Improving fragment-based ab initio protein structure assembly using low-accuracy contact-map predictions.
Improving fragment-based ab initio protein structure assembly using low-accuracy contact-map predictions.
复制标题
DOI：
10.1038/s41467-021-25316-w
复制
发表时间：
2021-08-18
影响因子：
16.6
通讯作者：
Zhang Y
中科院分区：
文献类型：
--
作者：
Mortuza SM;Zheng W;Zhang C;Li Y;Pearce R;Zhang Y
基于序列的接触预测在辅助非同源结构建模方面已经显示出相当大的前景，但它通常需要许多同源序列和足够数量的正确接触来实现正确的折叠。在这里，我们开发了一种方法C-QUARK，它集成了多个深度学习和基于协同进化的接触图，以指导复制交换蒙特卡罗碎片组装模拟。该方法在247个非冗余蛋白上进行了测试，其中C-QUARK可以折叠75%的TM评分（模板建模评分）≥0.5的情况，这是QUARK实现的2.6倍。对于接触准确性低或同源序列少的59个案例，C-QUARK正确折叠的蛋白质是其他基于接触的折叠方法的6倍。C-QUARK还在第13届CASP（蛋白质结构预测的关键评估）实验的64个自由建模目标上进行了测试，其平均GDT_TS（全局距离测试）得分比最佳CASP预测器高5%。这些数据以稳健的方式展示了使用低精度和稀疏接触图预测建模非同源蛋白质结构的进展。从序列中预测蛋白质结构仍然不可能对所有蛋白质进行。在这里，作者介绍了一种整合深度学习和蛋白质协同进化信息的方法，以更准确地指导非同源蛋白质结构的预测。
Sequence-based contact prediction has shown considerable promise in assisting non-homologous structure modeling, but it often requires many homologous sequences and a sufficient number of correct contacts to achieve correct folds. Here, we developed a method, C-QUARK, that integrates multiple deep-learning and coevolution-based contact-maps to guide the replica-exchange Monte Carlo fragment assembly simulations. The method was tested on 247 non-redundant proteins, where C-QUARK could fold 75% of the cases with TM-scores (template-modeling scores) ≥0.5, which was 2.6 times more than that achieved by QUARK. For the 59 cases that had either low contact accuracy or few homologous sequences, C-QUARK correctly folded 6 times more proteins than other contact-based folding methods. C-QUARK was also tested on 64 free-modeling targets from the 13th CASP (critical assessment of protein structure prediction) experiment and had an average GDT_TS (global distance test) score that was 5% higher than the best CASP predictors. These data demonstrate, in a robust manner, the progress in modeling non-homologous protein structures using low-accuracy and sparse contact-map predictions. Predicting protein structure from sequence is still not possible for all proteins. Here, the authors introduce a method that integrates deep learning and information about protein co-evolution to guide the prediction of non-homologous protein structures with greater accuracy.
登录
查看更多内容
DOI：
10.1093/bioinformatics/btx781
发表时间：
2018-05-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Adhikari B;Hou J;Cheng J
通讯作者：
Cheng J
影响因子：
2.7
作者：
LIU, DC;NOCEDAL, J
通讯作者：
NOCEDAL, J
影响因子：
2.9
作者：
Abriata, Luciano A.;Tamo, Giorgio E.;Dal Peraro, Matteo
通讯作者：
Dal Peraro, Matteo
影响因子：
5.8
作者：
Cheng, JL;Baldi, P
通讯作者：
Baldi, P
影响因子：
5.8
作者：
He, Baoji;Mortuza, S. M.;Zhang, Yang
通讯作者：
Zhang, Yang