Oral cancer prediction on epigenomics data using machine learning methods

Abstract

Epigenomic is the study that deals with phenotype alteration that do not cause any modification in the DNA sequence of cells. Epigenomics is formed up of the word’s epi and genomics, with epi deriving from the Greek prefix. The epi- in Epigenomics refers to features that are "on top of" or "in addition to" the traditional genetic base for inheritance. As a result, it basically adds something on the top of DNA to modify its characteristics, thereby prohibiting some DNA behaviors. These changes take place in cancer cells and are the single cause of cancer. Oral Cancer is one of the most common type of Cancer and responsible for hundreds of thousands of deaths every year. Can we predict Oral Cancer at its early stage? The main objective of this study and research is to find the most important genes which affect the whole process of identifying Oral Squamous Cell Carcinoma (OSCC) and to predict OSCC in a patient accurately. OSCC is one of the most prevalent cancers worldwide, with a global incidence of more than 350,000 new cases and 177,000 deaths every year, though with considerable geographic and environmental risk factor differences worldwide. Tobacco use, alcohol consumption, and Epstein-Barr virus (EBV) infection are the main risk factors associated with Oral cancer (for nasopharyngeal cancer). The data includes methylation, histone, human genome and RNA-Sequences. The data is accessed through open-source technologies in R and Python programming languages. The data is processed to reduce the dimensionality and extract the most relevant features and with the help of statistical analysis and advanced machine learning techniques, the prediction of Oral cancer is obtained from the fine-tuned model.