5-Hydroxymethylcytosine signatures in circulating cell-free DNA as diagnostic biomarkers for human cancers

Abstract

DNA modifications such as 5-methylcytosine (5mC) and 5-hydroxymethylcytosine (5hmC) are epigenetic marks known to affect global gene expression in mammals. Given their prevalence in the human genome, close correlation with gene expression and high chemical stability, these DNA epigenetic marks could serve as ideal biomarkers for cancer diagnosis. Taking advantage of a highly sensitive and selective chemical labeling technology, we report here the genome-wide profiling of 5hmC in circulating cell-free DNA (cfDNA) and in genomic DNA (gDNA) of paired tumor and adjacent tissues collected from a cohort of 260 patients recently diagnosed with colorectal, gastric, pancreatic, liver or thyroid cancer and normal tissues from 90 healthy individuals. 5hmC was mainly distributed in transcriptionally active regions coincident with open chromatin and permissive histone modifications. Robust cancer-associated 5hmC signatures were identified in cfDNA that were characteristic for specific cancer types. 5hmC-based biomarkers of circulating cfDNA were highly predictive of colorectal and gastric cancers and were superior to conventional biomarkers and comparable to 5hmC biomarkers from tissue biopsies. Thus, this new strategy could lead to the development of effective, minimally invasive methods for diagnosis and prognosis of cancer from the analyses of blood samples.

Figure 1

Detecting 5hmC biomarkers in cfDNA of human cancers. (A) Workflow of 5hmC-Seal profiling from cfDNA is shown. Purified cfDNA is ligated with standard sequencing adaptors. 5hmC-containing cfDNA fragments are selectively labeled with a biotin group. The biotin-labeled fragments are captured on the avidin beads, followed by PCR amplification and next-generation sequencing (NGS). (B) Cancers of different tissue origins (e.g., lung, colon, stomach, liver, ovary, pancreas) may release cfDNA decorated with distinct 5hmC modification patterns. Unique 5hmC signatures specific for different cancer types could be detected as biomarkers for diagnosis and prognosis. As shown in this panel, a unique 5hmC signature may correspond to each cancer type. (C) Schematic overview of sample collection, data generation and analysis is shown.

Figure 2

Differential 5hmC loci associated with cancer. (A) Average 5hmC levels in gene bodies in healthy controls (health) and cancer patients (colon, stomach), estimated for plasma cfDNA (plasma cf), white blood cell genomic DNA (WBC) and tissue genomic DNA (tumor, adjacent), were clustered by correlation distance. (B) Counts per million reads at SULF1 gene (plus ± 20 kb region) in plasma cfDNA of the 15 healthy controls and 18 colorectal cancer patients. The moving averages at 0.01 smoother span are shown. (C) The distribution of colorectal cancer-associated 5hmC loci detected at 5% false discovery rate in plasma cfDNA. Each vertical bar denotes a differential locus (a histone modification peak or a gene body). The color key indicates the relative magnitude of log₂ fold change in cancer patients vs controls. (D) Pearson's correlation of log₂ fold changes between all analyzed genes and their neighboring genes (points) was plotted against the null distribution of correlation with their first neighboring genes (curves), generated by shuffling gene positions for 1 000 times. Blue and orange points denote data from plasma cfDNA and tissue gDNA, respectively, for colorectal cancer. In C and D, chromosome 1 is shown as an example. (E) Cancer plasma cfDNA and tumor gDNA exhibit correlation in average 5hmC density (library size and feature length normalized log₂ counts, black bars). However, there is no correlation in the log₂ fold changes between differential 5hmC loci detected (between cancer vs health (plasma cfDNA)) and tumor vs adjacent tissue (tissue gDNA), (orange bars). (F) Genes with a 5hmC level elevated in cancer plasma cfDNA (cancer cf) are enriched in genes with high 5hmC level in tissue gDNA (tumor high, adjacent high). To estimate fold enrichment, the 1st, 5th and 10th percentile genes in descending order of the log₂ fold change in cancer cfDNA were compared against the corresponding percentile genes in descending order of the average 5hmC level in tissue gDNA. Similarly, genes with a 5hmC level decreased in cancer plasma, and cfDNA are enriched in genes with low 5hmC levels in tissue gDNA (tumor low, adjacent low). In contrast, differentially marked genes detected in tumor gDNA (tumor) show no such enrichment pattern. Dashed line denotes no enrichment.

