{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-08-21T18:21:36.167Z","headline":"斯坦福与 Arc Institute 用 AI 设计全新病毒基因组，16 种在实验室成功杀死细菌","description":"斯坦福大学与 Arc Institute 团队用 AI 模型 Evo 从零设计完整病毒基因组，并在实验室构建出 16 种自然界不存在的功能性病毒。Evo 提出 70 万个候选基因组，团队仅筛选最有希望的 285 个序列合成并植入细菌，其中 16 个成功复制并杀死宿主。该研究已通过同行评审发表于《Science》，但 Evo 未接受人类病原体数据训练，且能否推广至其他病毒类群仍是未知数。 🔗 阅读原文 via AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","url":"https://www.aioga.com/news/cmsiys4dz1yqironkuitnfi7t/","mainEntityOfPage":"https://www.aioga.com/news/cmsiys4dz1yqironkuitnfi7t/","datePublished":"2026-08-07T12:50:56.000Z","dateModified":"2026-08-07T12:50:56.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://the-decoder.com/stanford-and-arc-institute-scientists-used-ai-to-design-new-viruses-that-killed-bacteria-in-the-lab","https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t"],"canonicalUrl":"https://www.aioga.com/news/cmsiys4dz1yqironkuitnfi7t/","directAnswer":{"@type":"Answer","text":"斯坦福大学与 Arc Institute 团队使用 Evo 设计完整病毒基因组，从约70万个候选中筛选并合成285个序列，最终有16个在细菌中形成可复制并杀死宿主的病毒。研究已通过同行评审并发表于《Science》。","url":"https://www.aioga.com/news/cmsiys4dz1yqironkuitnfi7t/","dateCreated":"2026-08-07T12:50:56.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"the-decoder.com source article","url":"https://the-decoder.com/stanford-and-arc-institute-scientists-used-ai-to-design-new-viruses-that-killed-bacteria-in-the-lab","datePublished":"2026-08-07T12:50:56.000Z","provider":{"@type":"Organization","name":"the-decoder.com","url":"https://the-decoder.com/stanford-and-arc-institute-scientists-used-ai-to-design-new-viruses-that-killed-bacteria-in-the-lab"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","datePublished":"2026-08-07T12:50:56.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t"}}],"aggregationSource":"The Decoder：AI News（RSS）","originalPublisher":{"name":"the-decoder.com","url":"https://the-decoder.com/stanford-and-arc-institute-scientists-used-ai-to-design-new-viruses-that-killed-bacteria-in-the-lab"},"geoDeepAnswer":null,"article":{"id":"cmsiys4dz1yqironkuitnfi7t","slug":"cmsiys4dz1yqironkuitnfi7t","url":"https://www.aioga.com/news/cmsiys4dz1yqironkuitnfi7t/","title":"斯坦福与 Arc Institute 用 AI 设计全新病毒基因组，16 种在实验室成功杀死细菌","title_en":"","summary":"斯坦福大学与 Arc Institute 团队用 AI 模型 Evo 从零设计完整病毒基因组，并在实验室构建出 16 种自然界不存在的功能性病毒。Evo 提出 70 万个候选基因组，团队仅筛选最有希望的 285 个序列合成并植入细菌，其中 16 个成功复制并杀死宿主。该研究已通过同行评审发表于《Science》，但 Evo 未接受人类病原体数据训练，且能否推广至其他病毒类群仍是未知数。 🔗 阅读原文 via AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","source":"The Decoder：AI News（RSS）","sourceUrl":"https://the-decoder.com/stanford-and-arc-institute-scientists-used-ai-to-design-new-viruses-that-killed-bacteria-in-the-lab","aiHotUrl":"https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","publishedAt":"2026-08-07T12:50:56.000Z","category":"行业动态","score":72,"selected":true,"articleBody":["A team from Stanford University and the Arc Institute had an AI model design complete viral genomes from scratch, then built 16 functional viruses in the lab that don't exist in nature. The work had previously only been available as a preprint. It has now been peer-reviewed and published in the journal Science：http://www.science.org/doi/10.1126/science.aec2657.","The New York Times reports：https://www.nytimes.com/2026/08/06/science/ai-viruses-bacteria-arc.html new details, particularly about the hit rate. The model, called Evo, proposed 700,000 possible genomes. The team pursued only the most promising candidates, had 285 sequences chemically synthesized as DNA, and inserted them into bacteria. Sixteen of those produced viruses capable of replicating. The preprint had mentioned 302 synthesized genomes.","The training process is also coming into sharper focus. Evo first learned from roughly nine trillion nucleotides drawn from millions of animals, plants, microbes, and viruses, picking up patterns that run through the entire tree of life. Only then did a second, specialized training round follow, using the 11 genes of the phage Phi X-174 and about 15,000 of its closest relatives. For doctoral student and co-author Samuel King, it was the logical move. \"It just felt like the obvious next step,\" he said.","The resulting viruses weren't just weak copies, either. They proved as robust as natural ones, and some replicated even faster than Phi X-174. \"They're not just sickly versions of stuff that already exists,\" says Oliver Crook, a protein chemist at the University of Oxford who wasn't involved in the study. Patrick Cai, a synthetic biologist at the University of Manchester, calls the work an \"important milestone.