Scientists have created the first functional viruses designed using artificial intelligence, marking a major step for AI-powered biotechnology while also raising new questions about biosafety and security.
The viruses are bacteriophages, which infect bacteria rather than humans. Bacteriophages are already used in some parts of the world to treat persistent bacterial infections. In laboratory tests, a combination of the AI-designed viruses successfully killed E. coli bacteria that had developed resistance to natural bacteriophages.
AI Designed Complete Viral Genomes
Dr. Brian Hie, a chemical engineer at Stanford University, and his team used genome language models to design functioning bacteriophage genomes.
These systems work with genetic sequences in a way similar to how large language models process and generate text. Researchers then produced the designed viruses in a laboratory and tested them against E. coli.
The researchers said the ability to rapidly design genomes for specific bacteria and overcome resistance could transform phage therapy and expand the tools available to biotechnology.
Researchers Warn About Safety Risks
The breakthrough also creates significant biosafety, biocontainment and biosecurity concerns.
The researchers urged scientists working on whole-genome design to involve safety and security experts throughout their projects.
Prof. Tom Inglesby and Dr. Moritz Hanke of the Johns Hopkins Center for Health Security warned that generative AI can now be used to compose functional viral genomes, while governance mechanisms have not yet caught up with that capability.
Tom Ellis, professor of synthetic genome engineering at Imperial College London, described the research as impressive but noted that bacteriophages have very small and relatively simple genomes. Designing more complex organisms would therefore be considerably harder.
He said AI trained on genetic information from dangerous organisms could potentially design more harmful viruses. However, restricting access to sensitive genetic data and screening suspicious genome synthesis requests could reduce those risks.
Ellis also argued that modifying existing pathogens remains an easier and more immediate threat than creating an entire dangerous genome with AI.
Dr. Filippa Lentzos of King’s College London said regulation should not focus only on AI models. She called for a layered approach covering model development and access, research oversight, DNA synthesis screening, and established laboratory biosafety and biosecurity procedures.
The post Scientists Create the World’s First Virus Designed by AI appeared first on ProPakistani.