Universal penalized regression (Elastic-net) model with differentially methylated promoters for oral cancer prediction

Shantanab Das ¹, Saikat Karuri ¹, Joyeeta Chakraborty ¹

⁰Human Genetics Unit, Indian Statistical Institute, 203 B T Road, Kolkata, 700 108, India.

European Journal of Medical Research +

|

September 11, 2024

View abstract on PubMed

Summary

This study developed a DNA methylation model for oral cancer detection, proving effective across diverse global populations. The model shows high accuracy in identifying oral cavity squamous cell carcinoma (OSCC) and potential for early disease detection.

Area Of Science

Oncology
Genetics
Biomarker Discovery

Background

DNA methylation is a promising biomarker for cancer diagnosis.
Previous studies on DNA methylation biomarkers for oral squamous cell carcinoma (OSCC) were geographically limited.
The generalizability of DNA methylation as a diagnostic marker for oral cancer across diverse populations remains under-investigated.

Purpose Of The Study

To investigate the generalizability of DNA methylation as a diagnostic marker for oral cancer across different geographical locations.
To develop and validate a robust DNA methylation-based model for oral cavity squamous cell carcinoma (OSCC) detection.

Main Methods

Utilized genome-wide methylation data from 384 oral cavity cancer and normal tissues (TCGA HNSCC and Eastern India).
Developed an Elastic-net model using common differentially methylated CpGs.
Validated the model using 812 HNSCC and normal samples from seven countries, and further confirmed with Droplet Digital PCR (ddMSRE) and pyrosequencing.

Main Results

The model demonstrated high diagnostic performance: 91% sensitivity, 100% specificity, and 95% accuracy (ddMSRE).
Pyrosequencing validation showed 96% sensitivity, 91% specificity, and 93% accuracy for OSCC vs. contralateral normal samples.
The model exhibited comparable sensitivity, specificity, and accuracy across different geographical locations, anatomical sites, and cancer stages.

Conclusions

A DNA methylation model was developed, identifying crucial genomic regions in OSCC.
The model demonstrated consistent accuracy in detecting oral cancer across diverse geographical locations.
High specificity in distinguishing cancer from contralateral normal tissues suggests potential for early oral cancer detection.

Keywords:

DNA methylation Droplet digital PCR HNSCC Linear regression techniques Methylation-sensitive restriction enzyme Oral squamous cell carcinoma

Related Concept Videos

Epigenetic Regulation

Epigenetic changes alter the physical structure of the DNA without changing the genetic sequence and often regulate whether genes are turned on or off. This regulation ensures that each cell produces only proteins necessary for its function. For example, proteins that promote bone growth are not produced in muscle cells. Epigenetic mechanisms play an essential role in healthy development. Conversely, precisely regulated epigenetic mechanisms are disrupted in diseases like cancer.
X-chromosome...