5-Hydroxymethylcytosine signatures in cell-free DNA provide information about tumor types and stages

Abstract

5-Hydroxymethylcytosine (5hmC) is an important mammalian DNA epigenetic modification that has been linked to gene regulation and cancer pathogenesis. Here we explored the diagnostic potential of 5hmC in circulating cell-free DNA (cfDNA) using a sensitive chemical labeling-based low-input shotgun sequencing approach. We sequenced cell-free 5hmC from 49 patients of seven different cancer types and found distinct features that could be used to predict cancer types and stages with high accuracy. Specifically, we discovered that lung cancer leads to a progressive global loss of 5hmC in cfDNA, whereas hepatocellular carcinoma and pancreatic cancer lead to disease-specific changes in the cell-free hydroxymethylome. Our proof-of-principle results suggest that cell-free 5hmC signatures may potentially be used not only to identify cancer types but also to track tumor stage in some cancers.

Figure 1

Sequencing of 5hmC in cfDNA. (A) General procedure of cell-free 5hmC sequencing. cfDNA is ligated with Illumina adapter and labeled with biotin on 5hmC for pull-down with streptavidin beads. The final library is completed by directly PCR from streptavidin beads. (B) Percentage of reads mapped to spike-in DNA in the sequencing libraries. Error bars indicate SD. (C) Metagene profiles of log₂ fold change of cell-free 5hmC to input cfDNA ratio in genes ranked according to their expression in cell-free RNA-Seq.

Figure 2

Lung cancer leads to progressive loss of 5hmC enrichment in cfDNA. (A) Genome browser view of the cell-free 5hmC distribution in a 10 mb region in chromosome 6. The overlapping tracks of healthy, non-metastatic lung cancer, metastatic lung cancer and input cfDNA samples are shown in line plot. (B) Heatmap of 1 159 metastatic lung cancer differential genes in healthy, lung cancer samples and the unenriched input cfDNA. Hierarchical clustering was performed across genes and samples. (C) Boxplot of number of hMRs (normalized to 1 million reads) identified in each group. (D) Boxplots of CCNY and PDIA6 5hmC FPKM in lung cancer and other cfDNA samples. ^*P < 0.05, ^**P < 0.01, ^***P < 0.001, ^****P < 1e-5, Welch t-test.

Figure 3

Cell-free 5hmC for monitoring HCC progression and treatment. (A) tSNE plot of 5hmC FPKM from healthy, HBV and HCC samples. (B) Heatmap of 1 006 HCC differential genes in healthy, HBV and HCC samples. Hierarchical clustering was performed across genes and samples. (C, D) Boxplots of AHSG (C) and TET2 (D) 5hmC FPKM in HBV, HCC (pre-op), HCC post-op, HCC recurrence and other cfDNA samples. ^*P < 0.05, ^**P < 1e-4, ^***P < 1e-5, Welch t-test. (E) tSNE plot of 5hmC FPKM from healthy, HCC pre-op, HCC post-op and HCC recurrence samples.

Figure 4

Cancer type and stage prediction with cell-free 5hmC. (A) tSNE plot of 5hmC FPKM in cfDNA from healthy and various cancer samples. (B) The actual and predicted classification by leave-one-out cross-validation using Mclust (MC) and Random Forest (RF) algorithm, based on two feature sets (gene body and DhMR). (C) The Cohen's kappa coefficient for measuring inter-classifier agreement (GB for gene body). The error bar indicates 95% confidence interval of the Cohen's kappa estimate.