Dynamic, stage-course protein interaction network using high power CpG sites in Head and Neck Squamous Cell Carcinoma

Head and neck cancer is the sixth leading cause of cancer across the globe and is more prevalent in the developing countries of South Asia, including Pakistan [1]. DNA methylation is an important contributor to the pathophysiology of the various stages of cancer making it important to understand the role of specific methylation events in each stage of a particular cancer [2]. Previous studies have classified early and late stages of liver carcinoma using two class. machine learning models based on differentially methylated CpG sites [3]. No studies have been conducted to classify pathological stages (I-IV) of HNSCC using four class machine learning models using mutated gene associated CpG sites in HNSCC, partly due to high computational expense and small sample size

Objective; Retrieve and process primary tumor DNA methylation profiles of HNSCC with known pathologic stages then identifying the key CpG sites and building machine learning models based on identified CpG sites