AI creates first synthetic viruses

{"text":[[{"start":6.1,"text":"Scientists in the US have for the first time used artificial intelligence to create viruses unknown in nature, a milestone in synthetic biology that promises advances in healthcare but also raises important biosafety and biosecurity concerns."}],[{"start":21.18,"text":"Stanford University researchers developed a generative AI programme called Evo 2 that writes new genomes — the genetic instructions for life encoded in DNA. They used it to design and make 16 synthetic phages, small viruses that infect bacteria."}],[{"start":37.34,"text":"Phages are sometimes used instead of antibiotic drugs to kill bacteria causing disease."}],[{"start":42.42,"text":"When tested in their secure lab, the researchers found that these novel phages were more effective at killing the common microbe E. coli than the natural phage ΦX174, which served as a template for Evo 2 to work on. The results were published on Thursday in the journal Science."}],[{"start":58.26,"text":"“Our study is a proof of concept showing for the first time that generative design can generate entire functional genomes,” said Brian Hie, the project leader. “We chose to work with phages because they are small viruses, well studied and have broad applications in molecular biology and therapeutics.”"}],[{"start":75.7,"text":"The approach could be extended later to larger organisms such as bacteria and then to more complex forms of life, he added."}],[{"start":82.78,"text":"“The importance of Brian Hie’s landmark paper cannot be overstated,” said Adrian Woolfson, a genomics expert who is chief executive of the DNA synthesis company Genyro. “It is biology’s Wright Brothers moment, where we stop looking over our shoulder at the entities that evolution has created . . . and are confronted with the vast expanses of future biological possibility.”"}],[{"start":104.62,"text":"Phage therapy has been used in eastern Europe for many decades. Specific phages are matched to the patient’s precise bacterial strain and delivered by topical application, injection or orally to the infection site. It is not widely applied in the West for several reasons, including the complex procedures required and the potential for bacteria to evolve resistance."}],[{"start":124.638,"text":"AI could help lead to a revival of phage therapy, said Samuel King, another member of the Stanford team. “With more evidence coming out on the emergence of scary antibiotic-resistant pathogens, we will need innovative alternative solutions — and phage therapy is certainly one.”"}],[{"start":139.58,"text":"For safety, the initial Stanford study was based on a non-pathogenic strain of E. coli and used a genomic language model that was not trained on viruses capable of infecting the more complex cells that make up animals and plants. However, the technology could in future encompass a much wider range of viruses and extend to designing entirely new organisms without having to start from a natural genome."}],[{"start":null,"text":"

"}],[{"start":164.58,"text":"Evo 2 is open source, available for anyone to download free of charge to design new genomes themselves."}],[{"start":171.86,"text":"“We don’t have plans right now to commercialise this work,” said Hie. “We’re an academic lab funded by philanthropy and government grants. It is our responsibility to put the basic technology out there for use by as many people as possible because of the vast potential benefits to health and humanity.”"}],[{"start":189.62,"text":"Those benefits outweigh the risk that bad actors could modify the AI tool for bioterrorist purposes, Hie maintained. But Thomas Inglesby and Moritz Hanke, of the Center for Health Security at Johns Hopkins University, warned in the same issue of Science that the study “raises urgent biosafety and biosecurity questions”."}],[{"start":210.1,"text":"While praising the Stanford scientists for the precautions they took in their research, Inglesby and Hanke said: “Existing governance frameworks are insufficient for overseeing generative genomics . . . The question is no longer whether generative viral genome design will exist. It is whether society can build oversight that allows its benefits to unfold while preventing it from enabling serious harm.”"}],[{"start":235.22,"text":""}]],"url":"https://audio.ftcn.net.cn/album/a_1786077353_1814.mp3"}