Characterising Aromatic Side Chains in Proteins through the Synergistic Development of NMR Experiments and Deep Neural Networks
Preprint
Abstract
Nuclear magnetic resonance (NMR) spectroscopy has become an important technique in structural biology for characterising the structure, dynamics and interactions of macromolecules. While a plethora of NMR methods are now available to inform on backbone and methyl-bearing side-chains of proteins, a characterisation of aromatic side chains is more challenging and often requires specific labelling or 13 C-detection. Here we present a deep neural network (DNN) named FID-Net-2, which transforms NMR spectra recorded on simple uniformly 13 C labelled samples to yield high-quality 1 H- 13 C correlation spectra of the aromatic side chains. Key to the success of the DNN is the design of a complementary set of NMR experiments that produce spectra with unique features to aid the DNN produce high-resolution aromatic 1 H- 13 C correlation spectra with accurate intensities. The reconstructed spectra can be used for quantitative purposes as FID-Net-2 predicts uncertainties in the resulting spectra. We have validated the new methodology experimentally on protein samples ranging from 7 to 40 kDa in size. We demonstrate that the method can accurately reconstruct high resolution two-dimensional aromatic 1 H- 13 C correlation maps, high resolution three-dimensional aromatic-methyl NOESY spectra to facilitate aromatic 1 H- 13 C assignments, and that the intensities of peaks from the reconstructed aromatic 1 H- 13 C correlation maps can be used to quantitatively characterise the kinetics of protein folding. More generally, we believe that this strategy of devising new NMR experiments specifically for analysis using customised DNNs represents a substantial advance that will have a major impact on the study of molecules using NMR in the years to come.Keywords
This publication has 48 references indexed in Scilit:
- FID-Net: A versatile deep neural network architecture for NMR spectral reconstruction and virtual decouplingJournal of Biomolecular NMR, 2021
- Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep LearningAngewandte Chemie, 2019
- Using Deep Neural Networks to Reconstruct Non-uniformly Sampled NMR SpectraJournal of Biomolecular NMR, 2019
- Optimal Isotope Labeling of Aromatic Amino Acid Side Chains for NMR Studies of Protein Dynamics2019
- Arginine Side‐Chain Hydrogen Exchange: Quantifying Arginine Side‐Chain Interactions in SolutionChemphyschem, 2018
- Nmrglue: an open source Python package for the analysis of multidimensional NMR dataJournal of Biomolecular NMR, 2013
- Probing Arginine Side‐Chains and Their Dynamics with Carbon‐Detected NMR Spectroscopy: Application to the 42 kDa Human Histone Deacetylase 8 at High pHAngewandte Chemie International Edition, 2013
- NMRPipe: A multidimensional spectral processing system based on UNIX pipesJournal of Biomolecular NMR, 1995
- Resolution enhancement and spectral editing of uniformly 13C-enriched proteins by homonuclear broadband 13C decouplingJournal of Magnetic Resonance (1969), 1992
- A constant-time 2D overbodenhausen experiment for inverse correlation of isotopically enriched speciesJournal of Magnetic Resonance (1969), 1992