晨间信号Morning Signal
《科学》 第391卷 第6781期 · 2026年1月8日 · 中文解读

深度对比学习实现全基因组虚拟筛选

Deep contrastive learning enables genome-wide virtual screening · Y. Jia et al.
约 111 分钟Research Articles在小程序里点播,20 到 60 分钟做好
这篇讲什么
本文介绍了DrugCLIP,一种基于对比学习的虚拟筛选框架,其速度比传统对接快数百万倍,并在湿实验验证中成功识别出多种靶标的小分子配体。
原文开头
Deep contrastive learning enables genome- wide virtual screening Full article and list of author affiliations: https://doi.org/10.1126/ science.ads9530 Yinjun Jia†, Bowen Gao†, Jiaxin Tan†, Jiqing Zheng†, Xin Hong†, Wenyu Zhu, Haichuan Tan, Yuan Xiao, Liping Tan, Hongyi Cai, Yanwen Huang, Zhiheng Deng, Xiangwei Wu, Yue Jin, Yafei Yuan, Jiekang Tian, Wei He, Weiying Ma, Yaqin Zhang, Lei Liu*, Chuangye Yan*, Wei Zhang*, Yanyan Lan* INTRODUCTION: A substantial portion of the human druggable genome remains untargeted by small- molecule therapeutics. With the advance of protein structure prediction technologies such as AlphaFold, genome- wide drug discovery has become a more achievable goal. However, virtual screening tools that are in use now are far from meeting this need. …
摘自《科学》(Science)第391卷 第6781期 · 2026年1月8日,Y. Jia et al.。仅引用开头一小段供了解文章,版权归原刊所有,全文请阅读原刊。
晨间信号小程序码
微信扫码,在小程序里听完整版
不用登录先听一篇 · 或在微信搜索小程序 晨间信号
同期其他文章