An Analytical Study of Covid-19 Dataset using Graph-Based Clustering Algorithms

TL;DR

This paper applies three graph-based clustering algorithms to protein-protein interaction networks derived from COVID-19 gene data to analyze the structure and potential insights into the disease.

Contribution

It introduces the use of multiple graph-based clustering algorithms on COVID-19 PPI networks for disease analysis.

Findings

Identification of meaningful clusters in PPI networks

Insights into protein interactions related to COVID-19

Comparison of clustering algorithms' effectiveness

Abstract

Corona VIrus Disease abbreviated as COVID-19 is a novel virus which is initially identified in Wuhan of China in December of 2019 and now this deadly disease has spread all over the world. According to World Health Organization (WHO), a total of 3,124,905 people died from 2019 to 2021, April. In this case, many methods, AI base techniques, and machine learning algorithms have been researched and are being used to save people from this pandemic. The SARS-CoV and the 2019-nCoV, SARS-CoV-2 virus invade our bodies, causing some differences in the structure of cell proteins. Protein-protein interaction (PPI) is an essential process in our cells and plays a very important role in the development of medicines and gives ideas about the disease. In this study, we performed clustering on PPI networks generated from 92 genes of the Covi-19 dataset. We have used three graph-based clustering algorithms to give intuition to the analysis of clusters.