PanGu Drug Model: learn a molecule like a human  

作　　者：Xinyuan Lin Chi Xu Zhaoping Xiong Xinfeng Zhang Ningxi Ni Bolin Ni Jianlong Chang Ruiqing Pan Zidong Wang Fan Yu Qi Tian Hualiang Jiang Mingyue Zheng Nan Qiao 

机构地区：[1]Laboratory of Health Intelligence,Huawei Cloud Computing Technologies Co.,Ltd,Guizhou 550025,China [2]Shanghai Institute for Advanced Immunochemical Studies,and School of Life Science and Technology,ShanghaiTech University,Shanghai 200031,China [3]Drug Discovery and Design Center,State Key Laboratory of Drug Research,Shanghai Institute of Materia Medica,Chinese Academy of Sciences,Shanghai 201203,China

出　　处：《Science China(Life Sciences)》2023年第4期879-882,共4页中国科学（生命科学英文版）

摘　　要：Dear Editor,Recent achievements in large-scale pre-trained models like GPT-3 and PanGu-α have demonstrated astounding performances in many downstream tasks of natural language processing (NLP),confirming AI to be user-oriented for even industrial applications.Deep learning has been recognized as the most promising technology for pharmaceuticals,a powerful molecule pre-trained model that could economize researchers’tons of time.For the strategic application of AI capabilities to the drug discovery field,we pre-trained a model called PanGu Drug Model with 1.7 billion small molecules from ZINC20 (Irwin et al.,2020),DrugSpaceX(Yang et al.,2021),and UniChem (Chambers et al.,2013).

关 键 词：FIR trained STRATEGIC 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] R91[自动化与计算机技术—控制科学与工程]