How AI helps scientists design the next generation of medicines(AI 如何幫助科學家設計下一代藥物)
How AI helps scientists design the next generation of medicines(AI 如何幫助科學家設計下一代藥物)
來源: MIT Technology Review Insights(與 AstraZeneca 合作) 原文日期: 2026-07-23
中文摘要
本文探討 AI 如何重塑生物製藥的研發流程。AstraZeneca 的 Puja Sapra 說明其採用「build-measure-learn」循環:AI 計算生成候選分子,科學家只對排名最高的分子進行實驗室測試,大幅縮短迭代周期。McKinsey 估計生成式 AI 可將藥物發現時間縮短多達 50%。AstraZeneca 正在劍橋 Kendall Square 建設「未來實驗室」,整合 AI、機器人自動化和數據管道形成封閉式發現系統。終極目標是「de novo design」——AI 從零開始生成全新的蛋白質序列。關鍵洞察
原文關鍵句(英文保留)
> "Drugging the undruggable is becoming a reality. These technologies will eventually enable us to develop medicines against targets once thought impossible to reach."> "Engineers are designing systems that generate, validate, and learn at speed... The problems are genuinely hard: multimodal data fusion, closed-loop optimization, uncertainty quantification, and interpretability at the point of clinical decision-making."