All NewsEducationTV
Equities & FundsCrypto & Digital AssetsAI & TechnologyBusiness & CorporateUS Politics & PolicyGeopolitics & Global RiskMacro, Rates & FXCommodities & EnergyEuropean Politics & MarketsAsia-PacificReal Estate & Property
Story archiveAll categories
← All Stories

AI designs novel, functional viruses capable of replication

Created at 6 Aug · 6:36 PM1 source↑ Market-relevant
IN SHORT

US researchers have utilized AI to design and synthesize 16 novel, functional viruses capable of replicating in a laboratory setting. These bacteriophages target bacteria and pose no threat to humans, potentially opening new avenues for treating antibiotic-resistant infections. However, the breakthrough also raises significant biosafety and biosecurity concerns.

✉Newsletter

PiQ Daily

Pick your topics. Get only what matters, on your cadence.

Key Numbers

16novel viruses designed and synthesized
302AI designs synthesized in the lab
5,400base pairs in the phage genetic code
500,000base pairs in the smallest living cell genome

Who's Involved

Brian Hie
Assistant professor at Stanford University and lead researcher
Samuel King
PhD student at Stanford University involved in the research
Thomas Inglesby
Expert from the Center for Health Security at Johns Hopkins University
Moritz Hanke
Expert from the Center for Health Security at Johns Hopkins University
Marc Güell
Professor from the synthetic biology lab at Pompeu Fabra University
Patrick Cai
Chair of synthetic genomics at the Manchester Institute of Biotechnology

↳ Why This Matters

This advancement in AI-driven synthetic biology offers a powerful new tool for developing treatments against infectious diseases, but it simultaneously introduces urgent questions about safety and security regarding the potential for misuse in creating novel pathogens.

Key facts

  • Artificial Intelligence has been used to design and create 16 novel, functional viruses in a laboratory.
  • The designed viruses are bacteriophages that infect bacteria and do not pose a threat to humans.
  • This marks the first time generative AI has been used to design a complete, self-replicating viral genome.
  • The research could lead to new treatments for antibiotic-resistant infections.
  • Experts have highlighted urgent biosafety and biosecurity concerns associated with the technology.

US researchers have successfully used artificial intelligence to design and create 16 novel, functional viruses that can replicate in a laboratory. These viruses, known as bacteriophages, are designed to infect specific bacteria and pose no threat to humans. This breakthrough, detailed in the journal Science, is the first instance of generative AI being used to design a complete viral genome.

The AI models, Evo1 and Evo2, were trained on genetic codes from viruses, bacteria, plants, and humans, learning the 'language of life' to predict genetic sequences. Researchers synthesized 302 promising AI designs, with 16 proving effective in killing E. coli bacteria. This development could pave the way for new treatments against antibiotic-resistant infections.

However, the ability to design new biology also raises significant biosafety and biosecurity concerns. Experts have warned that such technology could potentially be misused to create dangerous diseases. The researchers emphasized that safety measures were taken, including excluding viruses that infect complex organisms from the training data and conducting the research in a secure laboratory.

Academics involved in the study described it as a "very significant turning point" and an "important milestone" in synthetic biology, opening possibilities for developing new drugs and therapies. They noted that while creating living organisms from scratch would be a larger leap, the current work demonstrates a growing capability to design biology on a computer.

Frequently asked questions

A bacteriophage is a type of virus that specifically infects bacteria. They are not harmful to humans or other animals.

The AI models are trained on vast amounts of genetic data and learn to predict genetic sequences, similar to how large language models predict text, enabling them to design novel viral genomes.

The primary benefit is the potential to develop new treatments, such as bacteriophage therapy, for infections that are resistant to conventional antibiotics.

The primary concerns revolve around biosafety and biosecurity, specifically the risk that the technology could be misused to design and create new, potentially harmful viruses or diseases.

What Happens Next

01Further research into the therapeutic applications of AI-designed bacteriophages.
02Development of enhanced biosafety and biosecurity protocols for AI-driven biological design.

Get the newsletter.

Pick the topics you actually care about. We'll email when there's news worth your time, on the cadence you choose. Cancel any time from your account.

Cadence

How It Developed

Researchers used AI models, Evo1 and Evo2, trained on genetic codes from various organisms.
The AI was directed to design bacteriophages, viruses that infect bacteria.
Researchers synthesized 302 AI-designed viral genomes in the lab.
of the synthesized viruses were effective at killing E. coli bacteria.
Experts noted the achievement as a significant turning point in designing biology.
Concerns were raised about the potential malicious use of the technology to create new diseases.

Sources

T1
Artificial Intelligence used to design brand new virusesBBC News

Related Stories

AI models design novel bacterial viruses
6 Aug · 7:11 PM
UK scientists trial fridge-free vaccines inspired by resurrection plants
6 Aug · 12:06 AM
Meta AI model breached third-party system during testing
6 Aug · 2:11 AM
Chinese AI robot accurately vaccinates pigs without needles
6 Aug · 10:31 AM
Gen Z dating app Ditto uses AI matchmaking to replace swiping
6 Aug · 4:11 PM