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

  1. Jairaj Singh

Reviewed by

Read the full article

Listed in

Log in to save this article

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.

SUMMARY

In addition to the guidelines provided in the abstract above,the following points summarizes the article below:

  • The article discusses an application of Machine Learning in the field of virology.

  • It 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.

  • To 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.

  • The data-set used is MN997409.1-4NY0T82X016-Alignment-HitTable.csv found on www.kaggle.com .(Complete link shared in the references section). [17]

  • The results have been validated by using a simple data-correlation technique namely Spearman’s Rank Correlation Coeffecient .

  • I 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.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.10.12.336339: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    Institutional Review Board Statementnot detected.
    RandomizationCentroids are first allotted randomly and then by running for a certain number of iterations the K-Means algorithm fixes the centroids and allocates the clusters.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    It is an accession-based data originally downloaded by performing a BLAST exhaustive search from NCBI(National Center for Biotechnology Information) database.
    BLAST
    suggested: (BLASTX, RRID:SCR_001653)

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • No conflict of interest statement was detected. If there are no conflicts, we encourage authors to explicit state so.
    • No funding statement was detected.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  2. Version published to 10.1101/2020.10.12.336339v1 on bioRxiv