\"","Crook tempers expectations, though. The AI didn't invent anything fundamentally new. The viruses are very similar to natural species：https://www.biorxiv.org/content/10.64898/2026.06.12.731871v1 and rely on the same biology. Whether Evo would be equally successful with other virus groups remains an open question. If it is, the results could yield useful tools for medicine and biotech. \"A lot of our science rests on viruses as technology,\" Crook says.","A gap in biosafety regulation is now more visible than ever. The U.S. National Institutes of Health released a policy on high-risk life sciences research：https://www.nih.gov/about-nih/nih-director/statements/announcement-release-us-government-policy-stopping-high-risk-life-sciences-research in late July. It bans experiments that make pathogens more dangerous. But purely computational work, meaning designing viral DNA on a computer, isn't covered \"unless it involves an entity of concern,\" the agency said.","The problem is obvious. With smallpox, that classification is clear-cut. With a virus that came out of an AI model, it isn't. \"What is the risk of what I've never seen before?\" asks Moritz Hanke of the Johns Hopkins Center for Health Security. He sees a wide gap between the pace of research and the guardrails around it. \"There's just a huge disconnect.\" His misuse scenario: \"You could say, 'Hey, genomic language model, make me an influenza genome that is modified to be more transmissible or to be more lethal.'\"","The team took precautions on its own. During training, Evo received no data on viruses that infect humans, nor on related pathogens from animals, plants, or fungi. That means the model can't generate those genomes in the first place. \"We just wanted to be extra careful,\" says Brian Hie, a computational biologist at Stanford and co-author of the study. Hanke calls that \"quite commendable,\" especially because no official rules required it. \"Because they don't get any guidance from anywhere on what they should be doing,\" he says.","Original article from September 21, 2025:","A research team in California has used artificial intelligence to design working viruses that kill bacteria, in what they describe as the \"first generative design of complete genomes.\" The project marks an early step toward AI-designed life forms, according to a report in MIT Technology Review.","The work was carried out by scientists at Stanford University and the nonprofit Arc Institute. In a preprint paper：https://www.biorxiv.org/content/10.1101/2025.09.12.675911v1, they describe how an AI system proposed new genetic codes for viruses. The team then chemically printed 302 of these designs as DNA strands and exposed them to E. coli bacteria. Sixteen of the AI-generated viruses successfully replicated and destroyed their bacterial hosts.","\"That was pretty striking, just actually seeing this AI-generated sphere,\" said Brian Hie, who runs the Arc Institute lab where the viruses were created.","At the center of the project is an AI called Evo：https://the-decoder.com/evo-2-an-ai-model-that-understands-the-language-of-life/, which functions like a large language model but is trained on biology instead of text. Instead of learning from books and articles, Evo was trained on about two million bacteriophage genomes. For this study, the researchers tasked it with proposing variants of phiX174, a simple bacteriophage containing only 11 genes and about 5,000 DNA letters.","Jef Boeke, a biologist at NYU Langone Health, described the project as an \"impressive first step\" toward AI-designed life, even though viruses themselves are not technically alive. He said the AI's performance was \"surprisingly good\" and its designs \"unexpected,\" with changes to gene orders and arrangements that human scientists hadn't considered.","Not everyone is convinced. J. Craig Venter, who helped pioneer synthetic DNA, called the method \"just a faster version of trial-and-error experiments.\" His lab once created synthetic cells through a similar process, but with much slower, manual searches through scientific literature.","The technology could have major applications. Doctors have long experimented with phage therapy as a treatment for multidrug-resistant bacterial infections. Viruses are also a key tool in gene therapy, where they deliver new genes into human cells. AI-designed viruses could make both approaches more effective.","But the risks are equally clear. The team deliberately avoided training Evo on human pathogens. Even so, Venter raised \"grave concerns\" about what could happen if the same approach were used on dangerous viruses like smallpox or anthrax. \"One area where I urge extreme caution is any viral enhancement research, especially when it's random so you don't know what you are getting,\" he said.","Scaling the method to living cells is also far more complex. A bacterium like E. coli has about 1,000 times more DNA than phiX174. \"The complexity would rocket from staggering to way, way more than the number of subatomic particles in the universe,\" Boeke warned.","Despite this, Jason Kelly, CEO of Ginkgo Bioworks, argues that pursuing AI-designed cells should be a national priority. He imagines automated labs that could continuously test AI-generated genome designs, feeding results back into the model. \"This would be a nation-scale scientific milestone, as cells are the building blocks of all life,\" he said. \"The US should make sure we get to it first.