Data-driven computational protein design.

Data-driven computational protein design.
复制标题

DOI:
10.1016/j.sbi.2021.03.009
复制
发表时间:
2021-08
影响因子:
6.8
通讯作者:
Keating AE
Keating AE
中科院分区:
生物学2区
文献类型:
--
作者:
Frappier V;Keating AE

文献摘要

参考文献

被引文献

相似文献

计算机蛋白质设计可以产生自然界中没有的蛋白质,这些蛋白质采用所需的结构并执行新的功能。尽管从理论上讲,蛋白质可以用从头算的方法来设计,但实际的成功来自于使用大量的数据来描述现有蛋白质及其变体的序列、结构和功能。我们介绍了最近在计算蛋白质设计中对多序列比对、蛋白质结构和高通量功能分析的创造性使用。方法范围从用实验数据加强基于结构的设计,到建立回归模型,再到训练产生新序列的深层神经网络。展望未来,深度学习对于最大化蛋白质设计数据的价值将变得越来越重要。
Computational protein design can generate proteins not found in nature that adopt desired structures and perform novel functions. Although proteins could, in theory, be designed with ab initio methods, practical success has come from using large amounts of data that describe the sequences, structures, and functions of existing proteins and their variants. We present recent creative uses of multiple sequence alignments, protein structures, and high-throughput functional assays in computational protein design. Approaches range from enhancing structure-based design with experimental data to building regression models to training deep neural nets that generate novel sequences. Looking ahead, deep learning will be increasingly important for maximizing the value of data for protein design.
DOI: 10.1371/journal.pcbi.1005786
发表时间: 2017-10
影响因子: 4.3
作者:
Bedbrook CN;Yang KK;Rice AJ;Gradinaru V;Arnold FH
通讯作者: Arnold FH
DOI: 10.1016/j.molcel.2018.08.033
发表时间: 2018-10-04
期刊: Molecular cell
影响因子: 16
作者:
Khersonsky O;Lipsh R;Avizemer Z;Ashani Y;Goldsmith M;Leader H;Dym O;Rogotner S;Trudeau DL;Prilusky J;Amengual-Rigo P;Guallar V;Tawfik DS;Fleishman SJ
通讯作者: Fleishman SJ
DOI: 10.1126/science.278.5335.82
发表时间: 1997-10-03
期刊: SCIENCE
影响因子: 56.9
作者:
Dahiyat, BI;Mayo, SL
通讯作者: Mayo, SL
DOI: 10.1016/s0022-2836(03)00896-9
发表时间: 2003-09-12
影响因子: 5.6
作者:
Binz, HK;Stumpp, MT;Plückthun, A
通讯作者: Plückthun, A
DOI: 10.1016/j.jmb.2005.11.036
发表时间: 2006-02-03
影响因子: 5.6
作者:
Grigoryan, G;Keating, AE
通讯作者: Keating, AE