[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fi0G15sad1tQgTgkf3Xrlwo9JCIoaHe1fkoPCNNp1w9M":3},{"code":4,"msg":5,"data":6},200,"操作成功",{"id":7,"title":8,"content":9,"digest":10,"source":10,"coverPath":11,"thumbsCoverPath":12,"isTop":13,"isShow":14,"baseClick":13,"clickCount":15,"createTime":16,"typeId":17,"isNewest":18,"newsInfoTypeRespVo":19,"voiceUrl":22,"voiceSize":23,"taskId":24,"releaseTime":25,"titleEn":26,"contentEn":27,"voiceUrlEn":28,"taskIdEn":29,"voiceSizeEn":30},1583,"清华 2026 年首篇 Science 论文：AI 帮助药物虚拟筛选提速百万倍","\u003Cp>\u003Cstrong class=\"ql-lineHeight-1-75\" style=\"font-size: 18px; color: rgb(255, 153, 0);\">\tIT之家 1 月 9 日消息，清华大学 2026 年首篇 Science 论文来了，清华大学智能产业研究院（AIR）兰艳艳教授联合生命学院、化学系团队（以下简称：联合团队），创新研发 AI 驱动的超高通量药物虚拟筛选平台 DrugCLIP。\u003C\u002Fstrong>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002Fc215fa4ac51e4306b4a61b621e8d04e4.png\" width=\"752\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">目前，人类对靶向药物的探索约覆盖人体全部可成药靶点的 10%，面对数以万计的潜在靶点，如何在广阔的化学空间中快速筛选苗头化合物，已成为该领域里的瓶颈。\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">DrugCLIP 筛选速度对比传统方法实现了\u003C\u002Fspan>\u003Cstrong style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">百万倍提升\u003C\u002Fstrong>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">，同时在预测准确率上也取得显著突破。\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002F0e6be0c0eead441ba7a88c4448e15bb2.png\" width=\"670\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp class=\"ql-align-center\">\u003Cspan class=\"ql-lineHeight-1-75\" style=\"color: rgb(187, 187, 187);\">基于 DrugCLIP 的超高速全基因组虚拟筛选\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">\t依托该平台，团队首次完成了覆盖人类基因组规模的药物虚拟筛选，可覆盖约 1 万个蛋白靶点、2 万个蛋白口袋，分析筛选超过 5 亿个类药小分子，总共富集出超过 200 万个潜在活性分子，构建了目前已知最大规模的蛋白-配体筛选数据库，该数据库已免费面向全球科研社区开放。\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002F0f7560408c6f41b0b916b53169d79370.png\" width=\"796\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">\t北京时间 1 月 9 日，研究成果以《深度对比学习实现基因组级别药物虚拟筛选》（Deep contrastive learning enables genome-wide virtual screening）为题，在线发表于《科学》（Science）。\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002F62d8b835fe18410c976d2ad4b3475810.png\" width=\"801\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"color: rgb(136, 136, 136);\">【新闻来源】MSN \u003C\u002Fspan>\u003Ca href=\"https:\u002F\u002Fwww.msn.cn\u002Fzh-cn\u002Fnews\u002Fother\u002Far-AA1TRpRz?ocid=msedgntphdr&cvid=6960a044903742af84c57e4ee0ce1732&ei=102\" rel=\"noopener noreferrer\" target=\"_blank\" style=\"color: rgb(136, 136, 136);\"> https:\u002F\u002Fwww.msn.cn\u002Fzh-cn\u002Fnews\u002Fother\u002Far-AA1RTDQy?ocid=BingHp01&cvid=6936317f054647a2afcd53fafcde084a&ei\u003C\u002Fa>\u003C\u002Fp>\u003Cp class=\"ql-align-justify\">\u003Cspan style=\"color: rgb(136, 136, 136);\">（本网转发此文章，旨在为读者提供更多的信息资讯，所涉内容不构成投资、消费建议。文章事实如有疑问，请与有关方核实，文章观点非本网观点，仅供读者参考。）\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>","","https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F01\u002Fb3affee0b7af4d1cb45736261f6c15c7\u002FAI领域.jpg","https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F01\u002Fthumbs\u002Fb3affee0b7af4d1cb45736261f6c15c7\u002FAI领域.jpg",0,1,43,"2026-01-12 16:21",2,false,{"id":17,"name":20,"enName":21},"芯位视野","Xinwei Vision","https:\u002F\u002Fxinwei-dev-test.oss-cn-shenzhen.aliyuncs.com\u002Fintelligent\u002Faudio%3A6f006390-3a2d-4510-a948-f238cc8fdd5a%3A0.wav?Expires=1768375030&OSSAccessKeyId=LTAI5tNvY2RkKjZw4LLWsrPK&Signature=A1h3AOE%2By6VrMWcAcZ6H20p%2FYUY%3D",2772320,"6f006390-3a2d-4510-a948-f238cc8fdd5a","2026-01-12 16:15","Tsinghua University's first Science paper in 2026: AI helps accelerate virtual drug screening by a million times","\u003Cp>\u003Cstrong class=\"ql-lineHeight-1-75\" style=\"font-size: 18px; color: rgb(255, 153, 0);\">\tIT之家 January 9 news, Tsinghua University's first Science paper in 2026 has arrived. Professor Lan Yanyan from the Institute for Intelligent Industry of Tsinghua University (AIR) jointly developed with the School of Life Sciences and the Department of Chemistry team (hereinafter referred to as the joint team), innovatively developed an AI-driven ultra-high throughput drug virtual screening platform, DrugCLIP.