Figure 3

Performance of 5hmC biomarkers for colorectal cancer. (A) The heat map shows clustering of cfDNA samples from both the discovery and validation batches, using the 989 differential gene bodies detected in plasma cfDNA from the discovery batch. (B) Correlation of 5hmC changes in cancer between the discovery and validation batches is higher in plasma cfDNA (cancer patients vs healthy individuals) than in tissue gDNA (tumors vs adjacent tissues), especially for 5hmC in gene bodies. (C, D) Classification of two independent validation batches using 5hmC classifier derived from plasma cfDNA from the discovery batch. (E) Classification of an independent set of colon cancer tumor tissues using 5hmC biomarkers detected from the discovery batch of tissue samples (tumors vs adjacent tissues). (F) The predicted cancer probability (i.e., score) based on 5hmC classifier from plasma cfDNA shows a significant trend associated with clinical stage. Patients after surgery show predicted scores undistinguishable from healthy individuals. (G) The 5hmC cfDNA classifier for colorectal cancer is disease- and potentially cancer type-specific, showing decreasing predicted probability in cfDNA from stomach, liver, pancreatic and thyroid cancer patients. AUC, area under curve; CAC, cancer patients; HEA, healthy controls; NOR, patients with benign tumor.

Figure 4

Performance of 5hmC biomarkers for gastric cancer. (A) The heat map shows clustering of cfDNA samples from both the discovery and validation batches, using the 1 431 differential gene bodies detected in plasma cfDNA from the discovery batch. (B) Correlation of 5hmC changes in cancer between the discovery and validation batches is higher in plasma cfDNA (cancer patients vs healthy individuals) than in tumor gDNA (tumors vs adjacent tissues), especially for 5hmC in gene bodies. (C, D) Classifying two independent validation batches using 5hmC classifier derived from plasma cfDNA from the discovery batch. (E) Classifying an independent set of gastric cancer tumor tissues using 5hmC biomarkers detected from the discovery batch of tissue samples (tumors vs adjacent tissues). (F) The predicted cancer probability (i.e., score) based on the 5hmC classifier from plasma cfDNA shows a trend associated with clinical stage. The one patient after surgery shows a predicted probability undistinguishable from healthy individuals. (G) The 5hmC cfDNA classifier for gastric cancer is disease- and potentially cancer type-specific, showing decreasing predicted probability in cfDNA from colorectal, liver, pancreatic and thyroid cancer patients.

Figure 5

The origin of cancer-associated 5hmC changes observed in plasma cfDNA. (A) The proportions of human reads in plasma cfDNA captured with 5hmC-Seal are shown for PDX mice grafted with tumor from three gastric cancer patients (stomach_1-3), three colorectal cancer patients (colon_1-3) and for PDX mice without graft (control_1-3). Vertical bars represent s.d. estimated from three replicate PDX mice for each patient. The PDX mice grafted with gastric tumor had greater number of passages (6-10) than those grafted with colorectal tumor (2-5). (B) The correlation of the 5hmC profile between tumor-derived, PDX plasma cfDNA and donor tumor gDNA depends on the number of passages of the PDX mouse. The size of the points is proportional to the size of grafted tumor, and the density of color denotes the growth rate of the grafted tumor. (C) Using the correlation distance of the top five genes that had the greatest 5hmC level in PDX plasma cfDNA, donor tumor gDNA and PDX plasma cfDNA from the same individual patient were clustered together. (D) Genes with elevated 5hmC level in cancer patient plasma cfDNA are enriched in genes with high 5hmC levels in PDX plasma cfDNA. To estimate fold enrichment, the fifth percentile genes in descending order of the log₂ fold change in patient cfDNA were compared against the corresponding fifth percentile genes in descending order of the 5hmC level in PDX mice (stomach pdx high, colon pdx high). Similarly, genes with decreased 5hmC level in cancer patient plasma cfDNA are enriched in genes with low 5hmC levels in PDX plasma cfDNA (stomach pdx low, colon pdx low). Dashed line denotes no enrichment.