AI used to identify new RNA viruses

Scientists have identified more than 160,000 ribonucleic acid (RNA) virus species, with the help of artificial intelligence, in what is perhaps the largest discovery of virus species.

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

The research was carried out jointly by scientists from Sun Yatsen University, Alibaba Cloud Intelligence, the University of Sydney, and some other institutions.

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

They play a pivotal role in the global ecosystem and some of them are the pathogens behind the outbreak of human infectious diseases, he said.

During the course of the research, a deep-learning algorithm termed LucaProt was developed to analyze the 10,487 RNA sequencing data generated from samples across diverse environments, including air, hot springs and hydrothermal vents.

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

"The vast majority of these viruses had been sequenced already and were on public databases, but they were so divergent that no one knew what they were," said Edwards Holmes, a professor at the School of Medical Sciences in the Faculty of Medicine and Health at the University of Sydney.

"They comprised what is often referred to as sequence 'dark matter'. Our AI method was able to organize and categorize all this disparate information, shedding light on the meaning of this dark matter for the first time," he was quoted in a statement released by the University of Sydney.

The AI tool was trained to compute the "dark matter" and identify viruses based on sequences and the secondary structures of the protein that all RNA viruses use for replication, fast-tracking the otherwise time-intensive virus discovery.

"To find these many new viruses in one fell swoop is mind-blowing, and it just scratches the surface, opening up a world of discovery. There are millions more to be discovered, and we can apply this same approach to identifying bacteria and parasites," Holmes said.

"The AI algorithm model allows us to dig out the viruses previously unknown or neglected. This capability is especially important in disease control and rapid identification of new pathogens," Shi said.