Robust Detection of DNA Hypermethylation of ZNF154 as a Pan-Cancer Locus with in Silico Modeling for Blood-Based Diagnostic Development

Abstract

Sites that display recurrent, aberrant DNA methylation in cancer represent potential biomarkers for screening and diagnostics. Previously, we identified hypermethylation at the ZNF154 CpG island in 15 solid epithelial tumor types from 13 different organs. In this study, we measure the magnitude and pattern of differential methylation of this region across colon, lung, breast, stomach, and endometrial tumor samples using next-generation bisulfite amplicon sequencing. We found that all tumor types and subtypes are hypermethylated at this locus compared with normal tissue. To evaluate this site as a possible pan-cancer marker, we compare the ability of several sequence analysis methods to distinguish the five tumor types (184 tumor samples) from normal tissue samples (n = 34). The classification performance for the strongest method, measured by the area under (the receiver operating characteristic) curve (AUC), is 0.96, close to a perfect value of 1. Furthermore, in a computational simulation of circulating tumor DNA, we were able to detect limited amounts of tumor DNA diluted with normal DNA: 1% tumor DNA in 99% normal DNA yields AUCs of up to 0.79. Our findings suggest that hypermethylation of the ZNF154 CpG island is a relevant biomarker for identifying solid tumor DNA and may have utility as a generalizable biomarker for circulating tumor DNA.

Figure 1

DNA methylation profile around the transcription start site (TSS) of ZNF154. A and B: A smoothed CpG methylation (mCpG) profile in a colon tumor sample (gray line) and adjacent normal tissue (dashed black line), obtained from whole-genome bisulfite sequencing data (A). The rug plot illustrated along the bottom of the panel marks all CpG positions (A). The TSS (vertical line, A) and the amplicon interval (gray rectangle, A) correspond to the region of the UCSC Human Genome Browser (black rectangle, B). C: Genomic positions of 20 CpGs in the 302-bp ZNF154 amplicon: enlarged view of the TSS region and partial overlap with the annotated CpG island.

Figure 2

Reproducibility data of amplicon sequencing products from bisulfite-converted cell line DNA. Results are shown for GM12878 (A) and K562 (B) cell lines. Each line represents a different replicate. Gray triangles represent the percentage of CpG methylation (mCpG) at four CpG positions present on the Illumina methylation array data, generated from the same cell types by ENCODE.

Figure 3

Comparison of CpG methylation (mCpG) levels in tumor and normal endometrial samples, as determined by amplicon sequencing. A: Box plots of percentage of mCpG at each CpG position within the amplicon in normal (empty black) and tumor (shaded gray) samples. Samples contained a minimum of 1000 aligned reads. B: Scatterplot of tumor (T) methylation levels measured with Illumina methylation arrays at probe cg21790626 (x axis) versus amplicon sequencing at the corresponding genomic position, chr19:58220494 (y axis), in the same samples. C: Scatterplot of the mean percentage of methylation across all amplicon CpG positions for each normal (N) sample, plotted against duplicate values.

Figure 4

Distribution of individual CpG methylation (mCpG) levels in lung, stomach, colon, and breast tumor and normal tissue samples. A: Box plots of the mean percentage of methylation, determined from bisulfite sequencing, at each CpG position within the amplicon in normal (empty black) and tumor (shaded gray) samples. Samples contained ≥1000 aligned reads. B: Scatterplots of the mean percentage of methylation across all amplicon CpG positions for tumor (T) and normal (N) samples are plotted against duplicate values, when both duplicates have at least 1000 aligned reads.

Figure 5

Methylation patterns of aligned reads in tumor versus normal endometrial, colon, stomach, lung, and breast tissue samples. A: Frequency of the 45 most repeated patterns. Unmethylated cytosines converted to thymines appear as (.), whereas methylated cytosines that were protected from conversion appear as (c). Each symbol represents the status of one of the 20 CpG cytosines in the amplicon. B: Hierarchical clustering of the samples based on these 45 patterns. Heat map coloring reflects the relative abundance of a given pattern across samples—going from white to black in each row or pattern would correspond to moving from the bottom upward in the merged tumor-and-normal box plot for that same pattern, similar to A.

Figure 6

Levels of CpG methylation (mCpG) of aligned reads in tumor versus normal endometrial, colon, stomach, lung, and breast tissue samples. Frequency of aligned reads as a function of the number of mCpGs, from 0 to 20, in normal (A) and tumor (B) samples. Different patterns with identical numbers of mCpGs have been grouped together.

Figure 7

Distinguishing tumor samples from normal tissue based on DNA methylation in endometrial, colon, stomach, lung, and breast samples. Cumulative distribution functions (CDFs) (top panel) and receiver operating characteristic (ROC) curves (bottom panel) are shown. CDFs of normal and tumor samples are in black and gray, respectively, plotted against a logarithmic x axis. ROC curves reveal the point of the maximal sum of sensitivity and specificity (gray dot). Each column contains CDFs and ROC curves corresponding to a different sample measurement, scaled to vary between 0 and 1. A: Mean fraction (percentage per 100) of methylated CpGs per sample, m. B–D: The results for the x, y, and z ratios, respectively, defined in the text. FPR, false-positive rate (ie, 1 − specificity); TPR, true-positive rate (ie, sensitivity).

Figure 8

Performance of the four selected predictors (m, x, y, and z; defined in text) in distinguishing endometrial, colon, stomach, lung, and breast tumors from normal samples at different simulated dilution levels. Area under the receiver operating characteristic curve (AUC) is plotted as a function of simulated tumor DNA dilution. The leftmost AUC values (when fraction of normal DNA is 0) correspond to the data presented in Figure 7.

Figure 9

Simulation: distinguishing endometrial, colon, stomach, lung, and breast tumors from normal samples when tumor signal is diluted. The graphs are arranged as in Figure 7. Tumor signal characteristics (gray CDFs) were simulated by mixing 1% tumor signal with 99% randomly picked normal signal. Normal samples are the same as in Figure 7 (black CDFs). A: Diluted tumors were practically indistinguishable from normal samples when relying on m, with an area under the receiver operating characteristic curve (AUC) of 0.54. B–D: By contrast, the capacity for classification persisted over dilutions for the other signal measures, x, y, and z (AUCs of 0.73, 0.75, and 0.63, from left to right). As an example of the use of the convex hull (gray off-diagonal line), C shows an increase in the AUC from 0.75 to 0.79. CDF, cumulative distribution function; FPR, false-positive rate (ie, 1 − specificity); TPR, true-positive rate (ie, sensitivity).