Scientists have used artificial intelligence (AI), which identifies an underlying genomic signature for the various DNA sequences of coronavirus-19, which causes COVID-19, a mechanism for vaccine and drug developers Provides important equipment.
According to researchers at Western University in Canada, this new data search tool will allow researchers to quickly and easily classify deadly viruses such as SARS-CoV-2 in just minutes.
He said that it provided a process of high importance for strategic planning and mobilized medical needs during an epidemic.
The study, published in the journal PLOS ONE, also supports the scientific hypothesis that the SARS-CoV-2 virus, which causes COVID-19 disease, has its origins in bats as Sarbecovirus, a subgroup of Betacoronavirus.
The “ultra-fast, scalable, and highly accurate” classification system uses a new graphic-based, specialized software and decision-tree approach to illustrate classification and arrive at a best option out of all possible outcomes, the researchers said.
The machine-learning method achieves a 100 percent accurate classification of novel coronavirus sequences and, more importantly, reveals the most relevant relationships among more than 5,000 viral genomes within minutes, the researchers said.
Machine learning is an application of AI that provides the ability to automatically learn and improve from experience without explicitly programming the system.
“We all needed the COVID-19 DNA sequence to discover our own internal sequence patterns,” said Kathleen Hill, a professor at the University of Western Ontario in Canada.
“We used that signature pattern and logical approach to closely match that pattern to other viruses and achieved a good level of classification in minutes – not days, not hours but minutes.” Hill said.