Dual Dove
A team of computer scientists and biologists have detected a fundamental genomic pattern for 29 various COVID-19 DNA sequences by employing machine learning. This newly developed data-finding tool enables scientists to quickly and easily identify a virus like the new COVID-19 in just a few minutes.
The process and pace are of high significance for strategic planning and mobilizing medical requirements throughout a pandemic. The study, named “Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study,” was published in PLOS ONE.
The ‘ultra-fast, scalable, and highly accurate’ labeling system uses a brand new graphics-based, specialized software and decision-tree methods to depict the classification and end up with the best choice out of all possible outcomes.
It Classifies Genomes Within Minutes
Biology professor Kathleen Hill, the study co-author, worked with researchers from West, specialized in Computer Science and Statistical and Actuarial Sciences, together with others from the University of Waterloo’s Department of Computer Science.
The machine-learning technique allegedly manages to get 100 percent accurate classification of the COVID-19 sequences and, above all, finds the most important association among more than 5,000 viral genomes again in just a few minutes.
“All we needed was the COVID-19 DNA sequence to discover its own intrinsic sequence pattern. We used that signature pattern and a logical approach to match that pattern as close as possible to other viruses and achieved a fine level of classification in minutes—not days, not hours but minutes,” Hill explained.
This labeling tool has already been employed to analyze over 5,000 unique viral genomic sequences, such as the COVID-19 sequences available on January 27th of this year. Hill seems to believe that the instrument, which can also label newly discovered virus sequences of COVID-19 or otherwise, will reportedly be an important element in the toolkit for treatment developers, front-line healthcare workers, and scientists during this global crisis.
