Gene Expression Analysis on Cancer Dataset

Abstract

Genes are the basis of tumor formations around the body, which is better known as cancer. They inhibit basic processes such as cell death (apoptosis) and promote cell division to an unhealthy extent. The expression of every gene provides a baseline to know the progress of cancer from the organ or tissue it originated from along with its approximated course of action. The analysis of such gene expression values using traditional machine learning methods provide a higher efficiency and accuracy in finding relationships between genes and also it may serve as a future for diagnosing the cancer by using these values. The main challenge is to use the bases that are created to efficiently compute the highly effective genes to treat specific types of cancer by using their expression values and thus, raise the question of a potential relationship between them for each type. A Random Forest Model has been used to perform Feature Selection over the dataset in order to extract the important features (i.e.) the most influential genes. They are then visualized by using traditional packages in Python (i.e. Scikit-plot, Matplotlib, Seaborn) and using a data visualization tool called Tableau to project the result of the analysis.