They use artificial intelligence to identify new RNA viruses.

Photo: CFP

Using artificial intelligence, scientists have identified more than 160,000 species of ribonucleic acid (RNA) viruses, perhaps the largest discovery of a virus species.

A report on the discovery was published Wednesday in the international scientific journal Cell.

The study was conducted jointly by scientists from Sun Yat-sen University, Alibaba Cloud Intelligence, the University of Sydney and several other institutions.

RNA viruses are ubiquitous, found even in the most extreme environments, and are the most mysterious microorganisms, said Shi Man, a professor at Sun Yat-sen University’s Zhongshan School of Medicine.

According to him, they play a critical role in the global ecosystem, and some of them are the causative agents of outbreaks of human infectious diseases.

The study developed a deep learning algorithm called LucaProt to analyze 10,487 RNA sequencing data obtained from samples from a variety of environments, including air, hot springs, and hydrothermal vents.

The algorithm identified 161,979 RNA virus species and 180 RNA virus supergroups, including many previously understudied groups, as well as RNA virus genomes of exceptional length.

“The vast majority of these viruses had already been sequenced and were in public databases, but they were so different that no one knew what they were,” said Edwards Holmes, a professor in the School of Health Sciences in the College of Medicine and Public Health. . University of Sydney.

“They consisted of what are often called “dark matter” sequences. Our artificial intelligence method was able to organize and classify all this disparate information, shedding light on the meaning of this dark matter for the first time,” he was quoted as saying in a statement released by the University of Sydney.

The artificial intelligence tool was trained to calculate “dark matter” and identify viruses based on the sequences and secondary structures of the protein that all RNA viruses use to replicate, speeding up virus detection that would otherwise take a long time.

“Discovering so many new viruses at once is amazing and is just the tip of the iceberg, opening up a world of discovery. We have millions more to discover, and we can apply the same approach to identifying bacteria and parasites,” Holmes said. .

“The artificial intelligence algorithm model allows us to detect viruses that were previously unknown or ignored. This capability is especially important for disease control and rapid identification of new pathogens,” Shi said.

(Web Editor: 周雨, Zhao Jian)