\"","Stay in the loop on AI. Clear, useful, no fluff.","Follow The Decoder for AI news, background stories and expert analyses.","The Decoder：https://the-decoder.com/"],"articleImages":[{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2025/09/dangerous_virus_computer_chatbot.png","alt":"Image description","afterParagraph":0,"url":"/media/articles/cmsiys4dz1yqironkuitnfi7t/e612658feb227790.png"}],"mediaStatus":"ok","articleBodyZh":["斯坦福大学和Arc研究所的一个团队让一个人工智能模型从零设计完整的病毒基因组，然后在实验室中构建了16种功能性病毒，这些病毒在自然界中并不存在。这项工作此前仅以预印本的形式发布。现在，它已通过同行评审并发表在《科学》杂志上：http://www.science.org/doi/10.1126/science.aec2657。","《纽约时报》报道了新的细节，特别是关于命中率：https://www.nytimes.com/2026/08/06/science/ai-viruses-bacteria-arc.html。该模型名为Evo，提出了700,000种可能的基因组。团队只追踪了最有前景的候选基因组，对285条序列进行了DNA化学合成，并将其插入细菌中。其中16条产生了能够复制的病毒。预印本中提到合成了302条基因组。","训练过程也变得更加清晰。Evo首先从数百万种动物、植物、微生物和病毒中约九万亿个核苷酸中学习，获取贯穿整个生命树的模式。只有在此之后，才进行第二轮、专门的训练，使用噬菌体Phi X-174的11个基因及约15,000个其最接近的亲属。对于博士生兼共同作者Samuel King来说，这是合乎逻辑的步骤。他说：“这感觉就是显而易见的下一步。”","最终得到的病毒也不仅仅是弱化的复制品。它们证明同自然病毒一样强健，有些甚至比Phi X-174复制得更快。“它们不仅仅是现有病毒的病弱版本，”牛津大学未参与该研究的蛋白质化学家Oliver Crook说。曼彻斯特大学的合成生物学家Patrick Cai称这项工作是“一个重要的里程碑”。","不过，Crook提醒不要过度期待。人工智能并没有发明任何基理上全新的东西。这些病毒与自然种类非常相似：https://www.biorxiv.org/content/10.64898/2026.06.12.731871v1，并依赖相同的生物学原理。Evo是否在其他病毒组中同样成功仍是一个悬而未决的问题。如果成功，结果可能为医学和生物技术提供有用工具。Crook说：“我们的很多科学研究都依赖病毒作为技术。”","生物安全监管的漏洞现在比以往任何时候都更明显。美国国立卫生研究院（NIH）在七月底发布了一项关于高风险生命科学研究的政策：https://www.nih.gov/about-nih/nih-director/statements/announcement-release-us-government-policy-stopping-high-risk-life-sciences-research。该政策禁止将病原体变得更具危险性的实验。但该机构表示，纯计算性工作，即在计算机上设计病毒 DNA 的工作，并不在其涵盖范围内，“除非它涉及关注的实体”。","问题显而易见。对于天花病毒，这种分类非常明确。而对于从 AI 模型生成的病毒，则不然。约翰霍普金斯大学健康安全中心的 Moritz Hanke 问：“我从未见过的东西，其风险是什么？”他认为研究进程与相关防护措施之间存在很大差距。“这之间存在巨大的脱节。”他设想的一种滥用情景是：“你可能会说，‘嘿，基因组语言模型，为我生成一个可以增加传播性或致死性的流感基因组。’”","该团队自行采取了预防措施。在训练过程中，Evo 没有使用感染人类的病毒的数据，也没有使用来自动物、植物或真菌的相关病原体的数据。这意味着该模型一开始就无法生成这些基因组。斯坦福大学的计算生物学家及研究共同作者 Brian Hie 表示：“我们只是想格外小心。”Hanke 称这是“相当值得称赞的”，尤其是因为没有任何官方规定要求这样做。他说：“因为他们没有从任何地方得到关于应该做什么的指导。”","2025年9月21日的原始文章：","加利福尼亚的一支研究团队使用人工智能设计了能够杀死细菌的活病毒，他们称之为“完整基因组的首次生成设计”。根据《麻省理工科技评论》的报道，该项目标志着迈向 AI 设计生命形式的早期一步。","这项工作由斯坦福大学和非营利组织Arc Institute的科学家完成。在一篇预印本论文中：https://www.biorxiv.org/content/10.1101/2025.09.12.675911v1，他们描述了一个人工智能系统如何为病毒提出新的基因密码。团队随后将其中302个设计化学打印为DNA链，并将其暴露于大肠杆菌中。由AI生成的16种病毒成功复制并破坏了其细菌宿主。","“这非常惊人，实际上亲眼看到这个AI生成的球体，”负责Arc Institute实验室的Brian Hie说道，这间实验室正是病毒产生的地方。","该项目的核心是一种名为Evo的人工智能：https://the-decoder.com/evo-2-an-ai-model-that-understands-the-language-of-life/，它的功能类似大型语言模型，但训练对象是生物学而非文本。Evo没有从书籍和文章中学习，而是从大约两百万个噬菌体基因组中接受训练。在这项研究中，研究人员让它设计phiX174的变体，这是一种只包含11个基因、约5000个DNA字母的简单噬菌体。","纽约大学朗格健康中心的生物学家Jef Boeke将该项目描述为迈向AI设计生命的“令人印象深刻的第一步”，即使病毒本身在技术上并不算活体。他说AI的表现“出乎意料的好”，其设计“令人意外”，在基因顺序和排列上作出了人类科学家未曾考虑的改变。","并非所有人都信服。合成DNA的先驱J. Craig Venter称这种方法“只是加快了的试错实验”。他的实验室曾通过类似过程创建合成细胞，但过程更加缓慢，需要手工查阅科学文献。","该技术可能具有重大应用。医生长期以来尝试过噬菌体疗法，以治疗多药耐药的细菌感染。病毒也是基因治疗中的关键工具，用于将新基因传递到人体细胞中。AI设计的病毒可能使这两种方法更加有效。","但风险同样明显。团队刻意避免让Evo接受人类病原体的训练。即便如此，Venter对如果用同样的方法对危险病毒如天花或炭疽进行实验可能发生的情况表示“严重关切”。他表示：“我特别呼吁在任何病毒增强研究中保持极度谨慎，尤其是随机增强的时候，因为你根本不知道会得到什么。”","将该方法扩展到活细胞也要复杂得多。像大肠杆菌这样的细菌，其DNA数量大约是phiX174的1000倍。“复杂性将从令人震惊的程度跃升到远远超过宇宙中亚原子粒子数量的水平，”Boeke警告道。","尽管如此，Ginkgo Bioworks的首席执行官Jason Kelly认为，追求AI设计的细胞应该成为国家优先事项。他设想了自动化实验室，可以持续测试AI生成的基因组设计，并将结果反馈到模型中。“这将是国家级的科学里程碑，因为细胞是所有生命的组成基础，”他说。“美国应该确保我们率先实现这一目标。”","保持对AI的关注。清晰、有用、没有废话。","关注The Decoder获取AI新闻、背景故事和专家分析。","解码器：https://the-decoder.com/"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"斯坦福大学与 Arc Institute 团队使用 Evo 设计完整病毒基因组，从约70万个候选中筛选并合成285个序列，最终有16个在细菌中形成可复制并杀死宿主的病毒。研究已通过同行评审并发表于《Science》。","background":"Evo 先从约9万亿个核苷酸中学习生命序列模式，随后使用噬菌体 Phi X-174 的11个基因及约1.5万个近缘序列进行专门训练。团队表示，训练数据排除了感染人类的病毒及相关动植物、真菌病原体。","viewpoint":"Aioga 判断，这项研究的重要性在于生成模型的输出已从候选序列进入实验验证阶段，但结果不等于 AI 创造了全新生物学机制。外部研究者指出，这些病毒仍与天然物种非常相似，并依赖相同的生物学基础。","implications":"该成果可能为医学与生物技术中的病毒工具研究提供新路径，但其对其他病毒类群是否同样有效仍未确定。值得关注的是，现有高风险生命科学政策对纯计算式病毒 DNA 设计的覆盖存在材料所述的监管空白。","nextStep":"后续应关注该方法能否在其他病毒类群中复现、候选筛选与实验成功率是否稳定，以及计算设计如何纳入生物安全治理。对模型训练数据的排除范围、合成环节审查和风险实体认定也需要更明确的规则。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-08-12T00:02:32.996Z","sourceHash":"088b23ed4fa92fe1","review":{"approved":true,"groundedness":95,"clarity":92,"duplicationRisk":12,"blockingIssues":[],"notes":["“Aioga 判断”属于明确标注的编辑观点，与来源中“进入实验验证阶段”的事实和外部研究者关于其生物学创新边界的评价基本一致。","“生成模型的输出已从候选序列进入实验验证阶段”是对候选筛选、DNA 合成和细菌实验过程的概括，未构成事实错误。","“监管空白”是对来源所述政策不覆盖纯计算式病毒 DNA 设计（除非涉及受关注实体）及监管滞后的概括；如需更严谨，可改为“存在监管覆盖不足”。","nextStep 中关于规则进一步明确的内容属于合理建议性判断，不是来源直接陈述，但已置于后续建议语境中。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","low-source-overlap","no-html","independent-ai-review"]}},"tags":["行业动态","The Decoder：AI News（RSS）"],"translations":{"zh-CN":{"title":"斯坦福与 Arc Institute 用 AI 设计全新病毒基因组，16 种在实验室成功杀死细菌","summary":"斯坦福大学与 Arc Institute 团队用 AI 模型 Evo 从零设计完整病毒基因组，并在实验室构建出 16 种自然界不存在的功能性病毒。Evo 提出 70 万个候选基因组，团队仅筛选最有希望的 285 个序列合成并植入细菌，其中 16 个成功复制并杀死宿主。该研究已通过同行评审发表于《Science》，但 Evo 未接受人类病原体数据训练，且能否推广至其他病毒类群仍是未知数。 