© ROOT-NATION.com - Use of content is permitted with a backlink.
American researchers have announced the use of AI to develop entirely new viruses that are fully functional and capable of self-replication in a laboratory setting. This is the first time in history that AI has completely designed entire genomes.
Read also: AERONAUT – everything that flies above the ground: aviation, UAVs and drones, rockets, and space
The 16 novel viruses produced as a result of the experiment are designed to target bacteria and pose no danger to humans. Scientists have called this breakthrough an extremely important turning point that could usher in a new era in the treatment of diseases. At the same time, experts in the field warn that creating viruses using AI raises urgent concerns about biosafety and security.
AI-based tools are rapidly improving and have previously been used to design new antibiotics. However, that task proved relatively simple compared to creating a viable virus from scratch.
As Brian Guy, an assistant professor at Stanford University – pictured on the left with a colleague – noted in an interview with the BBC, this step demonstrates the next level of complexity achievable by generative AI. According to him, generative AI has, for the first time, created a fully functional genome capable of replicating and performing other functions within cells, which was completely uncharted territory for the team.
In the context of these developments, other achievements in the field are also highlighted, including the use of AI tools to develop new antibiotics against gonorrhea and the superbug MRSA, as well as instances of discovering viruses in everyday settings that destroy bacteria and could save human lives.
The underlying technological principle is similar to that of large language models, such as ChatGPT, which predict sequences of words. In this case, AI models named Evo1 and Evo2 predict the “language of life” instead of ordinary text. These AI systems were trained using the genetic codes of viruses, bacteria, plants, and humans.
They were then configured to generate a specific type of virus – bacteriophages, which infect only certain types of bacteria. Researchers at Stanford University selected the 302 most promising concepts created by the AI and synthesized them in the lab. Of these, 16 viruses demonstrated high efficacy in killing E. coli bacteria.
Samuel King, a graduate student in the lab, said they realized the phages were working early in the morning. They placed the phages in Petri dishes containing a layer of cultured bacteria and watched for signs of their activity. According to King, when clear spots began to appear on the cultures, it sparked incredible excitement. Brian Guy recalls that when the results were presented to the entire team, the room erupted in spontaneous applause.
The creation of new phages has the potential to open up innovative avenues for combating infections that have become resistant to antibiotics. In addition, this achievement highlights AI’s ability to design new biological entities beyond the natural world within the field of synthetic biology. According to Brian Guy, this has the potential to significantly improve human health through the development of new drugs and therapies.
However, concerns have also been raised that such technology could be misused to create new diseases. In a commentary accompanying the publication in the journal *Science*, Dr. Thomas Inglesby and Dr. Moritz Hanke of the Center for Health Security at Johns Hopkins University noted that the discovery raises urgent biosafety questions. They emphasized that the question is no longer whether generative design of viral genomes will exist, but whether it can be used without causing serious harm. The experts stressed that the development of new viruses capable of causing disease should not continue.
The researchers themselves took steps to maximize safety. They removed viruses capable of infecting complex organisms from the training database, conducted experiments exclusively with phages rather than human viruses, and carried out all work in a secure laboratory. Brian Guy is convinced that even existing safety measures largely ensure the technology will be used for good.
The transition from computer bits to atoms remains a challenge. Viruses are not living organisms, and creating living organisms using AI will require another major leap forward. A phage’s genetic code consists of about 5,400 base pairs (letters). The smallest genome of a living cell is around 500,000 base pairs, while the human genome consists of 3 billion base pairs. Brian Guy noted that attempting to create simple living organisms will require a tremendous amount of work, but it is entirely feasible, and they are definitely interested in moving in this direction.
Professor Mark Gwell of the Synthetic Biology Laboratory at Pompeu Fabra University in Spain emphasized that the research marks an important turning point, as for the first time in history, biology is being designed on a computer. This opens up new possibilities for addressing humanity’s greatest challenges, such as creating phages to combat diseases, enzymes to treat genetic disorders, and antibodies for immunotherapy.
Professor Patrick Tsai, head of the synthetic genomics program at the Manchester Institute of Biotechnology, called the work a major milestone. He added that its significance extends far beyond phages, as language models of the genome are beginning to learn the design principles established by evolution, paving the way for writing genomes using AI.
Read also:Uncontrolled AI Again: OpenAI Has Frozen Development of Astra Due to the Threat of Cyberattacks