{"id":319232,"date":"2026-08-10T12:00:09","date_gmt":"2026-08-10T11:00:09","guid":{"rendered":"https:\/\/www.transcend.org\/tms\/?p=319232"},"modified":"2026-08-08T19:45:54","modified_gmt":"2026-08-08T18:45:54","slug":"this-a-i-just-created-viruses-not-found-in-nature","status":"publish","type":"post","link":"https:\/\/www.transcend.org\/tms\/2026\/08\/this-a-i-just-created-viruses-not-found-in-nature\/","title":{"rendered":"This A.I. Just Created Viruses Not Found in Nature"},"content":{"rendered":"
\"\"<\/a>

hi X-174\u2014a naturally occurring virus that infects bacteria and is similar to novel AI-generated viruses announced on 6 Aug 2026\u2014is seen in structured model.\u00a0 Photo: Wikimedia<\/p><\/div>\n

7 Aug 2026\u00a0<\/em>–\u00a0For the first time, scientists have used artificial intelligence to create new kinds of viruses, raising hopes for medical advances while also raising the disturbing possibility that the technology could someday be used to invent dangerous pathogens.<\/p>\n

Synthesizing viruses from scratch is hardly new. Researchers long ago<\/a> learned how to manufacture viral genomes; they are used to investigate antiviral drugs and vaccines, as well as to learn how viruses work.<\/p>\n

But the new study<\/a>, published Thursday in the journal Science, goes well beyond duplicating viral genes. Scientists at Stanford University and the Arc Institute, a research organization in Palo Alto, Calif., taught A.I. to recognize patterns of DNA structure in nature, and then to use that data to write recipes for entirely new viruses.<\/p>\n

The researchers followed those recipes to create DNA molecules, which they inserted into bacteria. The modified bacteria then produced viruses never seen in nature. The viruses were able to infect other bacteria, demonstrating that they were viable.<\/p>\n

\u201cThis is an important milestone,\u201d said Patrick Cai, a synthetic biologist at the University of Manchester, who was not involved in the study.<\/p>\n

The viruses dreamed up by A.I. do not pose a threat to humans, because they are all similar to a naturally occurring virus called Phi X-174, which can infect only bacteria.<\/p>\n

But the new study adds to growing worries<\/a> that artificial intelligence might enable the creation of a new generation of biological weapons, from deadly poisons to unstoppable pandemics.<\/p>\n

Dr. Moritz Hanke, a fellow at the Johns Hopkins Center for Health Security who was not involved in the new study, said governments and scientific organizations have been slow to develop guardrails that could block the creation of a deadly virus \u2014 even as the science races ahead.<\/p>\n

\u201cThere\u2019s just a huge disconnect,\u201d he said.<\/p>\n

The authors of the study relied on an A.I. model called Evo, which is similar in some ways to ChatGPT, made by OpenAI. (The New York Times has sued OpenAI, ChatGPT\u2019s creator, and its partner, Microsoft.)<\/p>\n

ChatGPT answers questions by stringing together words that seem likely to follow one another. It can do this thanks to years of training on vast amounts of text gathered from the internet, books and other sources.<\/p>\n

DNA is strikingly similar to a book in some ways: a string of molecular building blocks, known as nucleotides, arrayed like letters in a line of text. A gene consists of hundreds of nucleotides drawn from a four-letter alphabet: A, C, G and T. The sequence encodes the instructions for building proteins and other molecules.<\/p>\n

DNA has its own rules of grammar, and if a sequence violates them, the result is biological gibberish. Biologists have uncovered some of nature\u2019s grammatical rules, but many remain a mystery.<\/p>\n

The researchers wondered if Evo could pick up these rules on its own<\/a>. Instead of training it on text, they trained it on genetic sequences drawn from millions of animals, plants, microbes and viruses. All told, Evo scanned about nine trillion nucleotides.<\/p>\n

Evo eventually recognized patterns common across the tree of life and used them to generate blueprints for new genes encoding proteins that could perform specific jobs. These results led the team to wonder if Evo could master not just single genes but also an entire genome.<\/p>\n

As the A.I. would be able to handle only small genomes at first, the scientists decided to try to make viruses. While a human genome contains over three billion nucleotides, many viruses have genomes just a few thousand nucleotides long.<\/p>\n

\u201cIt just felt like the obvious next step,\u201d said Samuel King, a graduate student at Stanford University and an author of the new study. He and his colleagues gave Evo another round of training, this time on the 11 genes of Phi X-174 and about 15,000 of its closest relatives.<\/p>\n