🔗 阅读原文 via AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"斯坦福与 Arc Institute 用 AI 设计全新病毒基因组，16 种在实验室成功杀死细菌 - Aioga AI资讯","description":"斯坦福大学与 Arc Institute 团队用 AI 模型 Evo 从零设计完整病毒基因组，并在实验室构建出 16 种自然界不存在的功能性病毒。Evo 提出 70 万个候选基因组，团队仅筛选最有希望的 285 个序列合成并植入细菌，其中 16 个成功复制并杀死宿主。该研究已通过同行评审发表于《Science》，但 Evo 未接受人类病原体数据训练，且能否推...","url":"https://www.aioga.com/news/cmsiys4dz1yqironkuitnfi7t/","articleBody":["斯坦福大学和Arc研究所的一个团队让一个人工智能模型从零设计完整的病毒基因组，然后在实验室中构建了16种功能性病毒，这些病毒在自然界中并不存在。这项工作此前仅以预印本的形式发布。现在，它已通过同行评审并发表在《科学》杂志上：http://www.science.org/doi/10.1126/science.aec2657。","《纽约时报》报道了新的细节，特别是关于命中率：https://www.nytimes.com/2026/08/06/science/ai-viruses-bacteria-arc.html。该模型名为Evo，提出了700,000种可能的基因组。团队只追踪了最有前景的候选基因组，对285条序列进行了DNA化学合成，并将其插入细菌中。其中16条产生了能够复制的病毒。预印本中提到合成了302条基因组。","训练过程也变得更加清晰。Evo首先从数百万种动物、植物、微生物和病毒中约九万亿个核苷酸中学习，获取贯穿整个生命树的模式。只有在此之后，才进行第二轮、专门的训练，使用噬菌体Phi X-174的11个基因及约15,000个其最接近的亲属。对于博士生兼共同作者Samuel King来说，这是合乎逻辑的步骤。他说：“这感觉就是显而易见的下一步。”","最终得到的病毒也不仅仅是弱化的复制品。它们证明同自然病毒一样强健，有些甚至比Phi X-174复制得更快。“它们不仅仅是现有病毒的病弱版本，”牛津大学未参与该研究的蛋白质化学家Oliver Crook说。曼彻斯特大学的合成生物学家Patrick Cai称这项工作是“一个重要的里程碑”。","不过，Crook提醒不要过度期待。人工智能并没有发明任何基理上全新的东西。这些病毒与自然种类非常相似：https://www.biorxiv.org/content/10.64898/2026.06.12.731871v1，并依赖相同的生物学原理。Evo是否在其他病毒组中同样成功仍是一个悬而未决的问题。如果成功，结果可能为医学和生物技术提供有用工具。Crook说：“我们的很多科学研究都依赖病毒作为技术。”","生物安全监管的漏洞现在比以往任何时候都更明显。美国国立卫生研究院（NIH）在七月底发布了一项关于高风险生命科学研究的政策：https://www.nih.gov/about-nih/nih-director/statements/announcement-release-us-government-policy-stopping-high-risk-life-sciences-research。该政策禁止将病原体变得更具危险性的实验。但该机构表示，纯计算性工作，即在计算机上设计病毒 DNA 的工作，并不在其涵盖范围内，“除非它涉及关注的实体”。","问题显而易见。对于天花病毒，这种分类非常明确。而对于从 AI 模型生成的病毒，则不然。约翰霍普金斯大学健康安全中心的 Moritz Hanke 问：“我从未见过的东西，其风险是什么？”他认为研究进程与相关防护措施之间存在很大差距。“这之间存在巨大的脱节。”他设想的一种滥用情景是：“你可能会说，‘嘿，基因组语言模型，为我生成一个可以增加传播性或致死性的流感基因组。’”","该团队自行采取了预防措施。在训练过程中，Evo 没有使用感染人类的病毒的数据，也没有使用来自动物、植物或真菌的相关病原体的数据。这意味着该模型一开始就无法生成这些基因组。斯坦福大学的计算生物学家及研究共同作者 Brian Hie 表示：“我们只是想格外小心。”Hanke 称这是“相当值得称赞的”，尤其是因为没有任何官方规定要求这样做。他说：“因为他们没有从任何地方得到关于应该做什么的指导。”","2025年9月21日的原始文章：","加利福尼亚的一支研究团队使用人工智能设计了能够杀死细菌的活病毒，他们称之为“完整基因组的首次生成设计”。根据《麻省理工科技评论》的报道，该项目标志着迈向 AI 设计生命形式的早期一步。","这项工作由斯坦福大学和非营利组织Arc Institute的科学家完成。在一篇预印本论文中：https://www.biorxiv.org/content/10.1101/2025.09.12.675911v1，他们描述了一个人工智能系统如何为病毒提出新的基因密码。团队随后将其中302个设计化学打印为DNA链，并将其暴露于大肠杆菌中。由AI生成的16种病毒成功复制并破坏了其细菌宿主。","“这非常惊人，实际上亲眼看到这个AI生成的球体，”负责Arc Institute实验室的Brian Hie说道，这间实验室正是病毒产生的地方。","该项目的核心是一种名为Evo的人工智能：https://the-decoder.com/evo-2-an-ai-model-that-understands-the-language-of-life/，它的功能类似大型语言模型，但训练对象是生物学而非文本。Evo没有从书籍和文章中学习，而是从大约两百万个噬菌体基因组中接受训练。在这项研究中，研究人员让它设计phiX174的变体，这是一种只包含11个基因、约5000个DNA字母的简单噬菌体。","纽约大学朗格健康中心的生物学家Jef Boeke将该项目描述为迈向AI设计生命的“令人印象深刻的第一步”，即使病毒本身在技术上并不算活体。他说AI的表现“出乎意料的好”，其设计“令人意外”，在基因顺序和排列上作出了人类科学家未曾考虑的改变。","并非所有人都信服。合成DNA的先驱J. Craig Venter称这种方法“只是加快了的试错实验”。他的实验室曾通过类似过程创建合成细胞，但过程更加缓慢，需要手工查阅科学文献。","该技术可能具有重大应用。医生长期以来尝试过噬菌体疗法，以治疗多药耐药的细菌感染。病毒也是基因治疗中的关键工具，用于将新基因传递到人体细胞中。AI设计的病毒可能使这两种方法更加有效。","但风险同样明显。团队刻意避免让Evo接受人类病原体的训练。即便如此，Venter对如果用同样的方法对危险病毒如天花或炭疽进行实验可能发生的情况表示“严重关切”。他表示：“我特别呼吁在任何病毒增强研究中保持极度谨慎，尤其是随机增强的时候，因为你根本不知道会得到什么。”","将该方法扩展到活细胞也要复杂得多。像大肠杆菌这样的细菌，其DNA数量大约是phiX174的1000倍。“复杂性将从令人震惊的程度跃升到远远超过宇宙中亚原子粒子数量的水平，”Boeke警告道。","尽管如此，Ginkgo Bioworks的首席执行官Jason Kelly认为，追求AI设计的细胞应该成为国家优先事项。他设想了自动化实验室，可以持续测试AI生成的基因组设计，并将结果反馈到模型中。“这将是国家级的科学里程碑，因为细胞是所有生命的组成基础，”他说。“美国应该确保我们率先实现这一目标。”","保持对AI的关注。清晰、有用、没有废话。","关注The Decoder获取AI新闻、背景故事和专家分析。","解码器：https://the-decoder.com/"]},"en":{"title":"Stanford and the Arc Institute have used AI to design a brand-new viral genome, with 16 bacteria successfully killed in the lab","summary":"A team from Stanford University and the Arc Institute used the AI model Evo to design a complete viral genome from scratch and built 16 functional viruses that do not exist in nature in the lab. Evo proposed 700,000 candidate genomes, but the team selected only the most promising 285 sequences to synthesize and implant bacteria, of which 16 successfully replicated and killed the host. The study was published in Science through peer review, but Evo was not trained on human pathogen data, and whether it can be extended to other viral groups remains unknown. 🔗 Read the original article via AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"Industry","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford and the Arc Institute have used AI to design a brand-new viral genome, with 16 bacteria successfully killed in the lab - Aioga AI News","description":"A team from Stanford University and the Arc Institute used the AI model Evo to design a complete viral genome from scratch and built 16 functional viruses that do not exist in natu...","url":"https://www.aioga.com/en/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:16:23.935Z"},"ja":{"title":"スタンフォード大学とアーク研究所はAIを用いて新しいウイルスゲノムを設計し、16種の細菌が実験室で無事に殺滅しました","summary":"スタンフォード大学とアーク研究所のチームは、AIモデルEvoを用いてゼロから完全なウイルスゲノムを設計し、自然界には存在しない16の機能性ウイルスを構築しました。 Evoは70万の候補ゲノムを提案しましたが、チームは最も有望な285配列のみを選び、細菌の合成と移植に成功し、そのうち16が成功して宿主を殺しました。 この研究は査読を通じてScience誌に掲載されましたが、Evoはヒト病原体データに基づいて訓練されておらず、他のウイルス群への拡張が可能かどうかは不明です。 🔗 原文記事はAIHOTより読むことができます。 