Moutzouri, PinelopiCordova, Manuelde Almeida, Bruno SimoesTorodii, DariaEmsley, Lyndon2023-05-082023-05-082023-05-082023-04-1810.1002/anie.202301963https://infoscience.epfl.ch/handle/20.500.14299/197314WOS:000974684100001One key bottleneck of solid-state NMR spectroscopy is that H-1 NMR spectra of organic solids are often very broad due to the presence of a strong network of dipolar couplings. We have recently suggested a new approach to tackle this problem. More specifically, we parametrically mapped errors leading to residual dipolar broadening into a second dimension and removed them in a correlation experiment. In this way pure isotropic proton (PIP) spectra were obtained that contain only isotropic shifts and provide the highest H-1 NMR resolution available today in rigid solids. Here, using a deep-learning method, we extend the PIP approach to a second dimension, and for samples of L-tyrosine hydrochloride and ampicillin we obtain high resolution H-1-H-1 double-quantum/single-quantum dipolar correlation and spin-diffusion spectra with significantly higher resolution than the corresponding spectra at 100 kHz MAS, allowing the identification of previously overlapped isotropic correlation peaks.Chemistry, MultidisciplinaryChemistryh-1 resolutionisotropicmachine learningmagic angle spinningnmr spectroscopycrystal-structure predictionhigh-resolution nmr100 khz maspowder crystallographyc-13 nmrspectroscopyspectrah-1sensitivitycomplexestext::journal::journal article::research article