Shukla Vaibhav Kumar, Karunanithy Gogulan, Vallurupalli Pramodh, Hansen D Flemming
Department of Structural and Molecular Biology, Division of Biosciences, University College London, London WC1E 6BT, UK.
Tata Institute of Fundamental Research Hyderabad, 36/P, Gopanpally Village, Serilingampally Mandal, Ranga Reddy District, Hyderabad 500046, India.
Sci Adv. 2024 Dec 20;10(51):eadr2155. doi: 10.1126/sciadv.adr2155.
Nuclear magnetic resonance (NMR) spectroscopy is an important technique for deriving the dynamics and interactions of macromolecules; however, characterizations of aromatic residues in proteins still pose a challenge. Here, we present a deep neural network (DNN), which transforms NMR spectra recorded on simple uniformly C-labeled samples to yield high-quality H-C correlation maps of aromatic side chains. Key to the success of the DNN is the design of NMR experiments that produce data with unique features to aid the DNN produce high-resolution spectra. The methodology was validated experimentally on protein samples ranging from 7 to 40 kDa in size, where it accurately reconstructed multidimensional aromatic H-C correlation maps, to facilitate H-C chemical shift assignments and to quantify kinetics. More generally, we believe that the strategy of designing new NMR experiments in combination with customized DNNs represents a substantial advance that will have a major impact on the study of molecules using NMR in the years to come.
核磁共振（NMR）光谱学是推导大分子动力学和相互作用的一项重要技术；然而，蛋白质中芳香族残基的表征仍然是一个挑战。在此，我们展示了一种深度神经网络（DNN），它能将在简单的均匀碳标记样本上记录的NMR光谱进行转换，以生成高质量的芳香族侧链氢 - 碳相关图谱。DNN成功的关键在于NMR实验的设计，该实验能产生具有独特特征的数据，以帮助DNN生成高分辨率光谱。该方法在大小从7到40 kDa的蛋白质样本上进行了实验验证，在这些样本中它准确地重建了多维芳香族氢 - 碳相关图谱，以促进氢 - 碳化学位移归属并量化动力学。更普遍地说，我们认为将设计新的NMR实验与定制的DNN相结合的策略代表了一项重大进展，在未来几年将对使用NMR进行分子研究产生重大影响。