https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"業界動向","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"スタンフォード大学とアーク研究所はAIを用いて新しいウイルスゲノムを設計し、16種の細菌が実験室で無事に殺滅しました - Aioga AIニュース","description":"スタンフォード大学とアーク研究所のチームは、AIモデルEvoを用いてゼロから完全なウイルスゲノムを設計し、自然界には存在しない16の機能性ウイルスを構築しました。 Evoは70万の候補ゲノムを提案しましたが、チームは最も有望な285配列のみを選び、細菌の合成と移植に成功し、そのうち16が成功して宿主を殺しました。 この研究は査読を通じてScience誌に掲載...","url":"https://www.aioga.com/ja/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:16:25.651Z"},"ko":{"title":"스탠포드와 아크 연구소는 AI를 활용해 새로운 바이러스 게놈을 설계했으며, 실험실에서 16종의 박테리아가 성공적으로 죽였습니다","summary":"스탠퍼드 대학교와 아크 연구소의 팀은 AI 모델 Evo를 사용해 완전한 바이러스 게놈을 처음부터 설계하고, 실험실에서 자연에 존재하지 않는 16개의 기능성 바이러스를 만들었습니다. Evo는 70만 개의 후보 유전체를 제안했으나, 연구팀은 가장 유망한 285개 서열만 선정해 박테리아를 합성하고 이식했으며, 그중 16개가 성공적으로 복제되어 숙주를 죽였다. 이 연구는 동료 검토를 통해 Science에 게재되었으나, Evo는 인간 병원체 데이터를 기반으로 훈련받지 않았으며, 다른 바이러스 그룹으로도 확장될 수 있는지는 아직 알려지지 않았습니다. 🔗 원문 기사는 AIHOT를 통해 읽을 수 있습니다. https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"업계 동향","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"스탠포드와 아크 연구소는 AI를 활용해 새로운 바이러스 게놈을 설계했으며, 실험실에서 16종의 박테리아가 성공적으로 죽였습니다 - Aioga AI 뉴스","description":"스탠퍼드 대학교와 아크 연구소의 팀은 AI 모델 Evo를 사용해 완전한 바이러스 게놈을 처음부터 설계하고, 실험실에서 자연에 존재하지 않는 16개의 기능성 바이러스를 만들었습니다. Evo는 70만 개의 후보 유전체를 제안했으나, 연구팀은 가장 유망한 285개 서열만 선정해 박테리아를 합성하고 이식했으며, 그중 16개가 성...","url":"https://www.aioga.com/ko/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:16:41.771Z"},"es":{"title":"Stanford y el Instituto Arc han utilizado IA para diseñar un genoma viral completamente nuevo, con 16 bacterias eliminadas con éxito en el laboratorio","summary":"Un equipo de la Universidad de Stanford y del Arc Institute utilizó el modelo de IA Evo para diseñar un genoma viral completo desde cero y construyó 16 virus funcionales que no existen en la naturaleza en el laboratorio. Evo propuso 700.000 genomas candidatos, pero el equipo seleccionó solo las 285 secuencias más prometedoras para sintetizar e implantar bacterias, de las cuales 16 replicaron con éxito y mataron al huésped. El estudio fue publicado en Science mediante revisión por pares, pero Evo no fue entrenado con datos de patógenos humanos, y se desconoce si puede extenderse a otros grupos virales. 🔗 Lee el artículo original a través de AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"Industria","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford y el Instituto Arc han utilizado IA para diseñar un genoma viral completamente nuevo, con 16 bacterias eliminadas con éxito en el laboratorio - Aioga Noticias de IA","description":"Un equipo de la Universidad de Stanford y del Arc Institute utilizó el modelo de IA Evo para diseñar un genoma viral completo desde cero y construyó 16 virus funcionales que no exi...","url":"https://www.aioga.com/es/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:16:40.097Z"},"fr":{"title":"Stanford et l’Arc Institute ont utilisé l’IA pour concevoir un tout nouveau génome viral, avec 16 bactéries éliminées avec succès en laboratoire","summary":"Une équipe de l’université de Stanford et de l’Arc Institute a utilisé le modèle d’IA Evo pour concevoir un génome viral complet à partir de zéro et a construit 16 virus fonctionnels qui n’existent pas dans la nature dans le laboratoire. Evo a proposé 700 000 génomes candidats, mais l’équipe n’a sélectionné que les 285 séquences les plus prometteuses pour synthétiser et implanter des bactéries, dont 16 se sont répliquées avec succès et ont tué l’hôte. L’étude a été publiée dans Science par évaluation par des pairs, mais Evo n’a pas été entraîné sur des données de pathogènes humains, et il reste inconnu si elle peut être étendue à d’autres groupes viraux. 🔗 Lisez l’article original via AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"Industrie","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford et l’Arc Institute ont utilisé l’IA pour concevoir un tout nouveau génome viral, avec 16 bactéries éliminées avec succès en laboratoire - Aioga Actualités IA","description":"Une équipe de l’université de Stanford et de l’Arc Institute a utilisé le modèle d’IA Evo pour concevoir un génome viral complet à partir de zéro et a construit 16 virus fonctionne...","url":"https://www.aioga.com/fr/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:16:59.118Z"},"de":{"title":"Stanford und das Arc Institute haben KI eingesetzt, um ein brandneues virales Genom zu entwerfen, bei dem 16 Bakterien erfolgreich im Labor getötet wurden","summary":"Ein Team der Stanford University und des Arc Institute nutzte das KI-Modell Evo, um ein vollständiges virales Genom von Grund auf zu entwerfen und entwickelte 16 funktionale Viren, die in der Natur im Labor nicht existieren. Evo schlug 700.000 Kandidatengenome vor, doch das Team wählte nur die vielversprechendsten 285 Sequenzen aus, um Bakterien zu synthetisieren und einzupflanzen, von denen 16 erfolgreich replizierten und den Wirt töteten. Die Studie wurde in Science per Peer-Review veröffentlicht, aber Evo wurde nicht auf Daten menschlicher Krankheitserreger geschult, und ob sie auf andere Virusgruppen ausgeweitet werden kann, ist noch unbekannt. 