Twenty years ago, The Economist ran(刊登，发表) a story about a factory that could make dragons. It was an April Fool(愚人节玩笑), based on the idea that living cells could be modelled accurately inside computers. At the time, that idea was a fantasy. But the flourishing(蓬勃发展) of artificial intelligence in the intervening( intervening 期间的) decades appears to have brought it closer to reality(让……更接近现实). A sign of progress came on October 7th, when the Virtual Biology Initiative (VBI)(虚拟生物学倡议), a project to collect the data needed to create predictive models of how cells behave and change, announced that it had received commitments(承诺资金) worth $800m since its launch in April.
二十年前，《经济学人》刊登过一篇关于“造龙工厂”的报道。那是一个愚人节玩笑，其设想是活细胞可以在计算机中被精确建模。在当时，这个想法纯属幻想。但在此后几十年间，人工智能的蓬勃发展似乎让这一幻想离现实更近了一步。2026年10月7日出现了一个进展迹象：虚拟生物学倡议（VBI）宣布，自4月启动以来，该项目已获得价值8亿美元的承诺资金。VBI旨在收集必要数据，以创建能够预测细胞行为与变化的模型。
The VBI’s goals are medical. Predictive models will let researchers design more effective drugs that are more likely to pass successfully through clinical trials(临床试验). But, if that works, future generations of models might be used to design modified versions of existing organisms, such as crop plants—and perhaps, eventually, entirely new living things.(但如果这一目标实现，未来几代模型或许还能用来设计现有生物体的改良版本，比如农作物——甚至最终可能设计出全新的生命体。)
VBI的目标是医学性的。预测模型将让研究人员设计出更有效的药物，使其更有可能顺利通过临床试验。但如果这一目标实现，未来几代模型或许还能用来设计现有生物体的改良版本，比如农作物——甚至最终可能设计出全新的生命体。
Remixing biology
重新混合生物学
The technology that has made such advances conceivable(可想象的，可设想的) is deep learning, wherein(其中，在其中) large neural networks are trained to tackle complex problems. It is this technique that underpins the foundation models that power the chatbots marketed by firms such as Anthropic, Google and OpenAI.(正是这项技术支撑着基础模型，而基础模型又驱动着Anthropic、谷歌和OpenAI等公司销售的聊天机器人。) To such models, the long-chain molecules at the heart of biology (nucleic acids and proteins) are no different from the chains of words in human writing. Letting foundation models(基础模型) loose on them was thus an obvious idea. And it is proving extraordinarily(极其，非凡地) productive.
让这些进展变得可能的技术是深度学习，即训练大型神经网络来解决复杂问题。正是这项技术支撑着基础模型，而基础模型又驱动着Anthropic、谷歌和OpenAI等公司销售的聊天机器人。对这类模型而言，生物学核心的长链分子（核酸和蛋白质）与人类写作中的词链并无不同。因此，让基础模型去处理这些分子是一个显而易见的想法。而事实证明，它的成效极其显著。
Virus ex machina
机器造病毒
