DistantNews
Support us
AI designs functional new viruses in lab, raising safety concerns
๐Ÿ‡ท๐Ÿ‡ธ Serbia /Health & Science

AI designs functional new viruses in lab, raising safety concerns

From N1 Serbia · () Serbian

Translated from Serbian, summarized and contextualized by DistantNews.

At a glance

News Sources not specified Context piece
  • Researchers have used artificial intelligence to design and create 16 new, functional viruses that infect bacteria in a laboratory setting.
  • This marks the first time complete viral genomes have been designed using AI, a breakthrough that could advance disease treatment but also raises urgent safety concerns.
  • The AI models, trained on genetic codes, predict the "language of life" to create bacteriophages, which scientists observed successfully destroying E. coli bacteria.

American researchers have utilized artificial intelligence to design and create 16 novel, functional viruses capable of replicating in a laboratory. This achievement represents the first instance of complete viral genomes being designed with AI assistance. While these newly created viruses are designed to infect bacteria and pose no threat to humans, the breakthrough is being hailed as a significant scientific milestone with the potential to usher in a new era of disease treatment.

However, experts are sounding alarms about the "urgent" safety and security questions raised by AI-designed viruses. While AI tools are rapidly advancing and have been used for developing new antibiotics, creating a completely new, functional virus from scratch presents a far greater complexity. Brian Hay, an assistant professor at Stanford University, described this as the "next step in complexity" for generative AI, noting it's the first time the technology has designed a complete genome capable of replication and other cellular functions.

The AI technology functions similarly to large language models like ChatGPT, predicting sequences. In this case, AI models named Evo1 and Evo2 predict the "language of life" instead of text. These models were trained on the genetic codes of viruses, bacteria, plants, and humans. They were then specifically adapted to create bacteriophages, viruses that infect only certain types of bacteria.

This is the next step when it comes to the complexity of what can be designed by generative artificial intelligence. This is the first time that generative artificial intelligence has been used to design a complete genome, something that can replicate and perform other functions within cells... For us, this was completely new territory.

โ€” Brian HayDescribing the significance of designing a complete viral genome using AI.

Stanford researchers selected 302 promising AI designs and synthesized them in the lab. Sixteen of these proved effective in destroying E. coli bacteria. Samuel King, a doctoral student in the lab, described the moment of realization that the phages were working as "incredibly exciting." The development of new phages could offer novel approaches to treating infections that have become resistant to antibiotics, presenting a potential solution to the growing challenge of untreatable bacterial infections.

This advancement also highlights AI's capability to design new biological systems beyond natural existence, a field known as synthetic biology. Hay believes this has the potential to "enormously advance human health" through new drugs and therapies. Nevertheless, concerns are already being voiced about the potential misuse of this technology to create new diseases.

We started to notice these clear surfaces and it was incredibly exciting.

โ€” Samuel KingRecounting the moment researchers observed the AI-designed phages successfully destroying bacteria.
DistantNews Editorial

Originally published by N1 Serbia in Serbian. Translated, summarized, and contextualized by our editorial team with added local perspective. Read our editorial standards.