🔗 Lesen Sie den Originalartikel über AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford und das Arc Institute haben KI eingesetzt, um ein brandneues virales Genom zu entwerfen, bei dem 16 Bakterien erfolgreich im Labor getötet wurden - Aioga KI-News","description":"Ein Team der Stanford University und des Arc Institute nutzte das KI-Modell Evo, um ein vollständiges virales Genom von Grund auf zu entwerfen und entwickelte 16 funktionale Viren,...","url":"https://www.aioga.com/de/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:16:56.224Z"},"pt-BR":{"title":"Stanford e o Instituto Arc usaram IA para projetar um genoma viral totalmente novo, com 16 bactérias eliminadas com sucesso no laboratório","summary":"Uma equipe da Universidade de Stanford e do Arc Institute usou o modelo de IA Evo para projetar um genoma viral completo do zero e construiu 16 vírus funcionais que não existem na natureza no laboratório. Evo propôs 700.000 genomas candidatos, mas a equipe selecionou apenas as 285 sequências mais promissoras para sintetizar e implantar bactérias, das quais 16 se replicaram com sucesso e mataram o hospedeiro. O estudo foi publicado na revista Science por meio de revisão por pares, mas o Evo não foi treinado com dados de patógenos humanos, e se pode ser estendido para outros grupos virais ainda não se sabe. 🔗 Leia o artigo original via AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford e o Instituto Arc usaram IA para projetar um genoma viral totalmente novo, com 16 bactérias eliminadas com sucesso no laboratório - Aioga Notícias de IA","description":"Uma equipe da Universidade de Stanford e do Arc Institute usou o modelo de IA Evo para projetar um genoma viral completo do zero e construiu 16 vírus funcionais que não existem na...","url":"https://www.aioga.com/pt-BR/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:17:12.644Z"},"ru":{"title":"Стэнфорд и Институт Арк использовали искусственный интеллект для создания совершенно нового вирусного генома, в котором 16 бактерий были успешно уничтожены в лаборатории","summary":"Команда из Стэнфордского университета и Института Арк использовала модель ИИ Evo для создания полного вирусного генома с нуля и создала 16 функциональных вирусов, которые не существуют в природе в лаборатории. Evo предложила 700 000 кандидатов в геномы, но команда выбрала только наиболее перспективные 285 последовательностей для синтеза и имплантации бактерий, из которых 16 успешно воспроизводили и убивали хозяина. Исследование было опубликовано в журнале Science через рецензирование, но Evo не проходила обучение по данным о патогенах человека, и можно ли распространить его на другие вирусные группы, остаётся неизвестным. 🔗 Прочитайте оригинальную статью на сайте AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Стэнфорд и Институт Арк использовали искусственный интеллект для создания совершенно нового вирусного генома, в котором 16 бактерий были успешно уничтожены в лаборатории - Aioga Новости ИИ","description":"Команда из Стэнфордского университета и Института Арк использовала модель ИИ Evo для создания полного вирусного генома с нуля и создала 16 функциональных вирусов, которые не сущест...","url":"https://www.aioga.com/ru/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:17:12.669Z"},"ar":{"title":"استخدم ستانفورد ومعهد آرك الذكاء الاصطناعي لتصميم جينوم فيروسي جديد كليا، حيث تم قتل 16 بكتيريا بنجاح في المختبر","summary":"استخدم فريق من جامعة ستانفورد ومعهد آرك نموذج الذكاء الاصطناعي Evo لتصميم جينوم فيروسي كامل من الصفر وبنى 16 فيروسا وظيفيا لا يوجد في الطبيعة في المختبر. اقترح إيفو 700,000 جينوم مرشح، لكن الفريق اختار فقط أكثر 285 تسلسلا واعدا لتخليق وزرع البكتيريا، منها 16 نجح في تكرار وقتل المضيف. نشرت الدراسة في مجلة Science من خلال مراجعة الأقران، لكن إيفو لم يتم تدريبها على بيانات مسببات الأمراض البشرية، وما إذا كان يمكن توسيعها إلى مجموعات فيروسية أخرى لا يزال مجهولا. 🔗 اقرأ المقال الأصلي عبر AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"استخدم ستانفورد ومعهد آرك الذكاء الاصطناعي لتصميم جينوم فيروسي جديد كليا، حيث تم قتل 16 بكتيريا بنجاح في المختبر - Aioga أخبار الذكاء الاصطناعي","description":"استخدم فريق من جامعة ستانفورد ومعهد آرك نموذج الذكاء الاصطناعي Evo لتصميم جينوم فيروسي كامل من الصفر وبنى 16 فيروسا وظيفيا لا يوجد في الطبيعة في المختبر. اقترح إيفو 700,000 جينوم م...","url":"https://www.aioga.com/ar/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:17:27.526Z"},"hi":{"title":"स्टैनफोर्ड और आर्क इंस्टीट्यूट ने एक नए वायरल जीनोम को डिजाइन करने के लिए एआई का उपयोग किया है, जिसमें प्रयोगशाला में 16 बैक्टीरिया सफलतापूर्वक मारे गए हैं","summary":"स्टैनफोर्ड यूनिवर्सिटी और आर्क इंस्टीट्यूट की एक टीम ने एआई मॉडल ईवो का इस्तेमाल खरोंच से एक पूर्ण वायरल जीनोम डिजाइन करने के लिए किया और 16 कार्यात्मक वायरस बनाए जो प्रयोगशाला में प्रकृति में मौजूद नहीं हैं। ईवो ने 700,000 उम्मीदवार जीनोम का प्रस्ताव रखा, लेकिन टीम ने बैक्टीरिया को संश्लेषित करने और प्रत्यारोपित करने के लिए केवल सबसे आशाजनक 285 अनुक्रमों का चयन किया, जिनमें से 16 ने सफलतापूर्वक दोहराया और मेजबान को मार डाला। अध्ययन में प्रकाशित किया गया था विज्ञान सहकर्मी समीक्षा के माध्यम से, लेकिन इवो को मानव रोगज़नक़ डेटा पर प्रशिक्षित नहीं किया गया था, और क्या इसे अन्य वायरल समूहों तक बढ़ाया जा सकता है, यह अज्ञात है। 