Genomic Similarity of Nucleotides in SARS CoronaVirus using K-Means Unsupervised Learning Algorithm

Abstract

The drastic increase in the number of coronaviruses discovered and coronavirus genomes being sequenced have given us a great opportunity to perform genomics and bioinformatics analysis on this family of viruses. Coronaviruses possess the largest genomes (26.4 to 31.7 kb) among all known RNA viruses, with G + C contents varying from 32% to 43%. Phylogenetically, three genera, Alphacoronavirus, Betacoronavirus and Gammacoronavirus, with Betacoronavirus consisting of subgroups A, B, C were known to exist but now a new genus D also exists,namely the Deltacoronavirus. In such a situation, it becomes highly important for efficient classification of all virus data so that it helps us in suitable planning,containment and treatment. The objective of this paper is to classify SARS corona-virus nucleotide sequences based on parameters such as sequence length,percentage similarity between the sequence information,open and closed gaps in the sequence due to multiple mutations and many others.By doing this,we will be able to predict accurately the similarity of SARS CoV-2 virus with respect to other corona-viruses like the Wuhan corona-virus,the bat corona-virus and the pneumonia virus and would help us better understand about the taxonomy of the corona-virus family. SUMMARYIn addition to the guidelines provided in the abstract above,the following points summarizes the article below: O_LIThe article discusses an application of Machine Learning in the field of virology. C_LIO_LIIt aims to classify the SARS CoV2 virus as per the already known sequences of the bat-coronavirus, the Wuhan Sea Food Market pneumonia virus and the Wuhan coronavirus. C_LIO_LITo solve and predict the similarity of the SARS CoV2 coronavirus w.r.t other viruses discussed above,K-Means Unsupervised Learning Algorithm has been chosen. C_LIO_LIThe data-set used is MN997409.1-4NY0T82X016-Alignment-HitTable.csv found on www.kaggle.com.(Complete link shared in the references section).[17] C_LIO_LIThe results have been validated by using a simple data-correlation technique namely Spearmans Rank Correlation Coeffecient. C_LIO_LII have also discussed my future work using Deep Neural Nets that can help predict new virus sequences and effectively find similarity if any with already discovered viruses. C_LI