity cells were analyzed by ssGSEA. B Among the 29 immune checkpoint genes, 6 genes were differentially expressed between high and low risk group, P values were showed as: *P < 0.05, **P < 0.01, ***P < 0.001

Fig. 8

ROC evaluating diagnostic effectiveness and building a predictive nomogram. A ROC curve was plotted for 1-, 3- and 5-years overall survival in the TCGA group. B Nomogram to predict the 1-years, 3-years and 5-years overall survival of OV patients. C Calibration curve for the overall survival nomogram model in test group. D ROC curve was plotted for 1-, 3- and 5-years overall survival in the ICGC group. E Kaplan–Meier survival curve results in ICGC groups