🔗 AIHOT के माध्यम से मूल लेख पढ़ें · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"स्टैनफोर्ड और आर्क इंस्टीट्यूट ने एक नए वायरल जीनोम को डिजाइन करने के लिए एआई का उपयोग किया है, जिसमें प्रयोगशाला में 16 बैक्टीरिया सफलतापूर्वक मारे गए हैं - Aioga AI समाचार","description":"स्टैनफोर्ड यूनिवर्सिटी और आर्क इंस्टीट्यूट की एक टीम ने एआई मॉडल ईवो का इस्तेमाल खरोंच से एक पूर्ण वायरल जीनोम डिजाइन करने के लिए किया और 16 कार्यात्मक वायरस बनाए जो प्रयोगशाला में...","url":"https://www.aioga.com/hi/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:17:28.306Z"},"it":{"title":"Stanford e l'Arc Institute hanno utilizzato l'IA per progettare un genoma virale completamente nuovo, con 16 batteri eliminati con successo in laboratorio","summary":"Un team della Stanford University e dell'Arc Institute ha utilizzato il modello AI Evo per progettare un genoma virale completo da zero e ha costruito 16 virus funzionali che non esistono in natura in laboratorio. Evo propose 700.000 genomi candidati, ma il team selezionò solo le 285 sequenze più promettenti per sintetizzare e impiantare batteri, di cui 16 replicarono con successo e uccisero l'ospite. Lo studio è stato pubblicato su Science tramite peer review, ma Evo non è stato addestrato con dati sui patogeni umani, e resta sconosciuto se possa essere esteso ad altri gruppi virali. 🔗 Leggi l'articolo originale su AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford e l'Arc Institute hanno utilizzato l'IA per progettare un genoma virale completamente nuovo, con 16 batteri eliminati con successo in laboratorio - Aioga Notizie IA","description":"Un team della Stanford University e dell'Arc Institute ha utilizzato il modello AI Evo per progettare un genoma virale completo da zero e ha costruito 16 virus funzionali che non e...","url":"https://www.aioga.com/it/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:17:43.741Z"},"nl":{"title":"Stanford en het Arc Institute hebben AI gebruikt om een gloednieuw viraal genoom te ontwerpen, waarbij 16 bacteriën succesvol in het laboratorium zijn gedood","summary":"Een team van Stanford University en het Arc Institute gebruikte het AI-model Evo om een compleet viraal genoom vanaf nul te ontwerpen en bouwde 16 functionele virussen die in de natuur in het laboratorium niet bestaan. Evo stelde 700.000 kandidaatgenomen voor, maar het team selecteerde slechts de meest veelbelovende 285 sequenties om bacteriën te synthetiseren en te implanteren, waarvan 16 succesvol repliceerden en de gastheer doodden. De studie werd gepubliceerd in Science via peer review, maar Evo was niet getraind op gegevens over menselijke ziekteverwekkers, en of het kan worden uitgebreid naar andere virale groepen is nog onbekend. 🔗 Lees het originele artikel via AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford en het Arc Institute hebben AI gebruikt om een gloednieuw viraal genoom te ontwerpen, waarbij 16 bacteriën succesvol in het laboratorium zijn gedood - Aioga AI-nieuws","description":"Een team van Stanford University en het Arc Institute gebruikte het AI-model Evo om een compleet viraal genoom vanaf nul te ontwerpen en bouwde 16 functionele virussen die in de na...","url":"https://www.aioga.com/nl/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:17:43.967Z"},"tr":{"title":"Stanford ve Arc Enstitüsü, laboratuvarda başarıyla öldürülen 16 bakteriyi kullanarak yepyeni bir viral genom tasarladı","summary":"Stanford Üniversitesi ve Arc Enstitüsü'nden bir ekip, yapay zeka modeli Evo'yu kullanarak sıfırdan tam bir viral genom tasarladı ve laboratuvarda doğada bulunmayan 16 fonksiyonel virüs inşa etti. Evo 700.000 aday genom önerdi, ancak ekip bakterileri sentezlemek ve implante etmek için sadece en umut vadeden 285 diziyi seçti; bunlardan 16'sı başarılı bir şekilde çoğaltıp konakçını öldürdü. Çalışma, Science dergisinde hakem değerlendirmesi yoluyla yayımlandı, ancak Evo insan patojen verileri üzerine eğitilmedi ve bunun diğer viral gruplara da uygulanıp uygulanamayacağı bilinmemektedir. 🔗 Orijinal makaleyi AIHOT üzerinden okuyun · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford ve Arc Enstitüsü, laboratuvarda başarıyla öldürülen 16 bakteriyi kullanarak yepyeni bir viral genom tasarladı - Aioga AI Haberleri","description":"Stanford Üniversitesi ve Arc Enstitüsü'nden bir ekip, yapay zeka modeli Evo'yu kullanarak sıfırdan tam bir viral genom tasarladı ve laboratuvarda doğada bulunmayan 16 fonksiyonel v...","url":"https://www.aioga.com/tr/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:17:59.256Z"},"vi":{"title":"Stanford và Viện Arc đã sử dụng AI để thiết kế một bộ gen virus hoàn toàn mới, với 16 vi khuẩn được tiêu diệt thành công trong phòng thí nghiệm","summary":"Một nhóm từ Đại học Stanford và Viện Arc đã sử dụng mô hình AI Evo để thiết kế bộ gen virus hoàn chỉnh từ đầu và xây dựng 16 loại virus chức năng không tồn tại trong tự nhiên trong phòng thí nghiệm. Evo đề xuất 700.000 bộ gen ứng viên, nhưng nhóm nghiên cứu chỉ chọn 285 trình tự triển vọng nhất để tổng hợp và cấy ghép vi khuẩn, trong đó 16 trình tự đã nhân bản thành công và tiêu diệt vật chủ. Nghiên cứu được công bố trên tạp chí Science thông qua phản biện đồng nghiệp, nhưng Evo không được đào tạo dựa trên dữ liệu mầm bệnh ở người, và liệu nó có thể mở rộng sang các nhóm virus khác hay không vẫn chưa rõ. 