\u003C\u002Fstrong>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002Fc215fa4ac51e4306b4a61b621e8d04e4.png\" width=\"752\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">Currently, human exploration of targeted drugs covers about 10% of all druggable targets in the human body. Facing tens of thousands of potential targets, how to quickly screen lead compounds in the vast chemical space has become a bottleneck in this field.\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">DrugCLIP has achieved a\u003C\u002Fspan>\u003Cstrong style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">million-fold improvement\u003C\u002Fstrong>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\"> in screening speed compared to traditional methods, and also made significant breakthroughs in prediction accuracy.\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002F0e6be0c0eead441ba7a88c4448e15bb2.png\" width=\"670\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp class=\"ql-align-center\">\u003Cspan class=\"ql-lineHeight-1-75\" style=\"color: rgb(187, 187, 187);\">Ultra-fast whole-genome virtual screening based on DrugCLIP\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">\tWith this platform, the team completed the first drug virtual screening covering the scale of the human genome, covering about 10,000 protein targets and 20,000 protein pockets, analyzing and screening more than 500 million drug-like small molecules, and finally enriching over 2 million potential active molecules, building the largest known protein-ligand screening database, which is now freely open to the global scientific community.\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002F0f7560408c6f41b0b916b53169d79370.png\" width=\"796\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-size: 18px;\" class=\"ql-lineHeight-1-75\">\tAt Beijing time on January 9, the research results were published online in Science under the title \"Deep Contrastive Learning Enables Genome-Wide Virtual Screening\".\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cimg alt=\"\" src=\"https:\u002F\u002Fimage.51xinwei.com\u002F2026\u002F03\u002Fhistory\u002F62d8b835fe18410c976d2ad4b3475810.png\" width=\"801\" height=\"null\" style=\"display: block; margin: auto;\">\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"color: rgb(136, 136, 136);\">【News Source】MSN \u003C\u002Fspan>\u003Ca href=\"https:\u002F\u002Fwww.msn.cn\u002Fzh-cn\u002Fnews\u002Fother\u002Far-AA1TRpRz?ocid=msedgntphdr&cvid=6960a044903742af84c57e4ee0ce1732&ei=102\" rel=\"noopener noreferrer\" target=\"_blank\" style=\"color: rgb(136, 136, 136);\"> https:\u002F\u002Fwww.msn.cn\u002Fzh-cn\u002Fnews\u002Fother\u002Far-AA1RTDQy?ocid=BingHp01&cvid=6936317f054647a2afcd53fafcde084a&ei\u003C\u002Fa>\u003C\u002Fp>\u003Cp class=\"ql-align-justify\">\u003Cspan style=\"color: rgb(136, 136, 136);\">（This article is reprinted by this site to provide readers with more information and resources. The content involved does not constitute investment or consumption advice. If there are any questions about the facts of the article, please verify with the relevant parties. The views expressed in the article are not the views of this site and are for reference only.）\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cbr>\u003C\u002Fp>","https:\u002F\u002Fxinwei-dev-test.oss-cn-shenzhen.aliyuncs.com\u002Fintelligent\u002Faudio%3A0d36471d-396d-4f47-bcbb-10a3a45ddd3d%3A0.wav?Expires=1774838430&OSSAccessKeyId=LTAI5tNvY2RkKjZw4LLWsrPK&Signature=aXYJ%2BfwLM8GyoT0NTgOpt%2FWcUfg%3D","0d36471d-396d-4f47-bcbb-10a3a45ddd3d",3841300]