TALOS+: a hybrid method for predicting protein backbone torsion angles from NMR chemical shifts.

TALOS+: a hybrid method for predicting protein backbone torsion angles from NMR chemical shifts.
复制标题

DOI:
10.1007/s10858-009-9333-z
复制
发表时间:
2009-08
影响因子:
2.7
通讯作者:
Bax A
Bax A
中科院分区:
生物学3区
文献类型:
--
作者:
Shen Y;Delaglio F;Cornilescu G;Bax A

文献摘要

参考文献

被引文献

相似文献

蛋白质中的 NMR 化学位移很大程度上取决于局部结构。 TALOS 程序建立了 13C、15N 和 1H 化学位移与骨架扭转角 φ 和 ψ 之间的经验关系(G. Cornilescu 等人 J. Biomol. NMR. 13, 289–302, 1999)。将原始 20 个蛋白质数据库扩展到 200 个蛋白质,将可预测主链角度的残基分数从 65% 增加到 74%,同时将错误率从 3% 降低到 2.5%。在数据库片段选择过程中添加两层神经网络过滤器构成了新程序 TALOS+ 的基础,该程序进一步将预测率提高到 88.5%,而不会增加错误率。排除 TALOS 预测的 2.5% 的残基与结晶状态下观察到的残基有很大差异,预测的 φ 和 ψ 角度的精度等于 ±13°。预测和晶体结构之间的巨大差异主要限于环区域,并且对于可获得多个 X 射线结构的少数情况,此类残基通常在不同结构中以不同状态被发现。 TALOS+ 输出包括对缺少化学位移的单个残基的预测,并且该程序的神经网络组件还可以高精度地预测二级结构。
NMR chemical shifts in proteins depend strongly on local structure. The program TALOS establishes an empirical relation between 13C, 15N and 1H chemical shifts and backbone torsion angles φ and ψ (G. Cornilescu et al. J. Biomol. NMR. 13, 289–302, 1999). Extension of the original 20-protein database to 200 proteins increased the fraction of residues for which backbone angles could be predicted from 65 to 74%, while reducing the error rate from 3 to 2.5 percent. Addition of a two-layer neural network filter to the database fragment selection process forms the basis for a new program, TALOS+, which further enhances the prediction rate to 88.5%, without increasing the error rate. Excluding the 2.5% of residues for which TALOS makes predictions that strongly differ from those observed in the crystalline state, the accuracy of predicted φ and ψ angles, equals ±13°. Large discrepancies between predictions and crystal structures are primarily limited to loop regions, and for the few cases where multiple X-ray structures are available such residues are often found in different states in the different structures. The TALOS+ output includes predictions for individual residues with missing chemical shifts, and the neural network component of the program also predicts secondary structure with good accuracy.
DOI: 10.1038/2345
发表时间: 1998-10-01
期刊: NATURE STRUCTURAL BIOLOGY
影响因子: --
作者:
Cai, M;Huang, Y;Clore, GM
通讯作者: Clore, GM
DOI: 10.1110/ps.0222303
发表时间: 2003-02-01
期刊: PROTEIN SCIENCE
影响因子: 8
作者:
Hung, LH;Samudrala, R
通讯作者: Samudrala, R
DOI: 10.1006/jmbi.1993.1413
发表时间: 1993-07-20
影响因子: 5.6
作者:
ROST, B;SANDER, C
通讯作者: SANDER, C
DOI: 10.1073/pnas.0610313104
发表时间: 2007-06-05
影响因子: 11.1
作者:
Cavalli, Andrea;Salvatella, Xavier;Vendruscolo, Michele
通讯作者: Vendruscolo, Michele
DOI: 10.1007/s10858-007-9208-0
发表时间: 2008-01-01
影响因子: 2.7
作者:
Berjanskii, Mark V.;Wishart, David S.
通讯作者: Wishart, David S.