Epigenetically reprogrammed methylation landscape drives the DNA self-assembly and serves as a universal cancer biomarker

Abstract

Epigenetic reprogramming in cancer genomes creates a distinct methylation landscape encompassing clustered methylation at regulatory regions separated by large intergenic tracks of hypomethylated regions. This methylation landscape that we referred to as Methylscape is displayed by most cancer types, thus may serve as a universal cancer biomarker. To-date most research has focused on the biological consequences of DNA Methylscape changes whereas its impact on DNA physicochemical properties remains unexplored. Herein, we examine the effect of levels and genomic distribution of methylcytosines on the physicochemical properties of DNA to detect the Methylscape biomarker. We find that DNA polymeric behaviour is strongly affected by differential patterning of methylcytosine, leading to fundamental differences in DNA solvation and DNA-gold affinity between cancerous and normal genomes. We exploit these Methylscape differences to develop simple, highly sensitive and selective electrochemical or colorimetric one-step assays for the detection of cancer. These assays are quick, i.e., analysis time ≤10 minutes, and require minimal sample preparation and small DNA input.

Fig. 1

Epigenetic reprogramming modulates the physicochemical properties of genomic DNA. a Scheme: DNA from normal cells contain large levels of dispersed methylcytosines across the genome but DNA from cancer cells are hypomethylated at these sites and tend to form cluster of methylcytosines into CpG rich regulatory regions. This distinct methylation landscape leads to different solvation properties in solution, which in turn modulates their adsorption towards gold surface. Inset: TEM image showing the different solvation of DNA genome derived from the prostate tissue of a cancer patient and a healthy individual. b TEM image showing the different solvation of DNA based on their different methylation status. i) fully unmethylated WGA DNA ii) moderately methylated DNA from BT474 cancer cells iii) 100% CpG methylated Jurkat DNA. The solvation trend of DNA with increasing methylation levels is shown in right side. Scale bars are 2000 nm for all the TEM images. c AFM image showing the interaction behaviour of genomic DNAs with the gold surface based on their different methylation status. WGA and 100% methylated jurkat DNA shows very low adsorption, whereas BT474 DNA shows very high adsorption. The surface adsorption trend of genomic DNA with increasing global methylation levels is shown in right side

Fig. 2

Role of methylation on DNA-gold affinity. a Methodological approach for the electrochemical quantification of DNA adsorption on gold electrodes. First, the DPV current from the bare gold electrode was measured to get the baseline signal. The purified DNA extracted from cell line, tissue or plasma samples were then adsorbed onto the gold electrodes and the DPV current was measured to get the sample signal. The difference between the baseline and the sample signal is the i_r value_, which is normalized to %i_r for better understanding. The %i_r for a given DNA sample directly correlates with the adsorption level of DNA on gold electrodes. b Relative current (%i_r) mean values for the unmethylated WGA DNA (black), Aza treated demethylated Jurkat DNA (Blue), gDNA from BT474 and Jurkat cancer cells (red), HMEC gDNA from primary mammary cells (green) and 100% methylated gDNA from Jurkat cells (Brown). c Bar graph of relative current (%i_r) mean values for the adsorption of 140 bp methylated (red) and unmethylated (black) DNA fragments. d Bar graph of relative current (%i_r) mean values for the adsorption of individual cytosines (black) and methylcytosines (red) nucleotides. e Relative current (%i_r) mean values for various genomic DNAs prepared from WGA DNA by enzymatic reaction at different time points. Sample methylation levels are provided above each bar. Inset: electrophoresis gel of the enzymatically methylated DNA samples digested with methylation sensitive HpaII restriction enzyme. f Effect of cluster methylation towards adsorption. Each data point for b–e represents the average of three separate trials, and error bars represent the standard deviation of measurements (%RSD = < 5% for n = 3)

Fig. 3

Practical application of Methylscape approach. a Differential affinity/adsorption of genomic DNAs as a function of their cancer and normal origin. Bars represent the relative current (%i_r) mean values for DNA genomes derived from various normal (Black bars: Human Mammalian Epithelial Cell (HMEC), Prostate Epithelial cell (PrEC)) and cancer cell lines (Red bars: Breast cancer: BT474, MCF7, T47D, LNCap prostate cancer, HCT116 colorectal cancer and H-1975 lung cancer). Each data point represents the average of three separate trials, and error bars represent the standard deviation of measurements (%RSD = < 5% for n = 3). Right panel: Corresponding DPV graphs for all cell line DNAs and their respective baseline. b Individual box plot showing mean relative current (%i_r) values generated by electrochemical detection of genomic DNAs extracted from normal and cancer tissues of various cancer types (breast, prostate and lymph node). c The combined data for all the tissue samples derived from 31 healthy individuals and 72 cancer patients, Right: the ROC analysis and diagnostic test evaluation shows the Disease Prevalence (DP), positive predictive values (PPV), negative predictive values (NPV) and accuracy of the method. d Box plot showing relative current (%i_r) mean values generated by electrochemical detection for genomic DNAs extracted from plasma samples derived from 45 healthy individuals and 100 breast cancer patients, Right: the ROC analysis and diagnostic test evaluation shows the Disease Prevalence (DP), positive predictive values (PPV), negative predictive values (NPV) and accuracy of the method. In the box and whisker plots, the middle lines of the boxes represent the median (50th percentile) and the terminal line of the boxes represents the 25th to 75th percentile. The whiskers represent the lowest and the highest value

Fig. 4

Naked eye detection of cancer using AuNPs. a Schematic of the assay and proposed mechanism for different DNA types. b Mean relative absorbance values A_520/658 of 10 nm tannic-capped AuNP (pink) and AuNP- gDNA solution for unmethylated WGA (black), BT474 breast cancer cell line (red), and Aza treated Jurkat (light blue). Inset, the representative coloured solution. TEM images of c AuNPs alone, d AuNP-gDNA solution for unmethylated WGA, e AuNP with BT474 cancer DNA and f AuNP with 100% methylated Jurkat DNA (no salt was added during sample preparation, scale bars are 500 nm for normal images and 100 nm for the zoomed images in the black boxes). g Box plot showing the mean relative absorbance values A_520/658 of AuNP-gDNA solution for cancer and normal cells extracted from breast, prostate and lymph node tissues, Right: The ROC analysis and diagnostic test evaluation shows the Disease Prevalence (DP), positive predictive values (PPV), negative predictive values (NPV) and accuracy of the method. h Box plot showing the mean relative absorbance values A_520/658 of AuNP-gDNA solution for DNA samples derived from plasma samples of breast and colorectal cancer patients or healthy donors, Right: The ROC analysis and diagnostic test evaluation shows the Disease Prevalence (DP), positive predictive values (PPV), negative predictive values (NPV) and accuracy of the method. In the box and whisker plot, the middle lines of the boxes represent the median (50th percentile) and the terminal line of the boxes represents the 25th to 75th percentile. The whiskers represent the lowest and the highest value