iNeo-Vac-P01

Artificial Intelligence is transforming the phama industry for the better P01 Drug development is notoriously failure-prone.Only one in every ten drug candidates that enter human trials eventually goes onto the market.Turning a promising molecule into a useful medicine typically takes ten to 15 years after its discovery.These challenging economics mean that the cost of developing each successful drug is roughly $2.8bn. And because medicines ultimately come off-patent, the drive to find the next blockbuster is relentless. 药物研发的高失败率是众所周知的。在进入人体试验阶段的候选药物中，最终能成功上市的仅有十分之一。一个具有潜力的分子从被发现到转化为可用药物，通常需要耗费 10 至 15 年的时间。这种高难度的投入产出比意味着，每成功研发一种药物的成本约为 28 亿美元。而且，由于药物最终都会失去专利保护，制药企业不得不持续投入，力争研发出下一款 “重磅炸弹” 级药物。 failure-prone adj. 易出故障的；容易失败的；易失效的 -prone 易于...的；倾向于...的 accident-prone 易出事故的 error-prone易出错的 crisis-prone 易爆发危机的 economics  n. 经济因素，经济情况，成本效益状况 off-patent adj.专利保护到期的，不受专利保护的 blockbuster  n.一鸣惊人的作品，畅销书，大片 文中指 重磅炸弹级药物，畅销药； relentless adj.不停的，无情的；持续强烈的，不减弱的 P02 Enter generative AI,which the pharma industry is adopting at a terrific rate.By ingesting and analysing vast biological data sets, AI tools can identify promising target proteins and then suggest novel molecules that could latch onto those drug targets.They can sift through libraries of data to predict the potency and toxicity of candidates, before a single test tube is touched. AI can also help with trials, analysing health records to find the patients most likely to respond to novel treatments.Though it is still early days,the signs are promising. AI could lead to more efficient drug discovery,better medicines and more competition in the industry. 如今，生成式人工智能正以迅猛的势头被制药行业接纳应用。人工智能工具能够消化并分析海量的生物数据集，以此识别出具有潜力的目标蛋白，进而设计出可以靶向结合这些药物靶点的全新分子。在开展任何试管实验之前，人工智能就能筛选海量数据，预测候选药物的药效与毒性。此外，人工智能还能助力临床试验，通过分析健康记录，筛选出最有可能对创新疗法有反应的患者。尽管目前仍处于应用初期，但种种迹象已十分乐观。人工智能有望提高药物研发效率、催生更优质的药物，并为制药行业注入更强的竞争活力. latch onto 附着于，依附于；缠住或抓住不放； 在本文语境中指 与...靶向结合 sift through 细查，详审；筛查 P03 AI-designed molecules show an 80-90% success rate in early-stage safety trials,compared with a historical average of just 40-65%. It will be years before it becomes clear whether success rates rise in later-stage trials, too.But even if they do not, one model suggests that early-stage improvements alone could increase the success rate across the entire pipeline from 5-10% to 9-18%.The industry is also wringing efficiencies out of its business using AI,in areas from clinical documentation to HR.McKinsey reckons that if AI is fully utilised by the pharma industry-no doubt with its consultants' assistance-it could provide a boost worth $60bn-110bn annually. 在早期安全性试验中，人工智能设计的分子成功率可达 80% 至 90%，而历史平均水平仅为 40% 至 65%。至于后期临床试验的成功率是否也会随之提升，尚需数年时间才能见分晓。不过，即便后期成功率没有改善，有模型预测显示，单是早期阶段的成功率提升，就足以将整个药物研发流程的总体成功率从 5% 至 10% 提高到 9% 至 18%。与此同时，制药行业还在借助人工智能优化业务流程，覆盖从临床文档处理到人力资源管理等多个领域。麦肯锡预测，若制药行业能充分应用人工智能技术 —— 无疑这离不开咨询机构的协助 —— 每年有望新增 600 亿至 1100 亿美元的价值。 pipeline n.管道，输送管线； 文中指 药物研发管线、整套研发体系 wring v.用力拧，绞干；紧握；强行索取，榨取 wring sth out of 从中榨取，挖掘 wring- wrung-wrung efficiencies ， efficiency 的复数形式，指 效率，效能，提高功效的方法 P04 The hope is that improvements in the technology will push up the success rate even further. Sophisticated new models for understanding tricky bits of biology are emerging at a rapid pace. A few years ago an AI model called AlphaFold solved the problem of figuring out the structure of proteins.More complex puzzles,such as how cell membranes function, are likely to be cracked at some point. 人们期待技术的进一步升级能将药物研发的成功率推向更高水平。目前，用于解析复杂生物学难题的新型精密模型正层出不穷。几年前，一款名为 “阿尔法折叠” 的人工智能模型就攻克了蛋白质结构解析的难题。而像细胞膜功能机制这类更为复杂的科学谜题，相信在不久的将来也终将被破解。 