Reliable tumor detection by whole-genome methylation sequencing of cell-free DNA in cerebrospinal fluid of pediatric medulloblastoma

Abstract

Medulloblastoma (MB), the most common form of pediatric brain malignancy, has a low frequency of oncogenic mutations but pronouncedly abnormal DNA methylation changes. Epigenetic analysis of circulating cell-free tumor DNA (ctDNA) by liquid biopsy offers an approach for real-time monitoring of tumor status without tumor dissection. In this study, we identified 6598 differentially methylated CpGs in both MB tumors and the ctDNA isolated from matched cerebrospinal fluid (CSF) compared with normal cerebellum, which could be used to detect MB tumor occurrence and determine its subtype. Furthermore, DNA methylation changes in serial CSF samples could be used to monitor the treatment response and tumor recurrence. Integrating our data with large public datasets, we identified reliable MB DNA methylation signatures in ctDNA that have potential diagnostic and prognostic values. Our study sets the stage for exploiting epigenetic markers in CSF to improve the clinical management of patients with MB.

Fig. 1. Cytosine modifications in CSF ctDNA are highly concordant with those detected in MB tumors in situ.

(A) Schematic of the experimental design. Normal cerebellum tissue (n = 2), non–MB CSF samples (n = 6, four patients with hydrocephalus without symptoms of other diseases and two patients with acute lymphoblastic leukemia without brain metastasis), matched MB tumor tissue, and CSF sample pairs from patients with MB SHH (patients 1, 2, and 3) and CSF samples from patient 4 (WNT) were used in this study. (B) Pearson correlation analysis of the DNA methylation status of common CpG sites (covered at least 10 times) and common hydroxymethylated regions shared between CSF ctDNA samples and their matched MB tumors. (C) Pearson correlation analysis of the DNA methylation status of the CpG sites that are common between indicated CSF ctDNA samples and published MB tumor samples (n = 34). The minimal coverage of selected CpG sites was 5×. (D) Pearson correlation analysis of the DNA methylation and hydroxymethylation at the indicated regulatory elements between CSF ctDNA and matched MB tumors. (E) Scatter plots showing the correlation of DNA methylation levels between CSF ctDNA and matched MB tumors within CpG island (CGI) regions (CpGs covered at least 10 times).

Fig. 2. DNA modification changes in both MB tumors and MB CSF compared to normal cerebellum.

(A) Top: Venn diagrams of the number of hyper-DMRs (left) or hypo-DMRs (right) identified between cerebellum and MB tumor and between cerebellum and MB CSF. Bottom: Lists of transcription factor (TF) motifs that were enriched within shared hyper-DMRs (left) or hypo-DMRs (right). (B) The same analysis as described in (A) but for hydroxymethylation. (C and D) Scatter plots showing the correlation of differences in 5mC (C) or 5hmC (D) between the normal cerebellum and MB tumor and between cerebellum and MB CSF ctDNA. (E) The genome distributions of shared hyper-DMRs (red) and hypo-DMRs (blue) identified in (A) (left), shared hyper-DHMRs (red) and hypo-DHMRs (blue) identified in (B) (right). The y axes report the percentages of the DMRs or DHMRs relative to all DMRs or DHMRs, respectively. LINE, long interspersed nuclear element; SINE, short interspersed nuclear elements; LTR, long terminal repeat. (F) Multidimensional scaling (MDS) analysis of the 5hmC signals in the shared DHMRs identified in (B). (G) University of California, Santa Cruz (UCSC) genome browser view of 5hmC enrichment at the PRDM6 locus (chr5: 122,433,516 to 122,435,744) in cerebellum, MB tumor, and MB CSF ctDNA. The highlighted region exhibits increased 5hmC in both MB tumor and MB CSF samples.

Fig. 3. MB DNA methylation signatures in CSF ctDNA for cancer diagnosis.

(A) Heatmap representation of DNA methylation levels at MB CSF signature CpGs (n = 6598). (B) MDS analysis of the DNA methylation levels at MB CSF signature CpGs detected in cerebellum (dark green), MB tumor (red), MB CSF (orange), and nontumor CSF (light green). (C) UCSC genome browser view of DNA methylation and hydroxymethylation levels at the NEUROD1 locus (chr2: 182,539,000 to 182,550,000) in the indicated samples. (D) t-distributed stochastic neighbor embedding (t-SNE) analysis of the DNA methylation levels of the common CpG sites between MB CSF signature CpGs and the published DNA methylation array data from approximately 600 patients with MB (8). WNT, purple; SHH, maroon; group 3 (G3), dark blue; group 4 (G4), light blue. (E) Pearson correlation analysis of DNA methylation status of the common CpGs between MB CSF signature CpGs and subtype-specific CpGs identified from public data (20) (n = 1047 CpGs). Top: The methylation status in MB tumor samples. Bottom: the methylation status in MB CSF samples. (F) Heatmap representation of the selected 49 subtype-specific CpGs (of 1047 CpG sites), which exhibited concordant DNA methylation status between the three SHH-subtype MB CSF and MB tumor samples (this study) and public MB tumors data.

Fig. 4. Dynamic DNA methylation changes of MB CSF signature CpGs in CSF ctDNA along treatment.

(A) Top: The timeline for serial CSF collections and CSF cytology results in patient 2. Arrows indicate the time points of CSF sample collection (red arrows, CSF samples used in this study). Bottom: Heatmap representation of DNA methylation status of MB CSF (SHH) signature CpGs in normal cerebellum tissues, MB tumor tissue, and CSF at diagnosis, during treatment. (B) Top: The timeline for serial CSF collections and CSF cytology results in patient 3. Bottom: Heatmap representation of DNA methylation levels of MB CSF (SHH) signature CpGs in normal cerebellum tissues, MB tumor tissue, and CSF at diagnosis and during treatment. (C) The Venn diagram representation of overlapped CpGs between clusters 5 and 10 (patient 2) and clusters 2 and 5 (patient 3) and between cluster 4 (patient 2) and clusters 4, 9, 10, and 11 (patient 3). (D) Top: The timeline for serial CSF collections and CSF cytology results in patient 4. Bottom: Heatmap representation of DNA methylation status of MB CSF (WNT) signature CpGs in normal cerebellum tissues, MB tumor tissue from patient 4, published MB (WNT) tumors, and CSF from patient 4 at diagnosis and after treatment.

Fig. 5. Exploring the prognostic value of MB DNA methylation signatures in CSF ctDNA for clinical outcome.

(A) UCSC genome browser view showing DNA methylation and hydroxymethylation levels of CpGs (chr9: 97,786,878 to 97,786,879) located within the intron of C9orf3 for normal cerebellum, nontumor CSF, MB CSF ctDNA, and MB tumors, including data from this study and 34 public WGBS datasets (12). (B and C) Box plots representing the DNA methylation levels at the single CpG site highlighted in Fig. 4A, using previously published DNA methylation array data [B (8) and C (41)]. (D) Kaplan-Meier survival curves of patients with MB separated according to a methylation ratio cutoff value of 80% at the single CpG site highlighted in Fig. 4A. (E and F) Kalan-Meier curves and log-rank tests were used to visualize and compare the OS between low-risk and high-risk groups in the training cohort (n = 438 patients) (E) and the validation cohort (n = 189) (F) using the methylation ratios at the three CpGs in the model.