3=1+2:how the divide conquered de novo protein structure prediction and what is next?  

作　　者：Yaoqi Zhou Thomas Litfin Jian Zhan 

机构地区：[1]Institute of Systems and Physical Biology,Shenzhen Bay Laboratory,China [2]Institute for Glycomics,Griffith University,Australia

出　　处：《National Science Review》2023年第12期54-59,共6页国家科学评论（英文版）

基　　金：supported by the National Key Research and Development Program of China(2021YFF1200400);the Major Program of Shenzhen Bay Laboratory(S201101001);a Griffith University Postgraduate Fellowship。

摘　　要：Protein structure prediction has been a challenging problem for>60 years.Its progress has been considered incremental for the past 20 years until leaps were made by Alpha Fold that seemed to suddenly reach experimental accuracy.We argue that this unexpected success in 3D structure prediction was foreshadowed by prior advances in predicting 1D backbone structures and 2D side-chain distance maps in continuous angle and distance space as well as the embedding of these 1D and 2D features for end-to-end learning.

关 键 词：structure BACKBONE EMBEDDING 

分 类 号：Q51[生物学—生物化学]