tricky bits of biology  生物学中的棘手难题；复杂难懂、难以攻克的生物学领域问题 bits 指 具体的问题、领域、部分，这里相当于aspects crack  v.击败；战胜，破解 P05 The technology is already changing how the pharma industry works.A new generation of AI-native biotech startups-particularly in America and China-is emerging. Pharma companies are increasingly forming alliances with AI-biotech firms,as well as with technology giants including Amazon,Google,Microsoft and Nvidia.And those big tech firms have their own ambitions in health.Isomorphic Labs, a spin-out from Google DeepMind, is trying to design entirely new thera-peutic molecules from scratch inside a computer. Nvidia,too,has a generative-AI platform for drug discovery. Both firms are signing deals to offer design services to pharma companies.And in October Nvidia teamed up with Eli Lilly,the world's most valuable drugmaker,to build the pharma industry's most powerful supercomputer. 人工智能技术已然在改变制药行业的运作模式。新一代原生人工智能生物技术初创企业正在崛起，尤以美国和中国为盛。制药企业正愈发频繁地与人工智能生物科技公司展开合作，同时也在携手亚马逊、谷歌、微软、英伟达等科技巨头。这些科技巨头自身也在医疗健康领域怀揣着雄心壮志。谷歌旗下深度思维公司分拆出的同构实验室，正致力于在计算机中从零开始设计全新的治疗性分子。英伟达同样推出了用于药物研发的生成式人工智能平台。这两家公司都在与制药企业签约，提供药物设计服务。同年 10 月，英伟达还与全球市值最高的制药企业礼来公司合作，共同打造制药行业算力最强的超级计算机。 spin-out  n.衍生企业；（车辆）侧滑； from scratch 从零开始，从头做起，白手起家 P06 All this means that some of the value of drug discovery maybe captured by tech giants.For now,pharma firms have many clear advantages,including heaps of data,scientists who know the field and long experience of shepherding new drugs through a maze of regulation.Over time, though, as parts of biology become more of a computational problem that can be solved with technology, such advantages could be eroded.Pharma firms may need to buy in AI expertise in the same way that they buy early-stage assets from biotech firms today. 这一切都意味着，药物研发的部分价值或许将被科技巨头攫取。目前来看，制药企业仍坐拥诸多显著优势，包括海量的数据积累、深耕该领域的科研人才，以及引导新药通过繁杂监管审批流程的丰富经验。然而，随着生物学领域的部分研究逐渐转变为可通过技术手段解决的计算问题，制药企业的这些传统优势可能会被逐渐削弱。未来，制药企业或许需要像如今从生物科技公司收购早期研发项目一样，主动引进人工智能专业技术。 shepherd v.带领;引领;护送 erode v.侵蚀，削弱； P07 As drug discovery becomes more efficient,governments will need to turn their attention to other potential bottlenecks in the system,such as regulation and trials. America's Food and Drug Administration and the European Medicines Agency are themselves starting to use AI to screen the mountains of data they receive. As the number of drug candidates rises,faster regulatory reviews will be needed to avoid a logjam.Governments could also do more to encourage the sharing of patient data with  AI companies in privacy-preserving ways so that AI models-and drug discovery-can improve. 随着药物研发效率的提升，各国政府需要将目光投向该体系中其他潜在的瓶颈环节，例如监管审批与临床试验流程。美国食品药品监督管理局和欧洲药品管理局已开始运用人工智能技术，筛选其接收的海量数据。随着候选药物数量的不断增加，监管机构需要加快审批速度，避免出现审批积压的情况。各国政府还可以进一步采取措施，鼓励以保护隐私的方式，向人工智能企业共享患者数据，从而推动人工智能模型优化升级，助力药物研发进程。 logjam n. (因事情太多造成的)困境，僵局； P08 Time to get AI-pilled Patents,too,will need rethinking.Today,long patent lives let pharma firms recoup the investments they make,encouraging them to undertake the risky business of drug discovery.Yet if the costs and riskiness of innovation fall dramatically,then patent terms (which typically provide 10-15 years of market exclusivity) may need to become shorter.AI brings good news for drug innovation. But to ensure that it benefits both the makers and takers of new drugs, the industry and its regulators will need to adjust to this new reality. 是时候拥抱人工智能了 专利制度同样需要重新审视。如今，较长的专利保护期能让制药企业收回研发投入，从而激励它们投身于高风险的药物研发事业。但如果创新的成本与风险大幅降低，那么专利保护期限 —— 目前通常为 10 至 15 年的市场独占期 —— 或许就需要相应缩短。人工智能为药物创新带来了利好消息，但要确保这一技术既能惠及制药企业，又能造福患者，制药行业及其监管机构就必须主动适应这一新的行业现实。 recoup v.补偿，收回（成本），弥补（亏损） exclusivity n.专有权，独特性