They made this choice in part because scientists know Phi X-174 intimately, having studied it for close to a century. And because it\u2019s a bacteriophage that infects only E. coli, they knew that viruses similar to it would be safe.<\/p>\n

Once Evo got familiar with the genomes of Phi X-174 and its kin, the researchers prompted the model to write new versions of its own. Evo generated 700,000 potential versions; the scientists pursued only the ones that looked as if they had the best odds of succeeding.<\/p>\n

They ended up making DNA molecules from 285 of Evo\u2019s suggested sequences. When those genomes were ready to test, Mr. King and his colleagues inserted them into bacteria, which they spread across petri dishes.<\/p>\n

In many of the dishes, the microbes grew peacefully \u2014 Evo\u2019s genomes had failed. But in one dish, researchers noticed clear dots appearing in the cloudy film of bacteria, the telltale sign of multiplying viruses.<\/p>\n

The DNA that the scientists had inserted into the bacteria had produced protein shells that contained viral genes. The viruses burst out of the cells, leaving behind the ruptured husks of their dead hosts.<\/p>\n

As Mr. King and his colleagues tested more genomes, they saw more clear dots. All told, they discovered that 16 of Evo\u2019s genomes produced viable new viruses.<\/p>\n

They proved to be as resilient as natural ones. In fact, some multiplied faster than Phi X-174. \u201cThey\u2019re not just sickly versions of stuff that already exists,\u201d said Oliver Crook, a protein chemist at the University of Oxford who was not involved in the new study.<\/p>\n

Dr. Crook cautioned that Evo\u2019s viruses were not radically new creations. They tend to be very similar<\/a> to natural species, relying on the same underlying biology.<\/p>\n

Scientists will have to run more experiments to find out if Evo has the same success rate if it\u2019s trained on other groups of viruses. If so, Dr. Crook expected that scientists might find some A.I.-generated viruses that could become useful tools for medicine and biotechnology.<\/p>\n

\u201cA lot of our science rests on viruses as technology,\u201d he said. To treat people with genetic disorders, for example, doctors will load genes into viruses, which deliver them into cells.<\/p>\n

But along with this hope, Evo\u2019s initial success has raised concerns that A.I. could be used to create deadly pathogens. \u201cYou could say, \u2018Hey, genomic language model, make me an influenza genome that is modified to be more transmissible or to be more lethal,\u2019\u201d Dr. Hanke speculated.<\/p>\n

The potential dangers were already on the minds of the researchers as they trained Evo. They did not provide the model with data about viruses that infect humans, and they excluded similar viruses that infect other animals, plants and fungi.<\/p>\n

As a result, Evo can\u2019t generate genomes of viruses that could threaten humans. \u201cWe just wanted to be extra careful,\u201d said Brian Hie, a computational biologist at Stanford University and an author of the new study.<\/p>\n

Dr. Hanke credited Dr. Hie and his colleagues for taking that precaution. \u201cI think that\u2019s quite commendable,\u201d he said, \u201cbecause they don\u2019t get any guidance from anywhere on what they should be doing.\u201d<\/p>\n

Last week, Dr. Hanke noted, the National Institutes of Health rolled out<\/a> a new policy for stopping high-risk life science research. The policy would bar scientists from experiments that would make biological agents more harmful.<\/p>\n

But computer-based research \u2014 such as generating virus DNA with A.I. \u2014 \u201cis not prohibited by this policy unless it involves an entity of concern,\u201d the agency said in a statement.<\/p>\n

It\u2019s easy to tell if a natural virus like smallpox is an entity of concern. But Dr. Hanke said there\u2019s no consensus on judging the possible danger of a virus made by an A.I. model.<\/p>\n

\u201cWhat is the risk of what I\u2019ve never seen before?\u201d he asked.<\/p>\n

Go to Original – rsn.org<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Scientists trained artificial intelligence on libraries of DNA and then asked the model to create recipes for viral genomes. Sixteen of them were viable, yielding new viruses.” <\/p>\n","protected":false},"author":4,"featured_media":319233,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3078],"tags":[1733,4112],"class_list":["post-319232","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence-ai","tag-artificial-intelligence-ai","tag-science-and-ai"],"_links":{"self":[{"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/posts\/319232","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/comments?post=319232"}],"version-history":[{"count":1,"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/posts\/319232\/revisions"}],"predecessor-version":[{"id":319234,"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/posts\/319232\/revisions\/319234"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/media\/319233"}],"wp:attachment":[{"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/media?parent=319232"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/categories?post=319232"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.transcend.org\/tms\/wp-json\/wp\/v2\/tags?post=319232"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}