Protein tertiary structure prediction and refinement using deep learning and Rosetta in CASP14.
Protein tertiary structure prediction and refinement using deep learning and Rosetta in CASP14.
复制标题
作者：
Anishchenko I;Baek M;Park H;Hiranuma N;Kim DE;Dauparas J;Mansoor S;Humphreys IR;Baker D
trRosetta结构预测方法采用深度学习生成预测残差-残差距离和方向分布，并以此为基础构建3D模型。我们试图通过结合语言模型嵌入和模板信息作为输入（除了序列信息外）来改进该方法，这些信息是根据序列与目标的相似性加权的。我们还开发了一个改进管道，利用DeepAccNet精度预测器指导的trRosetta版本，重新组合无模板和模板生成的模型。基准测试和CASP结果都表明，新的管道比原来的trRosetta有了很大的改进，并且速度更快，需要的计算资源更少，在CASP14中位数< 3小时完成整个建模过程。我们的人类团队主要通过识别额外的同源序列输入到网络中来改进这个管道的结果。我们还使用DeepAccNet精度预测器来指导Rosetta高分辨率细化提交在常规和细化类别；虽然在CASP的相对尺度上表现相当好，但总体上的改进相当有限，部分原因是缺少域间或链间的接触。
The trRosetta structure prediction method employs deep learning to generate predicted residue‐residue distance and orientation distributions from which 3D models are built. We sought to improve the method by incorporating as inputs (in addition to sequence information) both language model embeddings and template information weighted by sequence similarity to the target. We also developed a refinement pipeline that recombines models generated by template‐free and template utilizing versions of trRosetta guided by the DeepAccNet accuracy predictor. Both benchmark tests and CASP results show that the new pipeline is a considerable improvement over the original trRosetta, and it is faster and requires less computing resources, completing the entire modeling process in a median < 3 h in CASP14. Our human group improved results with this pipeline primarily by identifying additional homologous sequences for input into the network. We also used the DeepAccNet accuracy predictor to guide Rosetta high‐resolution refinement for submissions in the regular and refinement categories; although performance was quite good on a CASP relative scale, the overall improvements were rather modest in part due to missing inter‐domain or inter‐chain contacts.
登录
查看更多内容
影响因子：
2.9
作者：
Haas J;Barbato A;Behringer D;Studer G;Roth S;Bertoni M;Mostaguir K;Gumienny R;Schwede T
通讯作者：
Schwede T
影响因子：
16.6
作者：
Hiranuma N;Park H;Baek M;Anishchenko I;Dauparas J;Baker D
通讯作者：
Baker D
影响因子：
14.9
作者：
Paez-Espino D;Chen IA;Palaniappan K;Ratner A;Chu K;Szeto E;Pillay M;Huang J;Markowitz VM;Nielsen T;Huntemann M;K Reddy TB;Pavlopoulos GA;Sullivan MB;Campbell BJ;Chen F;McMahon K;Hallam SJ;Denef V;Cavicchioli R;Caffrey SM;Streit WR;Webster J;Handley KM;Salekdeh GH;Tsesmetzis N;Setubal JC;Pope PB;Liu WT;Rivers AR;Ivanova NN;Kyrpides NC
通讯作者：
Kyrpides NC
影响因子：
2.9
作者：
Park, Hahnbeom;Lee, Gyu Rie;Baker, David
通讯作者：
Baker, David
DOI：
10.1073/pnas.1719115115
发表时间：
2018-03-20
影响因子：
11.1
作者：
Park, Hahnbeom;Ovchinnikov, Sergey;Baker, David
通讯作者：
Baker, David