De Novo Crystal Structure Determination from Machine Learned Chemical Shifts.
Martins BalodisManuel CordovaAlbert HofstetterGraeme M DayLyndon EmsleyPublished in: Journal of the American Chemical Society (2022)
Determination of the three-dimensional atomic-level structure of powdered solids is one of the key goals in current chemistry. Solid-state NMR chemical shifts can be used to solve this problem, but they are limited by the high computational cost associated with crystal structure prediction methods and density functional theory chemical shift calculations. Here, we successfully determine the crystal structures of ampicillin, piroxicam, cocaine, and two polymorphs of the drug molecule AZD8329 using on-the-fly generated machine-learned isotropic chemical shifts to directly guide a Monte Carlo-based structure determination process starting from a random gas-phase conformation.
Keyphrases
- crystal structure
- density functional theory
- solid state
- monte carlo
- molecular dynamics
- solid phase extraction
- molecularly imprinted
- magnetic resonance
- deep learning
- molecular dynamics simulations
- public health
- high resolution
- machine learning
- emergency department
- mass spectrometry
- global health
- drosophila melanogaster