🔗 Đọc bài viết gốc qua AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford và Viện Arc đã sử dụng AI để thiết kế một bộ gen virus hoàn toàn mới, với 16 vi khuẩn được tiêu diệt thành công trong phòng thí nghiệm - Tin tức AI Aioga","description":"Một nhóm từ Đại học Stanford và Viện Arc đã sử dụng mô hình AI Evo để thiết kế bộ gen virus hoàn chỉnh từ đầu và xây dựng 16 loại virus chức năng không tồn tại trong tự nhiên trong...","url":"https://www.aioga.com/vi/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:18:00.838Z"},"id":{"title":"Stanford dan Arc Institute telah menggunakan AI untuk merancang genom virus baru, dengan 16 bakteri berhasil dibunuh di laboratorium","summary":"Sebuah tim dari Universitas Stanford dan Arc Institute menggunakan model AI Evo untuk merancang genom virus lengkap dari awal dan membangun 16 virus fungsional yang tidak ada di alam di laboratorium. Evo mengusulkan 700.000 genom kandidat, tetapi tim hanya memilih 285 urutan paling menjanjikan untuk mensintesis dan menanamkan bakteri, di mana 16 di antaranya berhasil mereplikasi dan membunuh inang. Studi ini dipublikasikan di Science melalui tinjauan sejawat, namun Evo tidak dilatih berdasarkan data patogen manusia, dan apakah data ini dapat diperluas ke kelompok virus lain masih belum diketahui. 🔗 Baca artikel asli melalui AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford dan Arc Institute telah menggunakan AI untuk merancang genom virus baru, dengan 16 bakteri berhasil dibunuh di laboratorium - Berita AI Aioga","description":"Sebuah tim dari Universitas Stanford dan Arc Institute menggunakan model AI Evo untuk merancang genom virus lengkap dari awal dan membangun 16 virus fungsional yang tidak ada di al...","url":"https://www.aioga.com/id/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:18:15.235Z"},"th":{"title":"สแตนฟอร์ดและสถาบัน Arc ได้ใช้ AI ในการออกแบบจีโนมไวรัสใหม่ โดยมีแบคทีเรีย 16 ชนิดถูกฆ่าสําเร็จในห้องปฏิบัติการ","summary":"ทีมจากมหาวิทยาลัยสแตนฟอร์ดและสถาบัน Arc ใช้โมเดล AI Evo ในการออกแบบจีโนมไวรัสครบวงจรตั้งแต่ศูนย์ และสร้างไวรัสที่ใช้งานได้จริง 16 ตัวซึ่งไม่มีอยู่ในธรรมชาติในห้องแล็บ Evo เสนอจีโนมผู้สมัคร 700,000 ตัว แต่ทีมงานเลือกเพียง 285 ลําดับที่มีแนวโน้มดีที่สุดเพื่อสังเคราะห์และฝังแบคทีเรีย ซึ่ง 16 ลําดับสามารถจําลองและฆ่าเจ้าบ้านได้สําเร็จ การศึกษานี้ได้รับการตีพิมพ์ในวารสาร Science ผ่านการตรวจสอบโดยผู้เชี่ยวชาญ แต่ Evo ไม่ได้รับการฝึกอบรมจากข้อมูลเชื้อโรคในมนุษย์ และยังไม่ทราบว่าสามารถขยายไปยังกลุ่มไวรัสอื่น ๆ ได้หรือไม่ 🔗 อ่านบทความต้นฉบับผ่าน AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"สแตนฟอร์ดและสถาบัน Arc ได้ใช้ AI ในการออกแบบจีโนมไวรัสใหม่ โดยมีแบคทีเรีย 16 ชนิดถูกฆ่าสําเร็จในห้องปฏิบัติการ - ข่าว AI Aioga","description":"ทีมจากมหาวิทยาลัยสแตนฟอร์ดและสถาบัน Arc ใช้โมเดล AI Evo ในการออกแบบจีโนมไวรัสครบวงจรตั้งแต่ศูนย์ และสร้างไวรัสที่ใช้งานได้จริง 16 ตัวซึ่งไม่มีอยู่ในธรรมชาติในห้องแล็บ Evo เสนอจีโนม...","url":"https://www.aioga.com/th/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:18:15.723Z"},"pl":{"title":"Stanford i Instytut Arc wykorzystali sztuczną inteligencję do zaprojektowania zupełnie nowego genomu wirusowego, w którym 16 bakterii zostało skutecznie zabitych w laboratorium","summary":"Zespół ze Stanford University i Instytutu Arc wykorzystał model AI Evo do zaprojektowania kompletnego genomu wirusa od podstaw i zbudował 16 funkcjonalnych wirusów, które nie istnieją w laboratorium. Evo zaproponowało 700 000 genomów kandydatów, ale zespół wybrał tylko najbardziej obiecujące 285 sekwencji do syntezy i wszczepienia bakterii, z których 16 skutecznie się rozmnażało i zabiło gospodarza. Badanie zostało opublikowane w czasopiśmie Science w drodze recenzji, jednak Evo nie był szkolony na danych o patogenach ludzkich, a czy można je rozszerzyć na inne grupy wirusowe, pozostaje nieznane. 🔗 Przeczytaj oryginalny artykuł za pośrednictwem AIHOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Stanford i Instytut Arc wykorzystali sztuczną inteligencję do zaprojektowania zupełnie nowego genomu wirusowego, w którym 16 bakterii zostało skutecznie zabitych w laboratorium - Aioga Wiadomości AI","description":"Zespół ze Stanford University i Instytutu Arc wykorzystał model AI Evo do zaprojektowania kompletnego genomu wirusa od podstaw i zbudował 16 funkcjonalnych wirusów, które nie istni...","url":"https://www.aioga.com/pl/news/cmsiys4dz1yqironkuitnfi7t/","contentTranslated":true,"sourceHash":"f45c157e41ce9293","translatedAt":"2026-08-10T11:18:31.130Z"}},"evidenceTier":"verified-news","reviewStatus":"editorial-selected","indexable":true,"editorialCover":""}}