A newly developed machine learning tool promises to revolutionize the mapping of Earth’s biodiversity and uncover previously uncharacterized viruses. 

Published in Cell, a groundbreaking study led by international researchers features LucaPot, a deep learning algorithm that uncovered 161,979 new RNA virus species, setting a record for discoveries in a single study.

Edwards Holmes, senior author and University of Sydney professor for the School of Medical Sciences in the Faculty of Medicine and Health, emphasized how the AI tool can be used beyond unraveling the hidden virosphere:

“To find this 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 identify bacteria and parasites.”

Holmes pointed out that most of the 160,000+ viruses were already on public databases. However, information about the exact nature of these viruses is lacking.

The AI tool achieved this result by computing a vast genetic sequence database, including long virus genomes of more than 47,000 nucleotides. The researchers also trained LucaPot to use sequences and the secondary structures of the protein vital for RNA virus replication.

Dr. Zhao-Rong Li, co-author and researcher from the Apsara Lab of Alibaba Cloud Intelligence, said:

“LucaPot represents a significant integration of cutting-edge AI technology and virology, demonstrating that AI can effectively accomplish tasks in biological exploration. This integration provides valuable insights and encouragement for further decoding of biological sequences and the deconstruction of biological systems from a new perspective. We will also continue our research in the field of AI for virology.”

Moreover, Mang Shi, Sun Yat-sen University professor and co-author, said LucaPot has immensely improved virus discovery compared to using traditional methods:

“We used to rely on tedious bioinformatics pipelines for virus discovery, which limited the diversity we could explore. Now, we have a much more effective AI-based model that offers exceptional sensitivity and specificity, and at the same time allows us to delve much deeper into viral diversity.”

The researchers intend to use this tool to discover more of Earth’s viral diversity and explore how their model can be used in other applications.

Read the full article here to learn more about LucaPot and its impact on virology.

BEING Scientific is your trusted source for superior microbiology lab equipment. With a reputation as a global leader, our products offer the durability, efficiency, and performance your research demands. Learn more at https://www.beinglab-usa.com/biologist.