Учёные применили ИИ для создания 16 новых вирусов против бактериальной резистентности

Scientists have used AI systems to synthesize 16 new bacteriophage viruses — a potential alternative to antibiotics in the fight against bacterial resistance, reports Wired.

What are bacteriophages and why create them

Bacteriophages are viruses that attack bacteria, not human cells. Researchers view them as a promising alternative to antibiotics in combating pathogens that have developed resistance to treatment. According to the World Health Organization, antibiotic resistance already causes at least 1.27 million deaths per year, and by 2050 this figure is projected to rise significantly.

Traditionally, phages for therapeutic use were sought in nature — in soil, wastewater, and on plant surfaces. This is a painstaking and unpredictable process: the needed phage may simply not exist or may resist detection for years. Phage therapy, studied since the early 20th century, never reached the mass market largely because of this problem. The application of AI changes the equation: generative models can design new viral proteins in days, exploring molecular structures that scientists could not manually enumerate even over several lifetimes.

• 16 new viruses created using AI systems
• Goal — targeting bacteria resistant to antibiotics
• According to WHO, antibiotic resistance claims 1.27 million lives per year
• Traditional phage discovery takes years; AI synthesis takes days or hours

How exactly does AI create viruses that don't exist in nature?

AI was used to generate new viral protein sequences — a task virtually impossible to perform manually due to the astronomical number of possible variants. In this sense, AI acts as a molecular designer, generating thousands of candidates where a human team could test only a handful. Importantly, the 16 created viruses are not modifications of known phages: they are synthetic structures that did not previously exist in nature. The resulting objects are then tested in the laboratory for their ability to effectively target bacterial strains.

This approach opens the path to personalized phage therapies: it will be possible to design a virus specifically for a particular resistant strain in a particular patient — where a natural analogue does not exist or is unsuitable. Today, phage therapy is held back precisely by this limitation: matching the right phage on a "lock and key" basis succeeds only in some cases.

"Using AI systems to create viruses opens new possibilities for combating bacterial resistance," states the

Wired article.

Why regulation is not keeping pace with AI biotech

The development of viruses using AI is advancing faster than the regulatory frameworks around it. This is a familiar problem for biotechnology in general, but AI sharpens it: what previously required a specialized laboratory, a large team, and many years of work is now accessible far more quickly and with fewer resources. Entry barriers are falling — and along with them, the potential for misuse grows.

No unified international approach to oversight of AI-synthesized biological entities has yet been developed. Who is permitted to conduct such experiments? What level of safety verification is required before publishing results? The key vulnerability is dual use: the same models that design therapeutic phages could in theory be redirected toward creating dangerous pathogens. This is precisely why biosecurity experts insist: the lag of regulation behind AI capabilities is no longer an abstract threat, but a growing risk.

What this means

The creation of 16 viruses using AI is one of the most concrete examples of how generative technologies are transforming biomedicine: from searching for ready-made solutions in nature — to designing new ones from scratch. Medicine gains a potentially powerful tool against one of the major crises of modern healthcare. The answer to how quickly regulators can close the gap with the laboratory will largely determine whether this technology becomes primarily a means of treatment — or a source of fundamentally new risks.