United States: In the latest reports, an Artificial Intelligence tool has been helping researchers to discover an unknown virus species, that too at a ‘not known before’ speed from the data that was available to the present databases, as claimed the experts of mainland China, Hong Kong, and Australia.
More about the reports
According to the team of scientists, the discovery of almost 162,000 novel species of RNA virus has been able to be made in various different environments, such as the atmosphere, hot springs, and hydrothermal vents.
These findings have underlined the huge diversity and resilience in harsh situations that such viruses possess while also offering clues about other elemental life forms that came to be.
Therefore, after analyzing the previously unknown genetic sequences in public databases, the machine learning tool has spotted a number of viruses based on their sequences and hidden protein structure information that RNA viruses use for replication, scmp.com reported.
They identified whether a sequence represents an RNA virus species in one second or less.
More about the AI tool
As per the reports, the tool, which uses an algorithm, is developed by the Alibaba Cloud Intelligence team and made in collaboration with a team of virologists.
According to the team, “We developed a data-driven deep learning model that outperforms conventional methods in accuracy, efficiency and, most importantly, the breadth of virus diversity detected,” as scmp.com reported.
The article of the study was published in the peer-reviewed journal Cell on Wednesday.
As per the co-lead author, Shi Mang, who is a virologist and professor at the Sun Yat-sen University School of Medicine, the AI tool not only speeds up the virus discovery, which was generally a time-consuming and tedious task if done via traditional methods.
However, it also enables scientists to find an area that was previously unknown in the virus’s territory.
Mang said, “All the viruses discovered in this study exist in the environment and were sequenced. Our previous methods were not able to identify them, leaving them as ‘dark matter’ to scientists.”
“The AI tool fills this gap for us with high accuracy comparable to conventional methods in bioinformatics. It can uncover ‘dark matter’ sequences, along with those more closely related to established viral groups,” he continued.