Predictive Analytics to Combat with COVID-19 using Genome Sequencing

Abstract

The coronavirus outbreak (nCoV) has created an alarming situation at the international level.

COVID-19 pandemic is now continuing to develop and researchers across the world are working to combat COVID-19 and to reduce and prevent its spread. Traditional pathological tests are used but they are time-consuming & also the number of test kits & centers is limited. Surprising thing is 60% of patients may not have any symptoms but still, they are SAR-CoV-2 positive & may work as silent carriers causing an outbreak of this disease. And a reason to worry is that there is no vaccine & exact drug for this disease.

Machine learning techniques can be used to analyze clinical data but again symptoms vary from person-to-person & accuracy of clinical outcomes is questionable. To tackle this problem, this the paper proposes a technique to detect the presence of SAR-CoV-2 in a person using genome sequencing.

This will accurately help to detect the presence of the virus, to develop targeted therapies & vaccines and also to learn how the patient will respond to drugs. This paper summarizes the primary survey of existing work & proposes a technique using predictive analytics to detect the presence of SAR-CoV-2 using genome sequencing to combat COVID-19. This system will be able to differentiate SAR-CoV- 2 from its other subtypes, such as MERS-CoV, HCoV-NL63, HCoV-OC43, HCoV-229E, HCoV- HKU1, and SARS-CoV regardless of some missing information and noise in the dataset. Thus the proposed methodology can be used by doctors & practitioners as a tool for making ease in decision making.

Note: Funding: No Funding.

Conflict of Interest: Authors don't have any competing interest for publication of this work.

Keywords: COVID-19; machine learning; predictive analytics; genome sequencing SARS-CoV-2; India pandemic