FID-Net: A versatile deep neural network architecture for NMR spectral reconstruction and virtual decoupling.
FID-Net: A versatile deep neural network architecture for NMR spectral reconstruction and virtual decoupling.
复制标题
DOI：
10.1007/s10858-021-00366-w
复制
发表时间：
2021-05
影响因子：
2.7
通讯作者：
Hansen DF
中科院分区：
文献类型：
--
作者：
Karunanithy G;Hansen DF
近年来，深度神经网络（DNN）在分析和解释NMR数据方面的变革潜力已被清楚地认识到。然而，到目前为止，DNN在NMR中的大多数应用要么难以超越现有方法，要么局限于与网络训练数据非常相似的窄范围数据。这些限制阻碍了DNN在NMR中的大规模应用。为了解决这个问题，我们引入了FID-Net，这是一种受WaveNet启发的深度神经网络架构，用于对时域NMR数据进行分析。我们首先证明了这种架构在重建非均匀采样（NUS）生物分子NMR光谱的有效性。结果表明，一个单一的网络是能够重建一个不同的范围内的2D NUS光谱已获得任意的采样时间表，扫描宽度的范围内，和各种其他的采集参数。在这种情况下，训练的FID网络的性能超过或匹配目前用于重建NUS NMR谱的现有方法。其次，我们提出了一种基于FID-Net架构的网络，该网络可以在单次分析中有效地对HNCA蛋白质NMR光谱中的13 C α-13 C β偶联进行解耦，同时保留甘氨酸残基不受调制。这些DNN能够在广泛的场景中有效地工作，而无需重新训练，为它们在分析NMR数据中的广泛使用铺平了道路。在线版本包含补充材料，可通过10.1007/s10858-021-00366-w获得。
In recent years, the transformative potential of deep neural networks (DNNs) for analysing and interpreting NMR data has clearly been recognised. However, most applications of DNNs in NMR to date either struggle to outperform existing methodologies or are limited in scope to a narrow range of data that closely resemble the data that the network was trained on. These limitations have prevented a widescale uptake of DNNs in NMR. Addressing this, we introduce FID-Net, a deep neural network architecture inspired by WaveNet, for performing analyses on time domain NMR data. We first demonstrate the effectiveness of this architecture in reconstructing non-uniformly sampled (NUS) biomolecular NMR spectra. It is shown that a single network is able to reconstruct a diverse range of 2D NUS spectra that have been obtained with arbitrary sampling schedules, with a range of sweep widths, and a variety of other acquisition parameters. The performance of the trained FID-Net in this case exceeds or matches existing methods currently used for the reconstruction of NUS NMR spectra. Secondly, we present a network based on the FID-Net architecture that can efficiently virtually decouple 13Cα-13Cβ couplings in HNCA protein NMR spectra in a single shot analysis, while at the same time leaving glycine residues unmodulated. The ability for these DNNs to work effectively in a wide range of scenarios, without retraining, paves the way for their widespread usage in analysing NMR data. The online version contains supplementary material available at 10.1007/s10858-021-00366-w.
登录
查看更多内容
影响因子：
2.7
作者：
Helmus JJ;Jaroniec CP
通讯作者：
Jaroniec CP
影响因子：
64.8
作者：
Bouvignies, Guillaume;Vallurupalli, Pramodh;Hansen, D. Flemming;Correia, Bruno E.;Lange, Oliver;Bah, Alaji;Vernon, Robert M.;Dahlquist, Frederick W.;Baker, David;Kay, Lewis E.
通讯作者：
Kay, Lewis E.
影响因子：
15
作者：
Hyberts, Sven G.;Takeuchi, Koh;Wagner, Gerhard
通讯作者：
Wagner, Gerhard
影响因子：
0.6
作者：
Bostock, Mark;Nietlispach, Daniel
通讯作者：
Nietlispach, Daniel
影响因子：
16.6
作者：
Qu, Xiaobo;Huang, Yihui;Chen, Zhong
通讯作者：
Chen, Zhong